WO2021115190A1 - Indwelling needle that achieves needle tip positioning in image environment - Google Patents

Indwelling needle that achieves needle tip positioning in image environment Download PDF

Info

Publication number
WO2021115190A1
WO2021115190A1 PCT/CN2020/133557 CN2020133557W WO2021115190A1 WO 2021115190 A1 WO2021115190 A1 WO 2021115190A1 CN 2020133557 W CN2020133557 W CN 2020133557W WO 2021115190 A1 WO2021115190 A1 WO 2021115190A1
Authority
WO
WIPO (PCT)
Prior art keywords
needle
image
indwelling needle
positioning
layer
Prior art date
Application number
PCT/CN2020/133557
Other languages
French (fr)
Chinese (zh)
Inventor
朱锐
Original Assignee
深圳市中科微光医疗器械技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市中科微光医疗器械技术有限公司 filed Critical 深圳市中科微光医疗器械技术有限公司
Publication of WO2021115190A1 publication Critical patent/WO2021115190A1/en

Links

Images

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61MDEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M5/00Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
    • A61M5/14Infusion devices, e.g. infusing by gravity; Blood infusion; Accessories therefor
    • A61M5/158Needles for infusions; Accessories therefor, e.g. for inserting infusion needles, or for holding them on the body
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/11Region-based segmentation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61MDEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M2205/00General characteristics of the apparatus
    • A61M2205/60General characteristics of the apparatus with identification means
    • A61M2205/6063Optical identification systems

Definitions

  • the invention relates to an indwelling needle, in particular to an indwelling needle for realizing needle tip positioning in an image environment.
  • intravenous injection can bring direct and effective treatment to patients by injecting drugs directly into the vein.
  • intravenous injection is an invasive treatment method, and the injection needle needs to be inserted into the blood vessel under the skin. Such an invasive behavior will bring pain to the patient.
  • repeated intravenous infusion will cause multiple injuries to the patient.
  • the use of indwelling needles can allow patients to avoid repeated punctures, reduce the pain of patients, and reduce the workload of medical staff.
  • the widely used indwelling needles cannot provide feedback to the position of the needle tip of the medical staff.
  • Medical staff need to rely on personal experience and hand feeling to judge whether the indwelling needle is accurately inserted into the target blood vessel without piercing the blood vessel, which makes the medical staff The difficulty of the work increases.
  • a blood vessel imager that can determine the position of a blood vessel has appeared, but it is difficult to determine the position of the needle tip.
  • the prior art U.S. Pat. No. 9247906 publication date: 2016-02-02, describes a method and system for locating the position of a needle tip for intravenous infusion.
  • the system utilizes the absorption of near-infrared light by vascular protein, and uses optical equipment to form a contrast image of the needle tip and the subcutaneous tissue.
  • the system also uses optical fibers to alternately emit near-infrared light of different wavelengths, and one of the near-infrared light of one wavelength is used to locate the position of the needle tip.
  • the camera collects the reflected near-infrared light and processes it and projects it on the surface of the target area to complete the positioning of the needle tip.
  • the indwelling needle positioning system used uses the camera to capture the light emitted from the needle tip and project it to the target after processing. Area, so as to realize the positioning.
  • the light emitted by the needle tip after the optical fiber is used to guide the light is captured by the camera to realize the positioning.
  • the indwelling needle positioning technology in the prior art will cause the needle tip positioning to be not real-time because the emitted light source is not continuous, especially when the medical staff actually implement the puncture, the puncture time is short, and the positioning is not real-time. Just bigger.
  • the indwelling needle in the prior art is connected to the optical fiber, so it is necessary to use a specially prepared indwelling needle.
  • This type of indwelling needle needs to add a layer of glass to separate the optical fiber and the blood flow area to prevent the optical fiber from being contaminated.
  • This arrangement leads to The process of the indwelling needle is more complicated, and the processing difficulty and cost are also greater.
  • the gap in the needle tip will be filled with blood, causing the light path of the light source emitted from the needle tip to be affected. Obstacles will eventually lead to the gradual blurring of the positioning of the needle tip, which will affect the positioning effect.
  • the prior art can also use image processing methods to process the image of the indwelling needle, thereby predicting the position of the needle tip.
  • the image processing method only uses image processing because of excessive noise in the image.
  • the body of the indwelling needle presents the entire transparent color.
  • the color of the skin will be displayed in the image through the indwelling needle, making it impossible to locate the edge of the indwelling needle, or the edge of the indwelling needle will be unclear due to light factors, resulting in inaccurate needle tip position prediction results, which will cause needle tip positioning Inaccurate, affect the positioning effect.
  • the purpose of the present invention is to provide an indwelling needle capable of realizing needle tip positioning in an image environment, so as to solve the problems of complicated positioning and indwelling needle structure and inaccurate needle tip positioning in the prior art.
  • An indwelling needle for realizing needle tip positioning in an image environment comprising an indwelling needle body, the indwelling needle body includes a needle, and a positioning layer is arranged on the indwelling needle body; the positioning layer includes a reflective layer, so The above-mentioned reflective layer is displayed as a bright area in the image environment.
  • the positioning layer further includes a light-absorbing layer, the light-absorbing layer is displayed as a shadow area in an image environment, and the light-reflecting layer and the light-absorbing layer are staggered along the length direction of the needle.
  • the shape of the light-reflecting layer and the shape of the light-absorbing layer are both axisymmetric figures;
  • the symmetry axis of the light-reflecting layer and the light-absorbing layer is in the same straight line or arranged in parallel with the straight line where the inclined surface of the needle head is parallel to the horizontal plane and faces upward.
  • the light reflecting layer and the light absorbing layer are both rectangular.
  • the indwelling needle body further includes a bottom, a sleeve and a needle sleeve arranged along the length direction of the needle, and the needle is installed on the needle sleeve;
  • the positioning layer is arranged along the outer circumference of the bottom, sleeve and/or needle sleeve.
  • the positioning layer is arranged along the outer circumference of the needle sleeve.
  • the indwelling needle body further includes a needle handle, and the positioning layer is also arranged along the length direction of the needle handle.
  • the positioning layer includes multiple light-reflecting layers and multiple light-absorbing layers, and the area of the multiple light-reflecting layers gradually increases or decreases along the length direction of the indwelling needle.
  • the value y of the area of the light-reflecting layer with the largest area among the plurality of light-reflecting layers is:
  • a, b, h 1 , h 2 , p, q 1 and q 2 are all constant parameters, and x is the reflectance of the reflective layer; a>0, b>0, h 1 ⁇ 0, h 2 ⁇ 0, p >0, q 1 >0, q 2 >0.
  • the present invention has the following technical effects:
  • the indwelling needle provided by the present invention for realizing needle tip positioning in an image environment passes through a positioning layer provided on the indwelling needle body.
  • the positioning layer includes a reflective layer that can be displayed as a bright area in the image environment to prevent The problem that the indwelling needle body cannot be accurately displayed in the image caused by the indwelling needle image acquisition can accurately locate the position of the indwelling needle during image processing, thereby improving the accuracy of the needle tip positioning result; and the present invention only needs to be
  • the positioning can be realized by adding a positioning layer on the body of the indwelling needle, which is simpler and easier to realize than the positioning indwelling needle in the prior art;
  • the invention provides an indwelling needle that realizes needle tip positioning in an image environment.
  • a light-absorbing layer in the positioning layer noise interference near the light-reflective layer can be eliminated, so that the light-reflective layer can be accurately identified, thereby improving The accuracy of the needle point positioning result;
  • the indwelling needle provided by the present invention for realizing needle tip positioning in an image environment.
  • both the reflective layer and the light-absorbing layer are set as an axially symmetric image, the reflective layer and the light-absorbing layer can be quickly found by the image processing method.
  • the symmetry axis in the image can quickly locate the needle tip position, which improves the real-time performance of the needle tip positioning;
  • the position of the positioning layer is set at any position of the bottom, the cannula, and the outer circumference of the needle sleeve, which improves Improved the flexibility of positioning layer settings;
  • the position of the positioning layer is set on the outer circumference of the needle sleeve, so that the distance between the positioning layer and the needle tip is the shortest, reducing interference and improving It improves the accuracy of positioning layer recognition, thereby improving the real-time performance of needle tip positioning, and can also reduce the difficulty of the manufacturing process and save the material of the positioning layer;
  • the position of the positioning layer is also set on the needle handle to provide a positioning auxiliary line, thereby improving the accuracy of needle tip positioning;
  • the indwelling needle provided by the present invention for realizing needle tip positioning in an image environment gradually increases or decreases along the length of the indwelling needle by providing multiple reflective layers, so that the indwelling needle can be quickly found in the image.
  • the direction of the needle tip which can quickly locate the needle tip position, which improves the real-time positioning of the needle tip;
  • the indwelling needle provided by the present invention for realizing needle tip positioning in an image environment provides a method for determining the area of the reflective layer, and only needs to determine the material of the reflective layer to directly obtain the corresponding reflection under the highest recognition accuracy.
  • the area of the layer enables accurate identification of the reflective layer, thereby improving the accuracy of the needle tip positioning result.
  • FIG. 1 is a schematic diagram of the structure of an indwelling needle provided in an embodiment of the present invention
  • FIG. 2 is a schematic diagram of the indwelling needle provided in an embodiment of the present invention in an image environment
  • FIG. 3 is a schematic diagram of the structure of the positioning layer provided in an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of another positioning layer structure provided in an embodiment of the present invention.
  • Fig. 5 is a schematic diagram of an area model of a reflective layer provided in an embodiment of the present invention.
  • Figure 6 is a schematic diagram of a label provided in an embodiment of the present invention.
  • Fig. 7 is a schematic diagram of needle tip depth positioning provided in an embodiment of the present invention.
  • the indwelling needle provided by the present invention can identify the position of the needle tip in an infrared light environment and visually see the relative position of the needle tip and the punctured blood vessel. ; Then withdraw the puncture needle by 2 to 3 mm so that the needle tip is withdrawn into the catheter. There is no prompt for this operation in the prior art.
  • an indwelling needle for realizing needle tip positioning in an image environment is disclosed.
  • the indwelling needle body 1 includes a needle head 1-1.
  • the indwelling needle body 1 is provided with a positioning layer 2, and the positioning layer 2 includes the reflective layer 2-1, which is displayed as a bright area in the image environment.
  • the image environment specifically refers to the indwelling needle body 1 emitting infrared light and then using an image acquisition device to collect images, that is, the image of the indwelling needle body 1 is collected under the irradiation of infrared light.
  • an indwelling needle capable of realizing needle tip positioning is provided. As shown in Fig. 1, compared with ordinary indwelling needles, it has the function of realizing needle tip positioning. Because when the indwelling needle is inserted into the skin, the needle When the position cannot be seen with the naked eye, the reflective layer 2-1 of the indwelling needle provided in this embodiment can be displayed as a highlighted area on the image after imaging in an infrared light environment, as shown in Figure 2, Compared with the prior art adopting the image processing method to process the pure indwelling needle image, there is too much noise, which causes the problem of inaccurate positioning. In this embodiment, the reflective layer 2-1 is added to make the image clear By seeing the position of the reflective layer 2-1, the position of the indwelling needle can be accurately positioned during image processing, thereby improving the accuracy of the needle tip positioning result.
  • the area of the reflective layer 2-1 set on the indwelling needle body 1 is displayed as a highlight area in the image. After graying the image, the part of the highlight area is displayed as pure white in the image, as shown in Figure 2. .
  • the positional relationship between the position of the reflective layer 2-1 and the position of the needle tip is known.
  • the positional relationship can be used to obtain the position of the needle tip in the image.
  • it can be projected onto the skin, so that the medical staff can see the position of the needle tip in real time when performing a needle puncture, and compare the indwelling needle provided in this embodiment with the blood vessel in the prior art.
  • the imaging equipment is used at the same time, the position of the needle tip can be seen on the basis of the blood vessel, which can effectively prevent the indwelling needle from puncturing the blood vessel and improve the operation convenience of medical staff.
  • the indwelling needle provided in this embodiment for realizing needle tip positioning in an infrared light environment only needs to provide a positioning layer 2 on the indwelling needle body 1 and combining the image processing methods and image projection methods in the prior art to realize the needle tip positioning.
  • the positioning layer 2 further includes a light-absorbing layer 2-2, the light-absorbing layer 2-2 is displayed as a shadow area in the image environment, and the light-reflecting layer 2-1 and the light-absorbing layer 2-2 are along the length direction of the needle 1-1 Staggered settings.
  • Layer 2-2, the light-absorbing layer 2-2 and the light-reflecting layer 2-1 are arranged staggered.
  • the light-absorbing layer 2- The setting of 2 can eliminate the noise interference near the reflective layer 2-1, so that the reflective layer 2-1 can be accurately identified, and the algorithm can be used to locate the needle tip position and the catheter tip position with simple and fast calculation.
  • the arrangement of the light-reflecting layer 2-1 and the light-absorbing layer 2-2 of the positioning layer 2 can be the light-reflecting layer 2-1—the light-absorbing layer 2-2—the light-reflecting layer 2-1, or the light-absorbing layer 2- 2-reflective layer 2-1-light absorbing layer 2-2-reflective layer 2-1-light absorbing layer 2-2 and other staggered structures, taking into account the difficulty of the production process, the accuracy of recognition, and the simple algorithm
  • the time delay is low, and the light-reflecting layer 2-1, the light-absorbing layer 2-2, and the light-reflecting layer 2-1 are the best combination in the present invention.
  • the shape of the light-reflecting layer 2-1 and the shape of the light-absorbing layer 2-2 are both axially symmetrical figures;
  • the symmetry axis of the light-reflecting layer 2-1 and the light-absorbing layer 2-2 is in the same straight line or arranged in parallel with the straight line where the inclined surface of the needle 1-1 is parallel to the horizontal plane and faces upward.
  • the light-reflecting layer 2-1 and the light-absorbing layer 2-2 are both axially symmetrical, the light-reflecting layer 2-1 and the light-absorbing layer 2 can be quickly found by the image processing method.
  • -2 The axis of symmetry in the image.
  • the line where the axis of symmetry is located is the line where the needle is located.
  • the position of the needle tip can be quickly found by image processing combined with the length of the needle.
  • the shape of the positioning layer 2 can be a rectangle, a rhombus, a symmetrical triangle, etc., with axial symmetry, that is to say, as shown in FIG. 3, the light-reflecting layer 2-1 can be a rectangle and the light-absorbing layer 2-2 It can be a diamond shape.
  • the combination of the light-reflecting layer 2-1 and the light-absorbing layer 2-2 is the light-reflecting layer 2-1—the light-absorbing layer 2-2—the light-reflecting layer 2-1, as shown in FIG.
  • the shapes can be rectangular, rhombic or elliptical, and the shapes of the two reflective layers 2-1 can also be different from each other.
  • the shapes of the two light-reflecting layers 2-1 and one light-absorbing layer 2-1 may be the same or different from each other, that is, the shapes of the two light-absorbing layers 2-1 are also different from each other.
  • the light-reflecting layer 2-1 and the light-absorbing layer 2-2 are both rectangular.
  • the rectangular positioning layer 2 is selected as the optimal figure, because the rectangular area is the largest and the recognition accuracy is the highest. If other graphics can only recognize a part of the graphics due to rotation, inaccurate mark point recognition will occur, resulting in inaccurate recognition of the needle tip position and the catheter tip position.
  • the indwelling needle body 1 also includes the needle 1-1.
  • the bottom 1-2, the cannula 1-3 and the needle sleeve 1-4 are arranged in sequence in the length direction, and the needle 1-1 is installed on the needle sleeve 1-4;
  • the cannula 1-3 includes a first cannula 1-3-1, a second cannula 1-3-2, and a third cannula 1-3-3 arranged in sequence along the length direction of the needle 1-1.
  • One sleeve 1-3-1 is connected with the bottom 1-2, and the third sleeve 1-3-3 is connected with the needle sleeve 1-4;
  • the positioning layer 2 is arranged along the outer circumference of the bottom 1-2, the sleeve 1-3 and/or the needle sleeve 1-4.
  • the position of the positioning layer 2 is shown in FIG. 1, wherein the positions of the bottom 1-2, the outer circumference of the sleeve 1-3 and/or the needle sleeve 1-4 can all be used as the position of the positioning layer 2 That is to say, one or more positioning layers 2 may be provided on the indwelling needle body 1, and the arrangement of multiple positioning layers 2 can improve the accuracy of needle tip positioning, but will reduce the real-time positioning.
  • the positioning layer 2 can be provided at any position of the outer circumference of the bottom 1-2, the sleeve 1-3, and the needle sleeve 1-4, wherein due to the gap between the needle sleeve 1-4 and the needle 1-1 With the shortest distance, the field of view will be smaller, the interference will be smaller, and the accuracy of identifying the positioning layer 2 will be higher. Therefore, as shown in Figure 1, the position of the needle sleeve 1-4 is the optimal position of the positioning layer 2, and The positioning layer 2 is arranged on the outer circumference of the needle sleeve 1-4, and the manufacturing process of the positioning layer 2 is relatively low, and the material of the positioning layer 2 can be saved.
  • the indwelling needle body 1 further includes a needle handle 1-5, and the positioning layer 2 is also arranged along the length direction of the needle handle.
  • the positioning layer 2 at positions 1-5 of the needle handle is rectangular, which is used to provide a parallel line as a reference for positioning, so as to improve the recognition efficiency.
  • the positioning layer 2 includes multiple light-reflecting layers 2-1 and multiple light-absorbing layers 2-2, and the area of the multiple light-reflecting layers 2-1 gradually increases or decreases along the length direction of the indwelling needle.
  • the ratio between the areas of the two light-reflecting layers 2-1 separated by a light-absorbing layer 2-2 is between 0 and 1 or greater than 1.
  • the reflectivity of the reflective layer 2-1 depends on the concentration of the reflective material of the surface layer.
  • the reflective material of the reflective layer 2-1 required by the present invention has a reflectivity of more than 70% for near-infrared light.
  • the absorbance of near-infrared light is greater than 90%.
  • the reflective material mainly used in the medical field is light-absorbing powder, and the light-absorbing material is light-absorbing powder, which can be a multilayer composite polyester film or inorganic nanoparticles and organic coatings. Resin composite film.
  • the reflective layer 2-1 is selected from the 3A101-1 series of traditional Chinese medicine reflective powder produced by Lujia Reflective Material Company, and the light-absorbing layer 2-2 is made of near-infrared light-absorbing powder.
  • the first method is heat shrinking, and the material is directly sheathed on the indwelling needle body 1 by heat shrinking at the corresponding position;
  • the second method is to plate the material directly on the corresponding position on the indwelling needle body 1, and the third method is the adhesive method.
  • the value y of the area of the reflective layer 2-1 is Among them, a, b, h 1 , h 2 , p, q 1 and q 2 are all constant parameters, and x is the reflectance of the reflective layer 2-1; a>0, b>0, h 1 ⁇ 0, h 2 ⁇ 0, p>0, q 1 >0, q 2 >0.
  • the reflectivity and the reflective area of the reflective layer 2-1 jointly determine the accuracy of the needle tip recognition.
  • the reflective layer 2-1 has the higher the reflectivity and the reflective area, the greater the accuracy of the needle tip recognition. High, when the reflectance is more than 80% and the minimum reflective area is more than 5mm 2 , the needle tip can be accurately identified.
  • the reflective area is between 1mm 2 and 30mm 2 , where the reflectivity is x (70% ⁇ x ⁇ 100%), and the reflective area y (1mm 2 ⁇ y ⁇ 30mm 2 ), the value y of the area of the reflective layer 2-1 is
  • the schematic diagram of the model between the value of the area of the reflective layer 2-1 and the reflectance of the reflective layer 2-1 is shown in FIG. 5. According to the model, it can be concluded that when the reflective layer 2-1 is determined When using a material that is less than the same, the reflectance of the material can be obtained, so that the area of the reflective layer 2-1 can be directly obtained, so that the accuracy of needle tip recognition remains stable.
  • the indwelling needle provided in this embodiment for realizing needle tip positioning in an image environment only needs to cover the positioning layer 2 on the indwelling needle body 1 to realize the positioning function.
  • a method for constructing an indwelling needle image segmentation model is disclosed, which is used to segment the infrared image of the indwelling needle provided in the first embodiment, and segment the reflective layer area and the indwelling needle tip area from the image. , The method is executed according to the following steps:
  • Step 1 Obtain multiple indwelling needle images, wherein the indwelling needle images include multiple reflective layer areas and indwelling needle tip areas;
  • the reflective layer is arranged on the outer circumference of the needle sleeve 1-4 and the reflective layer is rectangular, and the obtained indwelling needle image is shown in FIG. 2, wherein the reflective layer area is the white area in the image.
  • images of indwelling needles of different shapes are collected.
  • the indwelling needles of different shapes can be the indwelling needles with different positions or shapes of the positioning layer 2 in the first embodiment, or indwelling needles produced by different manufacturers.
  • Step 2 Perform data enhancement on each indwelling needle image obtained in Step 1 to obtain a sample set;
  • the data enhancement method is used to For expansion, by adjusting the brightness of the image, cropping and zooming the image, adding different forms of the image, while enhancing the data, it can also collect images under different conditions of the model as much as possible, thereby improving the generalization ability of the model.
  • Step 3 Mark each reflective layer area and the indwelling needle tip area of each indwelling needle image in the sample set to obtain multiple marked indwelling needle images including the reflective layer mark area and the indwelling needle needle mark area, and obtain First set of tags;
  • the traditional full convolutional network can obtain the segmentation results of the reflective layer and the needle, it does not use their edge features to constrain the results, which may lead to the segmentation results of the network output.
  • the edge of the middle reflective layer area and the needle area is not smooth enough, the shape is distorted, and there is a certain difference between the real segmentation area of the image, so in this embodiment, a segmentation network based on multi-task is proposed, without the need to increase training samples or Under the premise of other labeling work, the target contour recognition task is introduced.
  • the target contour of the training sample can be obtained according to the edge detection algorithm.
  • the recognition accuracy of the contour is improved, so that the network can extract the contour information of the target.
  • the segmentation result of the target is optimized. Therefore, by introducing a multi-task learning mechanism, the accuracy of the network model can be improved, so as to accurately identify the reflective layer area and the needle area.
  • an edge extraction method can be used to extract the reflective layer and the edge of the needle, and then use the expansion operation to obtain the object contour, and the expansion operation uses a disk filter with a radius of 5.
  • the introduction of contour recognition tasks is mainly to alleviate the problem that traditional segmentation networks cannot capture the target structure information, and to improve the accuracy of contour recognition by training the network, and then constrain the shape of the segmentation results to achieve the purpose of improving segmentation accuracy.
  • Step 4 Using the sample set as input and the first label set and the second label set as reference output, training a fully convolutional neural network to obtain an indwelling needle image segmentation model;
  • the loss function L of the fully convolutional neural network is:
  • ⁇ 1 and ⁇ 2 are weighting factors, ⁇ 1 and ⁇ 2 are both greater than 0; x represents the xth pixel in the indwelling needle image, l mask (x) represents the xth pixel is the first label, p mask (x;l mask (x)) represents the predicted probability value of the xth pixel as the first label; l contour (x) represents the xth pixel as the second label, p contour (x; l contour (x) ) Represents the predicted probability value of the xth pixel as the second label.
  • the structure of the segmentation network provided in this embodiment uses a traditional segmentation network. Based on the feature map output by the segmentation network, a 3x3 convolution kernel is used to obtain two results, namely the segmentation result and the contour extraction result, and the convolution kernel The number of channels depends on the number of feature maps, stride is 1, and padding is 1.
  • the identified target has two reflective layer 2-1 areas and one needle area, so the number of convolution kernels is 3.
  • a method for constructing an indwelling needle image segmentation model is mainly provided.
  • the image segmentation model constructed by the model construction method in this embodiment can be applied to various types of indwelling needle images, thereby improving image segmentation.
  • This embodiment discloses a method for locating the tip of the indwelling needle image, which is used to locate the position of the tip of the indwelling needle in the image of the indwelling needle, and the method is executed according to the following steps:
  • Step A Obtain an image of the indwelling needle to be positioned, wherein the image of the indwelling needle to be positioned includes a plurality of reflective layer regions and the indwelling needle tip area;
  • the indwelling needle described in the first embodiment is used, and an image including the indwelling needle in the first embodiment is collected as the image of the indwelling needle to be positioned.
  • Step B Input the indwelling needle image to be positioned into the indwelling needle image segmentation model obtained by the indwelling needle image segmentation model construction method of the second embodiment, and obtain the mark indwelling including the reflective layer mark area and the mark area of the indwelling needle needle Needle image
  • Step C Obtain the shape information and position information of the marked area of each reflective layer from the mark indwelling needle image, and obtain the shape information and position information of the marked area of the indwelling needle needle;
  • the shape information of the marking area of the reflective layer is the shape of the reflective layer, that is, the axisymmetric image in the first embodiment, which can be an ellipse, a symmetrical triangle, or a rectangle; the shape of the marking area of the indwelling needle pillow is generally a rectangle.
  • the position information is position information of vertices of various shapes.
  • Step D according to the shape information of the marking area of each reflective layer and the shape information of the marking area of the indwelling needle tip, searching for an image with the highest similarity in the indwelling needle image database as a sample image;
  • the indwelling needle image database includes a plurality of marked indwelling needle images output by the indwelling needle image segmentation model obtained by the method for constructing the indwelling needle image segmentation model in the second embodiment; wherein each marked indwelling needle image corresponds to a scale parameter
  • P 1 is the coordinates of the center point of any reflective layer marking area
  • P 2 is the coordinates of the center point of another reflective layer marking area
  • P 3 is the coordinates of the tip point of the indwelling needle
  • P 1 is the coordinates of the center point of any reflective layer marking area
  • P 2 is the coordinates of the center point of another reflective layer marking area
  • P 3 is the coordinates of the tip point of the indwelling needle
  • a random sampling consensus algorithm can be used to find an image that best matches the reflective layer mark area and the needle mark area in the indwelling needle image to be positioned among all the images in the database.
  • the purpose of this step is to obtain the scale parameter K, and use the scale parameter K of the sample image as the scale parameter K of the indwelling needle image to be positioned.
  • Step E According to the position information of each reflective layer mark area in the mark indwelling needle image obtained in step C, obtain the center point position coordinates of the two reflective layer mark areas, which are P 1 ′ and P 2 ′, respectively;
  • the positions of the two marking areas of the reflective layer are the same as the positions of the two marking areas of the reflective layer selected when calculating the ratio parameter K of the sample image;
  • Step F Use formula II to obtain the needle tip position point coordinate P 3 ′ in the image of the indwelling needle to be positioned:
  • the position of the needle tip in the image can be calculated by formula II, and the medical staff can view the position of the needle tip in the image in real time.
  • the image coordinate system and The transformation relationship of the actual coordinate system obtains the actual position of the needle tip, and then cooperates with the existing vascular imagers on the market to determine whether the needle tip penetrates the blood vessel in real time, which further improves the convenience of operation by medical staff.
  • a method for locating the depth of the tip of the indwelling needle image is disclosed, which is used to obtain the depth of the tip of the indwelling needle, which is executed according to the following steps:
  • Step I Obtain an indwelling needle image to be positioned, wherein the indwelling needle image includes a plurality of reflective layer areas and an indwelling needle needle area;
  • Step II Using the method for positioning the tip of the indwelling needle image described in the third embodiment to obtain the coordinate P 3 ′ of the position of the tip of the indwelling needle to be positioned in the image of the indwelling needle;
  • Step III Calibrate the sample image obtained in step D when using the indwelling needle image tip positioning method in the third embodiment to obtain coordinate transformation parameters
  • P 1 is the center point of any marking area of the reflective layer
  • P 2 is the center point of the marking area of the other reflective layer
  • the indwelling needle image when the indwelling needle image is calibrated, it can be pre-calibrated for each marked indwelling needle image in the database in the third embodiment, and the sample image of the third embodiment
  • the coordinate transformation parameter of is used as the transformation parameter of the image of the indwelling needle to be positioned, which can effectively save the time of program running and improve the real-time nature of needle tip depth positioning.
  • Step IV Use formula III to obtain the depth H of the tip of the indwelling needle, in mm:
  • P 4 ′ is the position of the needle penetrating the skin in the position information of the indwelling needle needle mark area obtained in step C of the indwelling needle image needle tip positioning method of claim 2 for the indwelling needle image to be positioned obtained in step I coordinate of;
  • P 3 ′ is the needle tip position point coordinate obtained by using the indwelling needle image tip positioning method according to claim 2 for the indwelling needle image to be positioned obtained in step I;
  • P 1 ′ and P 2 ′ are the position coordinates of the center points of the two reflective layer mark areas obtained in step E of the indwelling needle image tip positioning method of claim 2 for the indwelling needle image to be positioned obtained in step I;
  • the center point coordinates of the two reflective layers can be obtained according to the segmentation results of the two reflective layers, and the two reflective layers are calculated.
  • the distance between the center points can be the distance L2, L1 represents the actual distance between the two reflective layers, which is a known quantity, then the angle 1 can be expressed as:
  • point P 4 ′ is the needle entry point between the needle and the skin. The position of this point can be obtained through the segmentation model.
  • Point P 3 ′ is the predicted needle position, so point P 4 ′ to point P 3 The image distance of ′ can be calculated; and because the angle 1 is equal to the angle 2, the formula III is obtained, and the depth information of the needle tip can be obtained simply and effectively through the formula III.
  • the similar triangle method is used to obtain the needle tip depth information proportionally.
  • the needle tip depth positioning method provided in this embodiment solves the problem It overcomes the technical difficulty of the traditional technology that the needle tip depth information cannot be obtained, and the accuracy is high, and the real-time performance is high, which can meet the requirements of medical workers in actual use.
  • a device for constructing an indwelling needle image segmentation model includes an image acquisition module, a data enhancement module, a label acquisition module, and a model training module;
  • the image acquisition module is used to acquire multiple indwelling needle images, where the indwelling needle image includes multiple reflective layer areas and the indwelling needle needle area;
  • the data enhancement module is used to perform data enhancement on each indwelling needle image obtained to obtain a sample set
  • the label acquisition module is used to mark each reflective layer area and the indwelling needle needle area in each indwelling needle image in the sample set, and obtain multiple marked indwelling needle images including the reflective layer mark area and the indwelling needle needle mark area, and obtain the first A set of labels;
  • the model training module is used to take the sample set as the input, the first label set and the second label set as the reference output, train the full convolutional neural network, and obtain the indwelling needle image segmentation model;
  • the loss function L of the fully convolutional neural network is:
  • ⁇ 1 and ⁇ 2 are weighting factors, ⁇ 1 and ⁇ 2 are both greater than 0; x represents the xth pixel in the indwelling needle image, l mask (x) represents the xth pixel is the first label, p mask (x;l mask (x)) represents the predicted probability value of the xth pixel as the first label; l contour (x) represents the xth pixel as the second label, p contour (x; l contour (x) ) Represents the predicted probability value of the xth pixel as the second label.
  • Embodiment 6 is a diagrammatic representation of Embodiment 6
  • An indwelling needle image needlepoint positioning device characterized in that the device includes an image acquisition module, an image segmentation module, an information acquisition module, a sample comparison module, a position point coordinate acquisition module, and a needlepoint position calculation module;
  • the image acquisition module is used to obtain an image of the indwelling needle to be positioned, wherein the image of the indwelling needle to be positioned includes a plurality of reflective layer regions and the indwelling needle tip area;
  • the image segmentation module inputs the indwelling needle image to be positioned into the indwelling needle image segmentation model obtained by the indwelling needle image segmentation model construction device of claim 4, and obtains the marked indwelling needle image including the reflective layer marking area and the indwelling needle tip marking area;
  • the information obtaining module is used to obtain the shape information and position information of the marked area of each reflective layer from the mark indwelling needle image, and obtain the shape information and position information of the marked area of the indwelling needle needle;
  • the sample comparison module is used to find the image with the highest similarity in the indwelling needle image database as the sample image according to the shape information of the marking area of each reflective layer and the shape information of the marking area of the indwelling needle needle;
  • the indwelling needle image database includes a plurality of marked indwelling needle images output by the indwelling needle image segmentation model obtained by the indwelling needle image segmentation model construction device of claim 4; wherein each marked indwelling needle image corresponds to a scale parameter
  • P 1 is the coordinates of the center point of any reflective layer marking area
  • P 2 is the coordinates of the center point of another reflective layer marking area
  • P 3 is the coordinates of the tip point of the indwelling needle
  • P 1 is the coordinates of the center point of any reflective layer marking area
  • P 2 is the coordinates of the center point of another reflective layer marking area
  • P 3 is the coordinates of the tip point of the indwelling needle
  • the position point coordinate obtaining module is used to obtain the center point position coordinates of the two reflective layer marking areas according to the position information of each reflective layer marking area in the obtained marking indwelling needle image, which are respectively P 1 ′ and P 2 ′; two of them are The positions of the marking areas of the two reflective layers are the same as the positions of the two marking areas of the reflective layer selected when calculating the ratio parameter K of the sample image;
  • the needle tip position calculation module is used to obtain the needle tip position point coordinate P 3 ′ in the image of the indwelling needle to be positioned by using formula II:
  • an indwelling needle image tip depth positioning device for obtaining the depth of the indwelling needle tip, characterized in that the device includes an image acquisition module, a transformation parameter acquisition module, and a needle tip depth acquisition module;
  • the image acquisition module is used to obtain an image of the indwelling needle to be positioned, wherein the image of the indwelling needle to be positioned includes a plurality of reflective layer regions and the indwelling needle tip area;
  • the transformation parameter acquisition module is used to calibrate the indwelling needle image to obtain coordinate transformation parameters
  • P 1 is the center point of any marking area of the reflective layer
  • P 2 is the center point of the marking area of the other reflective layer
  • the unit Used to obtain the depth H of the tip of the indwelling needle using formula III, the unit is mm:
  • P 4 ′ is the coordinates of the position point where the needle penetrates the skin in the position information of the needle mark area of the indwelling needle obtained by the information obtaining module of the indwelling needle image needle tip positioning device of claim 5 in the indwelling needle image to be positioned;
  • P 3 ′ is the position point coordinates of the needle tip obtained by the indwelling needle image needle tip positioning device of claim 5 for the indwelling needle image to be positioned;
  • P 1 ′ and P 2 ′ are the position coordinates of the center points of the two reflective layer mark areas obtained by the position point coordinate obtaining module of the indwelling needle image needle point positioning device of claim 2 for the obtained indwelling needle image to be positioned;
  • Embodiment 8 is a diagrammatic representation of Embodiment 8
  • an indwelling needle tip positioning system which includes an image acquisition and recognition device and an indwelling needle.
  • the indwelling needle includes an indwelling needle body 1, and the indwelling needle body 1 includes a needle 1-1, and the indwelling needle body 1 is provided with Reflective layer 2;
  • the image acquisition and recognition device includes an image acquisition module, the indwelling needle image tip positioning device in the sixth embodiment, the indwelling needle image tip depth positioning device in the seventh embodiment, a blood vessel imaging module, an image projection module, a light source module, and a power supply module;
  • the power supply module is used to supply power to the image acquisition module, the image needle tip positioning device of the indwelling needle, the image needle tip depth positioning device of the indwelling needle, the blood vessel imaging module, the image projection module and the light source module;
  • the light source module is used to project infrared light to the skin
  • the image acquisition module is used to collect an image of the indwelling needle to be positioned in an infrared light environment, where the image of the indwelling needle to be positioned includes a plurality of reflective layer areas and the indwelling needle tip area;
  • the indwelling needle image needle point positioning device is used to input the indwelling needle image to be positioned, and output the needle point position point coordinates in the indwelling needle image;
  • the indwelling needle image needle tip depth positioning device is used to input the indwelling needle image to be positioned, and output the needle tip depth in the indwelling needle image;
  • the blood vessel imaging module is used to obtain blood vessel images
  • the image projection module is used to project the blood vessel image on the skin
  • the image projection module is also used to superimpose and project the needle tip on the blood vessel image according to the coordinates of the needle tip position;
  • the image projection module is also used to project the needle tip depth on the skin.
  • the indwelling needle is the indwelling needle provided in the first embodiment for realizing the needle tip positioning under the image environment.
  • the blood vessel imaging module is used to obtain the blood vessel image.
  • the blood vessel imaging module adopts a mature blood vessel imager in the prior art.
  • the blood vessel imager also uses the blood vessels to show different images in the image under infrared irradiation. Color-realized blood vessel image acquisition.
  • the image needle tip positioning device of the indwelling needle, the needle tip depth positioning device of the indwelling needle, and the blood vessel imaging device can be integrated in a microprocessor for implementation.
  • the image acquisition module is a near-infrared sensitive photosensitive module.
  • the image acquisition module is the OV2710DVP module.
  • the light source module includes an optical lens and a near-infrared light source, wherein the near-infrared light source is a near-infrared light source with a wavelength of 700 nm to 1700 nm.
  • the near-infrared light source selects a near-infrared light source with a wavelength of 850 nm or 940 nm.
  • the image projection module when the image projection module superimposes the needle tip position and the blood vessel position on the skin, it sets a marker point to represent the needle tip position projected on the skin.
  • the marker point can be a circle, a triangle, a star, etc.
  • the color can be any color that can be displayed on the skin, such as red and green.
  • the image acquisition and recognition device further includes a fan, a button module, and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Vascular Medicine (AREA)
  • Anesthesiology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Hematology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Infusion, Injection, And Reservoir Apparatuses (AREA)

Abstract

An indwelling needle that achieves needle tip positioning in an image environment, comprising an indwelling needle body (1), the indwelling needle body (1) comprising a needle (1-1) and a positioning layer (2) being provided on the indwelling needle body (1); the positioning layer (2) comprises a light reflecting layer (2-1), the light reflecting layer (2-1) being displayed in an image under the irradiation of an infrared light of a vascular imager as a highlight area. In the indwelling needle that achieves needle tip positioning in an image environment, the positioning layer (2) is provided on the indwelling needle body (1), the positioning layer (2) comprises the light reflecting layer (2-1), and the light reflecting layer (2-1) can be displayed as a highlight area in the image environment, preventing the problem in which the indwelling needle body (1) cannot be accurately displayed in an image during indwelling needle image acquisition, the position of an indwelling needle can be accurately positioned during image processing, thereby increasing needle tip positioning result accuracy; in addition, positioning can be achieved merely by adding the positioning layer (2) to the indwelling needle body (1), and in comparison with positioning indwelling needles in the existing technology, the present invention has a simple structure and is easy to implement.

Description

一种在影像环境下实现针尖定位的留置针An indwelling needle capable of realizing needle tip positioning in image environment 技术领域Technical field
本发明涉及留置针,具体涉及一种在影像环境下实现针尖定位的留置针。The invention relates to an indwelling needle, in particular to an indwelling needle for realizing needle tip positioning in an image environment.
背景技术Background technique
在临床治疗上,静脉注射通过将药物直接注射至静脉中可以给患者带来直接有效的治疗。但是静脉注射属于有创性治疗手段,需要将注射针头扎入皮下的血管中,这样的有创行为会给患者带来痛苦。特别是,对于一些需要每日的、连续的、间歇的进行注射治疗的患者而言,重复的实施静脉输液会给患者带来多次伤害。留置针的使用则可以让患者避免重复穿刺,降低患者的痛苦,减少医务人员的工作量。In clinical treatment, intravenous injection can bring direct and effective treatment to patients by injecting drugs directly into the vein. However, intravenous injection is an invasive treatment method, and the injection needle needs to be inserted into the blood vessel under the skin. Such an invasive behavior will bring pain to the patient. In particular, for some patients who need daily, continuous, and intermittent injection therapy, repeated intravenous infusion will cause multiple injuries to the patient. The use of indwelling needles can allow patients to avoid repeated punctures, reduce the pain of patients, and reduce the workload of medical staff.
但是,目前所广泛使用的留置针并不能反馈给医务人员针尖所在的位置,医务人员需要凭借个人的经验和手感来判断留置针是否准确的扎入目标血管中且未扎穿血管,使得医务人员的工作难度增加。现有技术中已经出现了可以确定血管位置的血管成像仪,但是针尖位置较难确定。However, the widely used indwelling needles cannot provide feedback to the position of the needle tip of the medical staff. Medical staff need to rely on personal experience and hand feeling to judge whether the indwelling needle is accurately inserted into the target blood vessel without piercing the blood vessel, which makes the medical staff The difficulty of the work increases. In the prior art, a blood vessel imager that can determine the position of a blood vessel has appeared, but it is difficult to determine the position of the needle tip.
现有技术U.S.Pat.No.9247906,公开日期:2016-02-02,阐述了一种定位静脉输液针尖位置的方法和系统。系统利用血管蛋白对近红外光的吸收性,利用光学设备形成针尖与皮下组织的对比图像。此外系统中还利用了光纤交替发射不同波段的近红外光,其中一个波段的近红外光用来定位针尖的位置。之后利用相机收集反射回来的近红外光,经过处理投影在目标区域表面,完成针尖的定位,但是其所使用的留置针定位系统是利用相机捕捉从针尖处发射出去的光,处理后投影至目标区域,从而实现定位采用光纤导光之后针尖发射出去的光被相机捕捉,从而实现定位。现有技术中的留置针定位技术会因为发射光源不是连续的,所以导致针尖的定位并不是实时的,特别是在医务人员实际实施穿刺时,穿刺时间较短,定位的不实时带来的影响就更大。此外,现有技术中的留置针连接着光纤,所以需要使用专门配制的留置针,这类留置针需要增加一层玻璃去隔开光纤和血流区域,防止光纤被污染,这样的设置导致了留置针的工艺更复杂,加工难度和成本也更大,另外现有技术中的定位留置针当针尖进入血管后,针尖中的空隙会被血液充满,导致从针尖处发射出去的光源的光路受到收到阻碍,最终导致针尖 处的定位逐渐模糊,影响定位效果。The prior art U.S. Pat. No. 9247906, publication date: 2016-02-02, describes a method and system for locating the position of a needle tip for intravenous infusion. The system utilizes the absorption of near-infrared light by vascular protein, and uses optical equipment to form a contrast image of the needle tip and the subcutaneous tissue. In addition, the system also uses optical fibers to alternately emit near-infrared light of different wavelengths, and one of the near-infrared light of one wavelength is used to locate the position of the needle tip. Afterwards, the camera collects the reflected near-infrared light and processes it and projects it on the surface of the target area to complete the positioning of the needle tip. However, the indwelling needle positioning system used uses the camera to capture the light emitted from the needle tip and project it to the target after processing. Area, so as to realize the positioning. The light emitted by the needle tip after the optical fiber is used to guide the light is captured by the camera to realize the positioning. The indwelling needle positioning technology in the prior art will cause the needle tip positioning to be not real-time because the emitted light source is not continuous, especially when the medical staff actually implement the puncture, the puncture time is short, and the positioning is not real-time. Just bigger. In addition, the indwelling needle in the prior art is connected to the optical fiber, so it is necessary to use a specially prepared indwelling needle. This type of indwelling needle needs to add a layer of glass to separate the optical fiber and the blood flow area to prevent the optical fiber from being contaminated. This arrangement leads to The process of the indwelling needle is more complicated, and the processing difficulty and cost are also greater. In addition, when the needle tip enters the blood vessel, the gap in the needle tip will be filled with blood, causing the light path of the light source emitted from the needle tip to be affected. Obstacles will eventually lead to the gradual blurring of the positioning of the needle tip, which will affect the positioning effect.
另外现有技术还可以采用图像处理的方法对留置针图像进行处理,从而预测针尖的位置,但是单纯采用图像处理的方法由于图像中噪声过多,例如留置针本体呈现整个透明的颜色,在采集图像时皮肤的颜色会透过留置针显示到图像中导致没法定位到留置针的边缘或者由于光照的因素会导致留置针的边缘不清晰,导致针尖位置预测结果不准确,从而会造成针尖定位不准,影响定位效果。In addition, the prior art can also use image processing methods to process the image of the indwelling needle, thereby predicting the position of the needle tip. However, the image processing method only uses image processing because of excessive noise in the image. For example, the body of the indwelling needle presents the entire transparent color. During the image, the color of the skin will be displayed in the image through the indwelling needle, making it impossible to locate the edge of the indwelling needle, or the edge of the indwelling needle will be unclear due to light factors, resulting in inaccurate needle tip position prediction results, which will cause needle tip positioning Inaccurate, affect the positioning effect.
发明内容Summary of the invention
本发明的目的在于提供一种在影像环境下实现针尖定位的留置针,用以解决现有技术中的定位留置针结构复杂且针尖定位不准确的问题。The purpose of the present invention is to provide an indwelling needle capable of realizing needle tip positioning in an image environment, so as to solve the problems of complicated positioning and indwelling needle structure and inaccurate needle tip positioning in the prior art.
为了实现上述任务,本发明采用以下技术方案:In order to achieve the above tasks, the present invention adopts the following technical solutions:
一种在影像环境下实现针尖定位的留置针,包括留置针本体,所述的留置针本体包括针头,在所述的留置针本体上设置有定位层;所述的定位层包括反光层,所述的反光层在影像环境下显示为高亮区域。An indwelling needle for realizing needle tip positioning in an image environment, comprising an indwelling needle body, the indwelling needle body includes a needle, and a positioning layer is arranged on the indwelling needle body; the positioning layer includes a reflective layer, so The above-mentioned reflective layer is displayed as a bright area in the image environment.
进一步地,所述的定位层还包括吸光层,所述的吸光层在影像环境下显示为阴影区域,所述的反光层与所述的吸光层沿着所述针头长度方向交错设置。Further, the positioning layer further includes a light-absorbing layer, the light-absorbing layer is displayed as a shadow area in an image environment, and the light-reflecting layer and the light-absorbing layer are staggered along the length direction of the needle.
进一步地,所述的反光层的形状与吸光层的形状均为轴对称图形;Further, the shape of the light-reflecting layer and the shape of the light-absorbing layer are both axisymmetric figures;
所述的反光层与吸光层的对称轴与所述的针头斜面平行于水平面朝向上方时所在的直线处于同一条直线或与平行设置。The symmetry axis of the light-reflecting layer and the light-absorbing layer is in the same straight line or arranged in parallel with the straight line where the inclined surface of the needle head is parallel to the horizontal plane and faces upward.
进一步地,所述的反光层与所述的吸光层均为矩形。Further, the light reflecting layer and the light absorbing layer are both rectangular.
进一步地,所述的留置针本体还包括沿着所述针头长度方向设置的底部、套管以及针套筒,所述的针头安装在所述的针套筒上;Further, the indwelling needle body further includes a bottom, a sleeve and a needle sleeve arranged along the length direction of the needle, and the needle is installed on the needle sleeve;
所述的定位层沿着所述底部、套管和/或针套筒的外圆周设置。The positioning layer is arranged along the outer circumference of the bottom, sleeve and/or needle sleeve.
进一步地,所述的定位层沿着所述针套筒的外圆周设置。Further, the positioning layer is arranged along the outer circumference of the needle sleeve.
进一步地,所述的留置针本体还包括针柄,所述的定位层还沿着所述的针柄的长度方向设置。Further, the indwelling needle body further includes a needle handle, and the positioning layer is also arranged along the length direction of the needle handle.
进一步地,所述的定位层包括多个反光层以及多个吸光层,所述的多个反光层的面积沿着留置针长度方向逐渐增大或减小。Further, the positioning layer includes multiple light-reflecting layers and multiple light-absorbing layers, and the area of the multiple light-reflecting layers gradually increases or decreases along the length direction of the indwelling needle.
进一步地,所述的多个反光层中最大面积的反光层面积的数值y为:Further, the value y of the area of the light-reflecting layer with the largest area among the plurality of light-reflecting layers is:
Figure PCTCN2020133557-appb-000001
Figure PCTCN2020133557-appb-000001
其中a、b、h 1、h 2、p、q 1以及q 2均为常数参数,x为反光层的反光度;a>0,b>0,h 1<0,h 2<0,p>0,q 1>0,q 2>0。 Among them, a, b, h 1 , h 2 , p, q 1 and q 2 are all constant parameters, and x is the reflectance of the reflective layer; a>0, b>0, h 1 <0, h 2 <0, p >0, q 1 >0, q 2 >0.
本发明与现有技术相比具有以下技术效果:Compared with the prior art, the present invention has the following technical effects:
1、本发明提供的一种在影像环境下实现针尖定位的留置针通过在留置针本体上设置的定位层,该定位层包括反光层,反光层能够在影像环境下显示为高亮区域,防止留置针图像采集时带来的留置针本体在图像中无法准确显示的问题,在图像处理时能够准确地定位到留置针的位置,从而提高了针尖定位结果的准确性;并且本发明仅需在留置针本体上增加定位层即可实现定位,相比于现有技术中的定位留置针结构简单,易于实现;1. The indwelling needle provided by the present invention for realizing needle tip positioning in an image environment passes through a positioning layer provided on the indwelling needle body. The positioning layer includes a reflective layer that can be displayed as a bright area in the image environment to prevent The problem that the indwelling needle body cannot be accurately displayed in the image caused by the indwelling needle image acquisition can accurately locate the position of the indwelling needle during image processing, thereby improving the accuracy of the needle tip positioning result; and the present invention only needs to be The positioning can be realized by adding a positioning layer on the body of the indwelling needle, which is simpler and easier to realize than the positioning indwelling needle in the prior art;
2、本发明提供的本发明提供的一种在影像环境下实现针尖定位的留置针通过在定位层中设置了吸光层,可以排除反光层附近的噪点干扰,使得精准识别反光层,从而提高了针尖定位结果的准确性;2. The invention provides an indwelling needle that realizes needle tip positioning in an image environment. By providing a light-absorbing layer in the positioning layer, noise interference near the light-reflective layer can be eliminated, so that the light-reflective layer can be accurately identified, thereby improving The accuracy of the needle point positioning result;
3、本发明提供的本发明提供的一种在影像环境下实现针尖定位的留置针通过将反光层与吸光层均设置为轴对称图像时,可以通过图像处理方法迅速的找到反光层以及吸光层在图像中的对称轴,从而能够快速地定位到针尖位置,提高了针尖定位的实时性;3. The indwelling needle provided by the present invention for realizing needle tip positioning in an image environment. When both the reflective layer and the light-absorbing layer are set as an axially symmetric image, the reflective layer and the light-absorbing layer can be quickly found by the image processing method. The symmetry axis in the image can quickly locate the needle tip position, which improves the real-time performance of the needle tip positioning;
4、本发明提供的本发明提供的一种在影像环境下实现针尖定位的留置针中将定位层的位置设置在底部、套管以及针套筒的外圆周的位置的任一个位置上,提高了定位层设置的灵活性;4. In the indwelling needle provided by the present invention for realizing needle tip positioning in an imaging environment, the position of the positioning layer is set at any position of the bottom, the cannula, and the outer circumference of the needle sleeve, which improves Improved the flexibility of positioning layer settings;
5、本发明提供的一种在影像环境下实现针尖定位的留置针中将定位层的位置设置在针套筒的外圆周上,使得定位层与针尖之间的距离最短,降低了干扰,提高了定位层识别的准确性,从而提高了针尖定位的实时性,并且还可以降低制作工艺难度,节省定位层的材料;5. In an indwelling needle for realizing needle tip positioning in an image environment provided by the present invention, the position of the positioning layer is set on the outer circumference of the needle sleeve, so that the distance between the positioning layer and the needle tip is the shortest, reducing interference and improving It improves the accuracy of positioning layer recognition, thereby improving the real-time performance of needle tip positioning, and can also reduce the difficulty of the manufacturing process and save the material of the positioning layer;
6、本发明提供的一种在影像环境下实现针尖定位的留置针中将定位层的位置还设置在了针柄上,用于提供一条定位辅助线,从而提高了针尖定位的准确性;6. In an indwelling needle that realizes needle tip positioning in an image environment provided by the present invention, the position of the positioning layer is also set on the needle handle to provide a positioning auxiliary line, thereby improving the accuracy of needle tip positioning;
7、本发明提供的一种在影像环境下实现针尖定位的留置针中通过设置了多 个反光层的面积沿着留置针长度方向逐渐增大或减小,使得在图像中可以快速的找到留置针针头的方向,从而能够快速地定位到针尖位置,提高了针尖定位的实时性;7. The indwelling needle provided by the present invention for realizing needle tip positioning in an image environment gradually increases or decreases along the length of the indwelling needle by providing multiple reflective layers, so that the indwelling needle can be quickly found in the image. The direction of the needle tip, which can quickly locate the needle tip position, which improves the real-time positioning of the needle tip;
8、本发明提供的一种在影像环境下实现针尖定位的留置针通过给出了反光层面积的确定方法,仅需确定反光层的材料就可以直接获得识别准确率最高的情况下对应的反光层的面积,使得精准识别反光层,从而提高了针尖定位结果的准确性。8. The indwelling needle provided by the present invention for realizing needle tip positioning in an image environment provides a method for determining the area of the reflective layer, and only needs to determine the material of the reflective layer to directly obtain the corresponding reflection under the highest recognition accuracy. The area of the layer enables accurate identification of the reflective layer, thereby improving the accuracy of the needle tip positioning result.
附图说明Description of the drawings
图1为本发明的一个实施例中提供的留置针结构示意图;FIG. 1 is a schematic diagram of the structure of an indwelling needle provided in an embodiment of the present invention;
图2为本发明的一个实施例中提供的留置针在影像环境下的示意图;2 is a schematic diagram of the indwelling needle provided in an embodiment of the present invention in an image environment;
图3为本发明的一个实施例中提供的定位层结构示意图;3 is a schematic diagram of the structure of the positioning layer provided in an embodiment of the present invention;
图4为本发明的一个实施例中提供的又一定位层结构示意图;4 is a schematic diagram of another positioning layer structure provided in an embodiment of the present invention;
图5为本发明的一个实施例中提供的反光层面积模型示意图;Fig. 5 is a schematic diagram of an area model of a reflective layer provided in an embodiment of the present invention;
图6为本发明的一个实施例中提供的标签示意图;Figure 6 is a schematic diagram of a label provided in an embodiment of the present invention;
图7为本发明的一个实施例中提供的针尖深度定位示意图。Fig. 7 is a schematic diagram of needle tip depth positioning provided in an embodiment of the present invention.
具体实施方式Detailed ways
下面结合附图和实施例对本发明进行详细说明。以便本领域的技术人员更好的理解本发明。需要特别提醒注意的是,在以下的描述中,当已知功能和设计的详细描述也许会淡化本发明的主要内容时,这些描述在这里将被忽略。The present invention will be described in detail below with reference to the drawings and embodiments. So that those skilled in the art can better understand the present invention. It is important to note that in the following description, when detailed descriptions of known functions and designs may dilute the main content of the present invention, these descriptions will be omitted here.
在临床医护人员对患者进行留置针穿刺操作时,为了能更好的一次性穿刺并留置成功,有这样的一个操作规范,依次为:扎止血带、去除护针帽、左右松动穿刺针、针尖斜面朝上以15到30度直刺静脉、见回血后降低角度到5到10度、继续进针2毫米、后撤穿刺针2到3毫米、持针座将导管和穿刺针一起全部送入血管、松开止血带打开调速器、将穿刺针完全撤出、固定留置针。这个过程中回血后继续穿刺2mm,对于医护人员无一个可量化的指示,全部凭借经验,而本发明提供的留置针可以在红外光环境下识别针尖位置直观看到针尖与穿刺的血管的相对位置;然后撤穿刺针2~3mm使得针尖撤至导管内,这个操作现有技术无提示。When clinical medical staff perform indwelling needle puncture operations on patients, in order to better one-time puncture and indwelling success, there is such an operating specification, in order: piercing the tourniquet, removing the needle guard, loosening the puncture needle, and the needle tip. Directly puncture the vein at an angle of 15 to 30 degrees with the inclined surface facing up. After seeing the blood return, reduce the angle to 5 to 10 degrees, continue to insert the needle 2 mm, withdraw the puncture needle 2 to 3 mm, and hold the needle holder to feed the catheter and the puncture needle together. Blood vessels, loosen the tourniquet, open the governor, withdraw the puncture needle completely, and fix the indwelling needle. In this process, the blood returns and continues to puncture 2mm. There is no quantifiable instruction for medical staff. All relying on experience, the indwelling needle provided by the present invention can identify the position of the needle tip in an infrared light environment and visually see the relative position of the needle tip and the punctured blood vessel. ; Then withdraw the puncture needle by 2 to 3 mm so that the needle tip is withdrawn into the catheter. There is no prompt for this operation in the prior art.
实施例一:Example one:
在本实施例中公开了一种在影像环境下实现针尖定位的留置针,包括留置针本体1,留置针本体1包括针头1-1,在留置针本体1上设置有定位层2,定位层2包括反光层2-1,反光层2-1在影像环境下显示为高亮区域。In this embodiment, an indwelling needle for realizing needle tip positioning in an image environment is disclosed. The indwelling needle body 1 includes a needle head 1-1. The indwelling needle body 1 is provided with a positioning layer 2, and the positioning layer 2 includes the reflective layer 2-1, which is displayed as a bright area in the image environment.
在本实施例中,影像环境具体是指向留置针本体1发射红外光后采用图像采集设备采集图像,即在红外光的照射下采集留置针本体1的图像。In this embodiment, the image environment specifically refers to the indwelling needle body 1 emitting infrared light and then using an image acquisition device to collect images, that is, the image of the indwelling needle body 1 is collected under the irradiation of infrared light.
在本实施例中提供了一种能够实现针尖定位的留置针,如图1所示,相比与普通的留置针多出了能够实现针尖定位的功能,由于当留置针插入皮肤内时,针头的位置用肉眼无法看到时,本实施例中提供的留置针的反光层2-1可以在红外光环境下经过成像后,在图像上显示为高亮的区域,如图2所示,相比于现有技术中采用图像处理方法对单纯留置针图像进行处理时存在的噪声过多,造成的定位不准确的问题,本实施例中通过加入了反光层2-1使得在图像中可以清晰的看到反光层2-1的位置,在图像处理时能够准确地定位到留置针的位置,从而提高了针尖定位结果的准确性。In this embodiment, an indwelling needle capable of realizing needle tip positioning is provided. As shown in Fig. 1, compared with ordinary indwelling needles, it has the function of realizing needle tip positioning. Because when the indwelling needle is inserted into the skin, the needle When the position cannot be seen with the naked eye, the reflective layer 2-1 of the indwelling needle provided in this embodiment can be displayed as a highlighted area on the image after imaging in an infrared light environment, as shown in Figure 2, Compared with the prior art adopting the image processing method to process the pure indwelling needle image, there is too much noise, which causes the problem of inaccurate positioning. In this embodiment, the reflective layer 2-1 is added to make the image clear By seeing the position of the reflective layer 2-1, the position of the indwelling needle can be accurately positioned during image processing, thereby improving the accuracy of the needle tip positioning result.
在留置针本体1上设置的反光层2-1的区域在图像中显示为高亮区域,经过对图像灰度化后,该部分高亮区域在图像中显示为纯白色,如图2所示。The area of the reflective layer 2-1 set on the indwelling needle body 1 is displayed as a highlight area in the image. After graying the image, the part of the highlight area is displayed as pure white in the image, as shown in Figure 2. .
在设置反光层2-1时就已知反光层2-1的位置与针尖位置之间的位置关系,在图像上获取了反光层2-1的位置时就可以利用位置关系得到图像中针尖的位置,再获得了图像中针尖位置以后,可以再投影到皮肤上,从而医务人员在进行扎针时可以实时地看到针尖的位置,将本实施例中提供的留置针与现有技术中的血管成像设备同时使用,在能看到血管的基础上还能够看到针尖位置,能够有效地防止留置针扎穿血管,提高了医务人员的操作便捷性。When the reflective layer 2-1 is set, the positional relationship between the position of the reflective layer 2-1 and the position of the needle tip is known. When the position of the reflective layer 2-1 is obtained on the image, the positional relationship can be used to obtain the position of the needle tip in the image. After obtaining the position of the needle tip in the image, it can be projected onto the skin, so that the medical staff can see the position of the needle tip in real time when performing a needle puncture, and compare the indwelling needle provided in this embodiment with the blood vessel in the prior art. When the imaging equipment is used at the same time, the position of the needle tip can be seen on the basis of the blood vessel, which can effectively prevent the indwelling needle from puncturing the blood vessel and improve the operation convenience of medical staff.
本实施例中提供的在红外光环境下实现针尖定位的留置针仅需在留置针本体1上设置定位层2在结合现有技术中的图像处理方法以及图像投影方法即可实现针尖定位。The indwelling needle provided in this embodiment for realizing needle tip positioning in an infrared light environment only needs to provide a positioning layer 2 on the indwelling needle body 1 and combining the image processing methods and image projection methods in the prior art to realize the needle tip positioning.
可选地,定位层2还包括吸光层2-2,吸光层2-2在影像环境下显示为阴影区域,反光层2-1与吸光层2-2沿着所述针头1-1长度方向交错设置。Optionally, the positioning layer 2 further includes a light-absorbing layer 2-2, the light-absorbing layer 2-2 is displayed as a shadow area in the image environment, and the light-reflecting layer 2-1 and the light-absorbing layer 2-2 are along the length direction of the needle 1-1 Staggered settings.
由于图像采集设备在红外光环境下采集留置针的图像时,常常会出现噪点,导致反光层2-1的位置提取的不准确导致针尖定位的不准确,因此在本实施例中还设置了吸光层2-2,吸光层2-2与反光层2-1交错设置,在图像中可以看到黑 白交错的吸光层2-2与反光层2-1,如图2所示,吸光层2-2的设置可以排除反光层2-1附近的噪点干扰,使得精准识别反光层2-1,使得算法简单快速运算即可定位针尖位置和导管尖端位置。When the image acquisition device collects the image of the indwelling needle in an infrared light environment, noise often occurs, which leads to inaccurate extraction of the position of the reflective layer 2-1 and inaccurate positioning of the needle tip. Therefore, light absorption is also set in this embodiment. Layer 2-2, the light-absorbing layer 2-2 and the light-reflecting layer 2-1 are arranged staggered. In the image, you can see the black-and-white staggered light-absorbing layer 2-2 and the light-reflecting layer 2-1, as shown in Figure 2, the light-absorbing layer 2- The setting of 2 can eliminate the noise interference near the reflective layer 2-1, so that the reflective layer 2-1 can be accurately identified, and the algorithm can be used to locate the needle tip position and the catheter tip position with simple and fast calculation.
在本实施例中,定位层2的反光层2-1以及吸光层2-2的排列可以是反光层2-1——吸光层2-2——反光层2-1,或者吸光层2-2——反光层2-1——吸光层2-2——反光层2-1——吸光层2-2等交错的结构,考虑到制作工艺的难易程度、识别的准确性、算法简单延时低,本发明优选反光层2-1——吸光层2-2——反光层2-1为最佳组合。In this embodiment, the arrangement of the light-reflecting layer 2-1 and the light-absorbing layer 2-2 of the positioning layer 2 can be the light-reflecting layer 2-1—the light-absorbing layer 2-2—the light-reflecting layer 2-1, or the light-absorbing layer 2- 2-reflective layer 2-1-light absorbing layer 2-2-reflective layer 2-1-light absorbing layer 2-2 and other staggered structures, taking into account the difficulty of the production process, the accuracy of recognition, and the simple algorithm The time delay is low, and the light-reflecting layer 2-1, the light-absorbing layer 2-2, and the light-reflecting layer 2-1 are the best combination in the present invention.
可选地,反光层2-1的形状与吸光层2-2的形状均为轴对称图形;Optionally, the shape of the light-reflecting layer 2-1 and the shape of the light-absorbing layer 2-2 are both axially symmetrical figures;
反光层2-1与吸光层2-2的对称轴与针头1-1斜面平行于水平面朝向上方时所在的直线处于同一条直线或与平行设置。The symmetry axis of the light-reflecting layer 2-1 and the light-absorbing layer 2-2 is in the same straight line or arranged in parallel with the straight line where the inclined surface of the needle 1-1 is parallel to the horizontal plane and faces upward.
在本实施例中,如图3所示,当反光层2-1与吸光层2-2的形状均为轴对称图形时,可以通过图像处理方法迅速的找到反光层2-1以及吸光层2-2在图像中的对称轴。In this embodiment, as shown in FIG. 3, when the shapes of the light-reflecting layer 2-1 and the light-absorbing layer 2-2 are both axially symmetrical, the light-reflecting layer 2-1 and the light-absorbing layer 2 can be quickly found by the image processing method. -2 The axis of symmetry in the image.
当对称轴与针头斜面所在的直线相互重合时,此时对称轴所在的直线就是针头所在的直线,可以通过图像处理的方法结合针头的长度就可以迅速的找到针尖的位置。When the line of symmetry axis and the bevel of the needle overlap each other, the line where the axis of symmetry is located is the line where the needle is located. The position of the needle tip can be quickly found by image processing combined with the length of the needle.
当对称轴与针头斜面所在的直线相互平行时,此时可以根据对称轴与针头所在直线的位置关系首先定位到针头所在的直线,再根据针头的长度定位针尖的位置。When the line of symmetry axis and the bevel of the needle are parallel to each other, you can first locate the line where the needle is located according to the position relationship between the axis of symmetry and the line where the needle is located, and then locate the position of the needle point according to the length of the needle.
在本实施例中,定位层2形状可以是矩形、菱形、对称三角形等具有轴对称性的图形,也就是说,如图3所示,反光层2-1可以是矩形,吸光层2-2可以是菱形。In this embodiment, the shape of the positioning layer 2 can be a rectangle, a rhombus, a symmetrical triangle, etc., with axial symmetry, that is to say, as shown in FIG. 3, the light-reflecting layer 2-1 can be a rectangle and the light-absorbing layer 2-2 It can be a diamond shape.
当反光层2-1与吸光层2-2的组合为反光层2-1——吸光层2-2——反光层2-1时,如图3所示,两个反光层2-1的形状可以同为矩形、菱形或椭圆形,两个反光层2-1的形状也可以互为不同。When the combination of the light-reflecting layer 2-1 and the light-absorbing layer 2-2 is the light-reflecting layer 2-1—the light-absorbing layer 2-2—the light-reflecting layer 2-1, as shown in FIG. The shapes can be rectangular, rhombic or elliptical, and the shapes of the two reflective layers 2-1 can also be different from each other.
两个反光层2-1与一个吸光层2-1的形状可以是相同的,也可以是相互不同的,即两个吸光层2-1的形状也相互不同。The shapes of the two light-reflecting layers 2-1 and one light-absorbing layer 2-1 may be the same or different from each other, that is, the shapes of the two light-absorbing layers 2-1 are also different from each other.
优选地,反光层2-1与吸光层2-2均为矩形。Preferably, the light-reflecting layer 2-1 and the light-absorbing layer 2-2 are both rectangular.
在本发明中,选用矩形定位层2为最优图形,因为矩形面积最大,识别的准确率最高。其他图形如果因为旋转导致设备只能识别到一部分图形时,就会出现标记点识别不准确从而导致针尖位置和导管尖端位置识别不准确。In the present invention, the rectangular positioning layer 2 is selected as the optimal figure, because the rectangular area is the largest and the recognition accuracy is the highest. If other graphics can only recognize a part of the graphics due to rotation, inaccurate mark point recognition will occur, resulting in inaccurate recognition of the needle tip position and the catheter tip position.
在本实施例中由于针头1-1需要插入皮肤内无法且没有必要在其上设置定位层2,因此定位层2可以覆盖到整个留置针本体1中除了针头1-1以外的位置,从而能够更加准确地定位针尖位置,但是为了降低留置针的成本,仅在留置针本体1的个别位置上设置定位层2即可,可选地,留置针本体1还包括沿着所述针头1-1长度方向依次设置的底部1-2、套管1-3以及针套筒1-4,针头1-1安装在针套筒1-4上;In this embodiment, since the needle 1-1 needs to be inserted into the skin, it is impossible and unnecessary to provide the positioning layer 2 on it, so the positioning layer 2 can cover the entire indwelling needle body 1 except for the needle 1-1, so that it can Position the needle tip more accurately, but in order to reduce the cost of the indwelling needle, it is only necessary to provide the positioning layer 2 on the individual positions of the indwelling needle body 1. Optionally, the indwelling needle body 1 also includes the needle 1-1. The bottom 1-2, the cannula 1-3 and the needle sleeve 1-4 are arranged in sequence in the length direction, and the needle 1-1 is installed on the needle sleeve 1-4;
其中套管1-3包括沿着针头1-1长度方向依次设置的第一套管1-3-1、第二套管1-3-2以及第三套管1-3-3,其中第一套管1-3-1与底部1-2连接,第三套管1-3-3与针套筒1-4连接;The cannula 1-3 includes a first cannula 1-3-1, a second cannula 1-3-2, and a third cannula 1-3-3 arranged in sequence along the length direction of the needle 1-1. One sleeve 1-3-1 is connected with the bottom 1-2, and the third sleeve 1-3-3 is connected with the needle sleeve 1-4;
定位层2沿着所述底部1-2、套管1-3和/或针套筒1-4的外圆周设置。The positioning layer 2 is arranged along the outer circumference of the bottom 1-2, the sleeve 1-3 and/or the needle sleeve 1-4.
在本实施例中,定位层2的位置如图1所示中,其中底部1-2、套管1-3和/或针套筒1-4的外圆周的位置均可作为定位层2位置,也就是说,定位层2在留置针本体1上可以设置有一个或多个,多个定位层2的设置可以提高针尖定位的准确率,但是会降低定位的实时性。In this embodiment, the position of the positioning layer 2 is shown in FIG. 1, wherein the positions of the bottom 1-2, the outer circumference of the sleeve 1-3 and/or the needle sleeve 1-4 can all be used as the position of the positioning layer 2 That is to say, one or more positioning layers 2 may be provided on the indwelling needle body 1, and the arrangement of multiple positioning layers 2 can improve the accuracy of needle tip positioning, but will reduce the real-time positioning.
定位层2可以在底部1-2、套管1-3以及针套筒1-4的外圆周的位置的任一个位置上设置,其中由于针套筒1-4与针头1-1之间的距离最短,视野范围就会比较小,干扰较小,识别定位层2的精确度较高,因此如图1所示,针套筒1-4的位置为定位层2的最优位置,而且将定位层2设置在针套筒1-4的外圆周上对于定位层2的制作工艺要求较低,可以节省定位层2材料。The positioning layer 2 can be provided at any position of the outer circumference of the bottom 1-2, the sleeve 1-3, and the needle sleeve 1-4, wherein due to the gap between the needle sleeve 1-4 and the needle 1-1 With the shortest distance, the field of view will be smaller, the interference will be smaller, and the accuracy of identifying the positioning layer 2 will be higher. Therefore, as shown in Figure 1, the position of the needle sleeve 1-4 is the optimal position of the positioning layer 2, and The positioning layer 2 is arranged on the outer circumference of the needle sleeve 1-4, and the manufacturing process of the positioning layer 2 is relatively low, and the material of the positioning layer 2 can be saved.
可选地,留置针本体1还包括针柄1-5,定位层2还沿着针柄的长度方向设置。Optionally, the indwelling needle body 1 further includes a needle handle 1-5, and the positioning layer 2 is also arranged along the length direction of the needle handle.
在本实施例中,如图4所示,针柄1-5位置的定位层2为矩形,用于提供一条平行线作为定位的参考,以提高识别效率。In this embodiment, as shown in FIG. 4, the positioning layer 2 at positions 1-5 of the needle handle is rectangular, which is used to provide a parallel line as a reference for positioning, so as to improve the recognition efficiency.
可选地,定位层2包括多个反光层2-1以及多个吸光层2-2,多个反光层2-1的面积沿着留置针长度方向逐渐增大或减小。Optionally, the positioning layer 2 includes multiple light-reflecting layers 2-1 and multiple light-absorbing layers 2-2, and the area of the multiple light-reflecting layers 2-1 gradually increases or decreases along the length direction of the indwelling needle.
在本实施例中,两个相隔了一个吸光层2-2的反光层2-1的面积之间的比例 关系为0到1之间或大于1。In this embodiment, the ratio between the areas of the two light-reflecting layers 2-1 separated by a light-absorbing layer 2-2 is between 0 and 1 or greater than 1.
在本实施例中,反光层2-1的反光度取决于表面层的反光材料的浓度,本发明所需的反光层2-1的反光材料对近红外光的反光度大于70%,吸光层2-2的对近红外光的吸光度大于90%即可,目前医学领域主要使用的反光材料为反光粉,吸光材料为吸光粉,可以是多层复合聚酯薄膜或无机纳米颗粒与有机涂层树脂复合成膜。In this embodiment, the reflectivity of the reflective layer 2-1 depends on the concentration of the reflective material of the surface layer. The reflective material of the reflective layer 2-1 required by the present invention has a reflectivity of more than 70% for near-infrared light. 2-2 The absorbance of near-infrared light is greater than 90%. At present, the reflective material mainly used in the medical field is light-absorbing powder, and the light-absorbing material is light-absorbing powder, which can be a multilayer composite polyester film or inorganic nanoparticles and organic coatings. Resin composite film.
具体地,反光层2-1选用路嘉反光材料公司生产的3A101-1系列中医用反光粉,吸光层2-2采用近红外吸光粉。Specifically, the reflective layer 2-1 is selected from the 3A101-1 series of traditional Chinese medicine reflective powder produced by Lujia Reflective Material Company, and the light-absorbing layer 2-2 is made of near-infrared light-absorbing powder.
将反光层2-1与吸光层2-2设置在留置针本体1上的方式有三种,第一种方式热缩,将材料通过热缩的方式直接套在留置针本体1上的相应位置;第二种方式,将材料直接镀在留置针本体1上的相应位置,第三种方式为胶粘的方式。There are three ways to arrange the light-reflecting layer 2-1 and the light-absorbing layer 2-2 on the indwelling needle body 1. The first method is heat shrinking, and the material is directly sheathed on the indwelling needle body 1 by heat shrinking at the corresponding position; The second method is to plate the material directly on the corresponding position on the indwelling needle body 1, and the third method is the adhesive method.
可选地,所述的反光层2-1面积的数值y为
Figure PCTCN2020133557-appb-000002
其中a、b、h 1、h 2、p、q 1以及q 2均为常数参数,x为反光层2-1的反光度;a>0,b>0,h 1<0,h 2<0,p>0,q 1>0,q 2>0。
Optionally, the value y of the area of the reflective layer 2-1 is
Figure PCTCN2020133557-appb-000002
Among them, a, b, h 1 , h 2 , p, q 1 and q 2 are all constant parameters, and x is the reflectance of the reflective layer 2-1; a>0, b>0, h 1 <0, h 2 < 0, p>0, q 1 >0, q 2 >0.
在本实施例中,反光层2-1的反光度和反光面积共同决定了针尖的识别准确性,当反光层2-1的反光度越高,反光面积越大,那么针尖识别的准确度越高,其中当反光度>80%,最小反光面积>5mm 2,即可准确识别针尖。 In this embodiment, the reflectivity and the reflective area of the reflective layer 2-1 jointly determine the accuracy of the needle tip recognition. When the reflective layer 2-1 has the higher the reflectivity and the reflective area, the greater the accuracy of the needle tip recognition. High, when the reflectance is more than 80% and the minimum reflective area is more than 5mm 2 , the needle tip can be accurately identified.
另外,当反光度介于70%~100%之间,反光面积介于1mm 2到30mm 2之间,其中反光度为x(70%≤x≤100%),反光面积y(1mm 2≤y≤30mm 2)时,反光层2-1面积的数值y为
Figure PCTCN2020133557-appb-000003
In addition, when the reflectivity is between 70% and 100%, the reflective area is between 1mm 2 and 30mm 2 , where the reflectivity is x (70%≤x≤100%), and the reflective area y (1mm 2 ≤y ≤30mm 2 ), the value y of the area of the reflective layer 2-1 is
Figure PCTCN2020133557-appb-000003
在本实施例中,反光层2-1面积的数值与反光层2-1的反光度之间的模型示意图,如图5所示,根据该模型可以得出,当确定了反光层2-1的材料时,就可以获得该种材料的反光度,从而可以直接获得反光层2-1的面积,使得针尖识别的准确率保持稳定。In this embodiment, the schematic diagram of the model between the value of the area of the reflective layer 2-1 and the reflectance of the reflective layer 2-1 is shown in FIG. 5. According to the model, it can be concluded that when the reflective layer 2-1 is determined When using a material that is less than the same, the reflectance of the material can be obtained, so that the area of the reflective layer 2-1 can be directly obtained, so that the accuracy of needle tip recognition remains stable.
在本实施例中,a=0.732,b=15.726,h 1=-37.477,h 2=-22.716,p=0.254,q 1=0.739,q 2=0.917。 In the present embodiment, a = 0.732, b = 15.726 , h 1 = -37.477, h 2 = -22.716, p = 0.254, q 1 = 0.739, q 2 = 0.917.
在本实施例中提供的在影像环境下实现针尖定位的留置针,相比于现有技术中的定位留置针,仅需在留置针本体1上覆盖定位层2,即可实现定位功能。Compared with the positioning indwelling needle in the prior art, the indwelling needle provided in this embodiment for realizing needle tip positioning in an image environment only needs to cover the positioning layer 2 on the indwelling needle body 1 to realize the positioning function.
实施例二:Embodiment two:
在本实施例中公开了一种留置针图像分割模型构建方法,用于对实施例一中提供的留置针的红外图像进行分割,将其中的反光层区域以及留置针针头区域从图像中分割出来,方法按照以下步骤执行:In this embodiment, a method for constructing an indwelling needle image segmentation model is disclosed, which is used to segment the infrared image of the indwelling needle provided in the first embodiment, and segment the reflective layer area and the indwelling needle tip area from the image. , The method is executed according to the following steps:
步骤1、获取多幅留置针图像,其中所述的留置针图像中包括多个反光层区域与留置针针头区域; Step 1. Obtain multiple indwelling needle images, wherein the indwelling needle images include multiple reflective layer areas and indwelling needle tip areas;
在本实施例中,反光层设置在针套筒1-4的外圆周上且反光层为矩形,获得的留置针图像如图2所示,其中反光层区域为图像中的白色区域。In this embodiment, the reflective layer is arranged on the outer circumference of the needle sleeve 1-4 and the reflective layer is rectangular, and the obtained indwelling needle image is shown in FIG. 2, wherein the reflective layer area is the white area in the image.
在本实施例中通过收集不同形状的留置针的图像,此时不同形状的留置针可以是实施例一中定位层2的位置不同或形状不同的留置针,还可以是不同厂家生产的留置针,在本实施例中对图像的质量不做具体的要求,可以为不同环境下采集的针头图像,将这些留置针图像作为训练样本,使得训练好的分割模型能够对多种不同的留置针图像进行分割。In this embodiment, images of indwelling needles of different shapes are collected. At this time, the indwelling needles of different shapes can be the indwelling needles with different positions or shapes of the positioning layer 2 in the first embodiment, or indwelling needles produced by different manufacturers. In this embodiment, there is no specific requirement on the quality of the image. It can be needle images collected in different environments, and these indwelling needle images can be used as training samples, so that the trained segmentation model can be used for a variety of different indwelling needle images. Split.
步骤2、对步骤1获得的每一幅留置针图像进行数据增强,获得样本集; Step 2. Perform data enhancement on each indwelling needle image obtained in Step 1 to obtain a sample set;
在本实施例中,考虑真实环境中的光照强度不同,采集到的图像中反光层2-1的尺寸不同,以及深度学习网络需要大量的样本进行训练,因此采用了数据增强的方法对数据集进行扩展,通过调整图像的亮度,裁剪并缩放图像,增加图像的不同形态,在增强数据的同时,又可以尽量模型不同条件下采集得到图像,从而提高模型的泛化能力。In this embodiment, considering that the light intensity in the real environment is different, the size of the reflective layer 2-1 in the collected images is different, and the deep learning network requires a large number of samples for training, the data enhancement method is used to For expansion, by adjusting the brightness of the image, cropping and zooming the image, adding different forms of the image, while enhancing the data, it can also collect images under different conditions of the model as much as possible, thereby improving the generalization ability of the model.
步骤3、标记所述的样本集中的每一幅留置针图像中的每一个反光层区域以及留置针针头区域,获得包括反光层标记区域以及留置针针头标记区域的多幅标记留置针图像,获得第一标签集;Step 3. Mark each reflective layer area and the indwelling needle tip area of each indwelling needle image in the sample set to obtain multiple marked indwelling needle images including the reflective layer mark area and the indwelling needle needle mark area, and obtain First set of tags;
获取所述的样本集中的每一幅留置针图像中的每一个反光层标记区域的轮廓以及留置针针头区域的轮廓,获得包括多幅反光层标记区域的轮廓以及留置针 针头区域的轮廓的多幅轮廓留置针图像,获得第二标签集;Obtain the contour of each reflective layer marking area and the contour of the indwelling needle needle area in each indwelling needle image in the sample set, and obtain the contours of multiple reflective layer marking areas and the contours of the indwelling needle needle area. A contour indwelling needle image to obtain the second label set;
在本实施例中,如图6所示,考虑到传统的全卷积网络虽然可以得到反光层以及针头的分割结果,但是没有利用它们的边缘特征对结果进行约束,可能导致网络输出的分割结果中反光层区域以及针头区域的边缘不够平滑,形状扭曲,和图像的真实分割区域之间有一定的差异,因此在本实施例中提出了基于多任务的分割网络,在不需要增加训练样本或者其他标注工作的前提下,引入目标轮廓识别任务,训练样本的目标轮廓可以根据边缘检测算法获得,通过引入目标轮廓的约束,提高了对轮廓的识别精度,从而使得网络提取到目标的轮廓信息,从而优化目标的分割结果,因此,通过引入多任务学习机制,可以提高网络模型的精度,从而准确的识别反光层区域以及针头区域。In this embodiment, as shown in Figure 6, it is considered that although the traditional full convolutional network can obtain the segmentation results of the reflective layer and the needle, it does not use their edge features to constrain the results, which may lead to the segmentation results of the network output. The edge of the middle reflective layer area and the needle area is not smooth enough, the shape is distorted, and there is a certain difference between the real segmentation area of the image, so in this embodiment, a segmentation network based on multi-task is proposed, without the need to increase training samples or Under the premise of other labeling work, the target contour recognition task is introduced. The target contour of the training sample can be obtained according to the edge detection algorithm. By introducing the constraint of the target contour, the recognition accuracy of the contour is improved, so that the network can extract the contour information of the target. In this way, the segmentation result of the target is optimized. Therefore, by introducing a multi-task learning mechanism, the accuracy of the network model can be improved, so as to accurately identify the reflective layer area and the needle area.
在本实施例中,如图6所示,对于轮廓的获取,可采用边缘提取方法,提取反光层以及针头的边缘,然后利用膨胀操作得到物体轮廓,膨胀操作采用半径为5的disk滤波。引入轮廓识别任务,主要是缓解传统的分割网络无法捕获目标结构信息的问题,通过训练网络提高轮廓识别精度,进而约束分割结果的形态,达到提高分割精度的目的。In this embodiment, as shown in FIG. 6, for the contour acquisition, an edge extraction method can be used to extract the reflective layer and the edge of the needle, and then use the expansion operation to obtain the object contour, and the expansion operation uses a disk filter with a radius of 5. The introduction of contour recognition tasks is mainly to alleviate the problem that traditional segmentation networks cannot capture the target structure information, and to improve the accuracy of contour recognition by training the network, and then constrain the shape of the segmentation results to achieve the purpose of improving segmentation accuracy.
步骤4、将所述的样本集作为输入,将所述的第一标签集以及第二标签集作为参考输出,训练全卷积神经网络,获得留置针图像分割模型;Step 4. Using the sample set as input and the first label set and the second label set as reference output, training a fully convolutional neural network to obtain an indwelling needle image segmentation model;
其中所述的全卷积神经网络的损失函数L为:The loss function L of the fully convolutional neural network is:
Figure PCTCN2020133557-appb-000004
Figure PCTCN2020133557-appb-000004
其中λ 1与λ 2为权重因子,λ 1与λ 2均大于0;x表示留置针图像中的第x个像素点,l mask(x)表示第x个像素点为第一标签,p mask(x;l mask(x))表示第x个像素点为第一标签的预测概率值;l contour(x)表示第x个像素点为第二标签,p contour(x;l contour(x))表示第x个像素点为第二标签的预测概率值。 Where λ 1 and λ 2 are weighting factors, λ 1 and λ 2 are both greater than 0; x represents the xth pixel in the indwelling needle image, l mask (x) represents the xth pixel is the first label, p mask (x;l mask (x)) represents the predicted probability value of the xth pixel as the first label; l contour (x) represents the xth pixel as the second label, p contour (x; l contour (x) ) Represents the predicted probability value of the xth pixel as the second label.
在本实施例中提供的分割网络的结构采用了传统的分割网络,在分割网络输出的特征图基础上,采用3x3的卷积核得到两个结果,即分割结果和轮廓提取结果,卷积核的通道数取决于特征图的个数,stride为1,padding为1。The structure of the segmentation network provided in this embodiment uses a traditional segmentation network. Based on the feature map output by the segmentation network, a 3x3 convolution kernel is used to obtain two results, namely the segmentation result and the contour extraction result, and the convolution kernel The number of channels depends on the number of feature maps, stride is 1, and padding is 1.
在本实施例中,识别的目标有两个反光层2-1区域以及一个针头区域,因此 卷积核的个数为3。In this embodiment, the identified target has two reflective layer 2-1 areas and one needle area, so the number of convolution kernels is 3.
在本实施例中主要提供了一种留置针图像分割模型构建方法,利用本实施例中的模型构建方法构建出的图像分割模型,可以应用至多种类型的留置针图像中,从而提高了图像分割的灵活性以及可使用范围。In this embodiment, a method for constructing an indwelling needle image segmentation model is mainly provided. The image segmentation model constructed by the model construction method in this embodiment can be applied to various types of indwelling needle images, thereby improving image segmentation. The flexibility and range of use.
实施例三:Embodiment three:
本实施例中公开了一种留置针图像针尖定位方法,用于在留置针图像中定位针尖的位置,所述的方法按照以下步骤执行:This embodiment discloses a method for locating the tip of the indwelling needle image, which is used to locate the position of the tip of the indwelling needle in the image of the indwelling needle, and the method is executed according to the following steps:
步骤A、获得待定位的留置针图像,其中所述的待定位的留置针图像中包括多个反光层区域与留置针针头区域;Step A: Obtain an image of the indwelling needle to be positioned, wherein the image of the indwelling needle to be positioned includes a plurality of reflective layer regions and the indwelling needle tip area;
在本实施例中,采用实施例一中所述的留置针,采集包含实施例一中的留置针的图像作为待定位留置针图像。In this embodiment, the indwelling needle described in the first embodiment is used, and an image including the indwelling needle in the first embodiment is collected as the image of the indwelling needle to be positioned.
步骤B、将所述的待定位的留置针图像输入至实施例二的留置针图像分割模型构建方法获得的留置针图像分割模型中,获得包括反光层标记区域以及留置针针头标记区域的标记留置针图像;Step B. Input the indwelling needle image to be positioned into the indwelling needle image segmentation model obtained by the indwelling needle image segmentation model construction method of the second embodiment, and obtain the mark indwelling including the reflective layer mark area and the mark area of the indwelling needle needle Needle image
步骤C、从标记留置针图像中获得每一个反光层标记区域的形状信息以及位置信息,获得留置针针头标记区域的形状信息以及位置信息;Step C: Obtain the shape information and position information of the marked area of each reflective layer from the mark indwelling needle image, and obtain the shape information and position information of the marked area of the indwelling needle needle;
在本实施例中,反光层标记区域形状信息为反光层的形状即实施例一中的轴对称图像,可以是椭圆形、对称三角形或者矩形等形状;留置针枕头标记区域的形状一般为矩形。In this embodiment, the shape information of the marking area of the reflective layer is the shape of the reflective layer, that is, the axisymmetric image in the first embodiment, which can be an ellipse, a symmetrical triangle, or a rectangle; the shape of the marking area of the indwelling needle pillow is generally a rectangle.
在本实施例中,位置信息为各种形状的顶点的位置信息。In this embodiment, the position information is position information of vertices of various shapes.
步骤D、根据每一个反光层标记区域的形状信息以及留置针针头标记区域的形状信息在留置针图像数据库中寻找相似度最高的一副图像作为样本图像;Step D, according to the shape information of the marking area of each reflective layer and the shape information of the marking area of the indwelling needle tip, searching for an image with the highest similarity in the indwelling needle image database as a sample image;
其中所述的留置针图像数据库包括多幅经过实施例二留置针图像分割模型构建方法获得的留置针图像分割模型输出的标记留置针图像;其中每幅标记留置针图像均对应一个比例参数
Figure PCTCN2020133557-appb-000005
其中P 1为任一个反光层标记区域的中心点坐标,P 2为另外一个反光层标记区域的中心点坐标,P 3为留置针针尖点 坐标;
Figure PCTCN2020133557-appb-000006
为P 2点至P 1点之间的图像距离,单位为像素点,
Figure PCTCN2020133557-appb-000007
为P 3点至P 2点之间的图像距离,单位为像素点;
The indwelling needle image database includes a plurality of marked indwelling needle images output by the indwelling needle image segmentation model obtained by the method for constructing the indwelling needle image segmentation model in the second embodiment; wherein each marked indwelling needle image corresponds to a scale parameter
Figure PCTCN2020133557-appb-000005
Where P 1 is the coordinates of the center point of any reflective layer marking area, P 2 is the coordinates of the center point of another reflective layer marking area, and P 3 is the coordinates of the tip point of the indwelling needle;
Figure PCTCN2020133557-appb-000006
Is the image distance from point P 2 to point P 1, in pixels,
Figure PCTCN2020133557-appb-000007
Is the image distance from point P 3 to point P 2 in pixels;
获得所述样本图像的比例参数K;Obtaining the scale parameter K of the sample image;
在本实施例中,通过随机抽样一致算法即可找出数据库所有的图像中与待定位的留置针图像中反光层标记区域与针头标记区域最匹配的一张图像。In this embodiment, a random sampling consensus algorithm can be used to find an image that best matches the reflective layer mark area and the needle mark area in the indwelling needle image to be positioned among all the images in the database.
本步骤的目的是获得比例参数K,将样本图像的比例参数K作为待定位的留置针图像的比例参数K。The purpose of this step is to obtain the scale parameter K, and use the scale parameter K of the sample image as the scale parameter K of the indwelling needle image to be positioned.
步骤E、根据步骤C中获得的标记留置针图像中每一个反光层标记区域的位置信息,获得两个反光层标记区域的中心点位置坐标,分别为P 1′以及P 2′;其中所述的两个反光层标记区域与所述的样本图像计算比例参数K时选择的两个反光层标记区域的位置相同; Step E. According to the position information of each reflective layer mark area in the mark indwelling needle image obtained in step C, obtain the center point position coordinates of the two reflective layer mark areas, which are P 1 ′ and P 2 ′, respectively; The positions of the two marking areas of the reflective layer are the same as the positions of the two marking areas of the reflective layer selected when calculating the ratio parameter K of the sample image;
步骤F、采用式II获得待定位的留置针图像中的针尖位置点坐标P 3′: Step F: Use formula II to obtain the needle tip position point coordinate P 3 ′ in the image of the indwelling needle to be positioned:
Figure PCTCN2020133557-appb-000008
Figure PCTCN2020133557-appb-000008
其中,
Figure PCTCN2020133557-appb-000009
为P 2′点至P 1′点之间的图像距离,单位为像素点。
among them,
Figure PCTCN2020133557-appb-000009
It is the image distance from point P 2 ′ to point P 1 ′, and the unit is pixel point.
在本步骤中,通过式II即可计算出针尖在图像中的位置,医护人员就可以在图像中实时地查看到针尖的位置,在获得了图像中针尖的位置后也可以利用图像坐标系与实际坐标系的变换关系获得针尖的实际位置,再配合市场上现有的血管成像仪即可实时地判断针尖是否扎穿血管,进一步地提高了医护人员操作的便捷性。In this step, the position of the needle tip in the image can be calculated by formula II, and the medical staff can view the position of the needle tip in the image in real time. After obtaining the position of the needle tip in the image, the image coordinate system and The transformation relationship of the actual coordinate system obtains the actual position of the needle tip, and then cooperates with the existing vascular imagers on the market to determine whether the needle tip penetrates the blood vessel in real time, which further improves the convenience of operation by medical staff.
实施例四:Embodiment four:
在本实施例中公开了一种留置针图像针尖深度定位方法,用于获得所述的留置针针尖的深度,按照以下步骤执行:In this embodiment, a method for locating the depth of the tip of the indwelling needle image is disclosed, which is used to obtain the depth of the tip of the indwelling needle, which is executed according to the following steps:
步骤I、获得待定位的留置针图像,其中所述的留置针图像中包括多个反光层区域与留置针针头区域;Step I: Obtain an indwelling needle image to be positioned, wherein the indwelling needle image includes a plurality of reflective layer areas and an indwelling needle needle area;
步骤II、采用实施例三所述的留置针图像针尖定位方法获得所述的待定位的留置针图像中针尖位置点坐标P 3′; Step II: Using the method for positioning the tip of the indwelling needle image described in the third embodiment to obtain the coordinate P 3 ′ of the position of the tip of the indwelling needle to be positioned in the image of the indwelling needle;
步骤III、对采用实施例三中的留置针图像针尖定位方法时所述的步骤D获得的样本图像进行标定,获得坐标变换参数
Figure PCTCN2020133557-appb-000010
其中P 1为任一个反光层标记区域的中心点,P 2为另外一个反光层标记区域的中心点,
Figure PCTCN2020133557-appb-000011
为两个中心点之间的实际距离,单位为mm,
Figure PCTCN2020133557-appb-000012
为P 2点至P 1点之间的图像距离,单位为像素点;
Step III: Calibrate the sample image obtained in step D when using the indwelling needle image tip positioning method in the third embodiment to obtain coordinate transformation parameters
Figure PCTCN2020133557-appb-000010
Where P 1 is the center point of any marking area of the reflective layer, P 2 is the center point of the marking area of the other reflective layer,
Figure PCTCN2020133557-appb-000011
Is the actual distance between two center points, the unit is mm,
Figure PCTCN2020133557-appb-000012
Is the image distance from point P 2 to point P 1 in pixels;
在本实施例中,在实施例三的基础上,对留置针图像进行标定时,可以是对实施例三中数据库中的每一幅标记留置针图像进行提前标定,将实施例三的样本图像的坐标变换参数作为待定位的留置针图像的变换参数,从而可以有效地节约程序运行的时间,提高了针尖深度定位的实时性。In this embodiment, on the basis of the third embodiment, when the indwelling needle image is calibrated, it can be pre-calibrated for each marked indwelling needle image in the database in the third embodiment, and the sample image of the third embodiment The coordinate transformation parameter of is used as the transformation parameter of the image of the indwelling needle to be positioned, which can effectively save the time of program running and improve the real-time nature of needle tip depth positioning.
步骤IV、采用式III获得留置针针尖的深度H,单位为mm:Step IV: Use formula III to obtain the depth H of the tip of the indwelling needle, in mm:
Figure PCTCN2020133557-appb-000013
Figure PCTCN2020133557-appb-000013
其中P 4′为对步骤I获得的待定位的留置针图像采用权利要求2所述的留置针图像针尖定位方法中步骤C获得的留置针针头标记区域的位置信息中的针入皮肤的位置点的坐标; Wherein P 4 ′ is the position of the needle penetrating the skin in the position information of the indwelling needle needle mark area obtained in step C of the indwelling needle image needle tip positioning method of claim 2 for the indwelling needle image to be positioned obtained in step I coordinate of;
P 3′为对步骤I获得的待定位的留置针图像采用权利要求2所述的留置针图像针尖定位方法获得的针尖位置点坐标; P 3 ′ is the needle tip position point coordinate obtained by using the indwelling needle image tip positioning method according to claim 2 for the indwelling needle image to be positioned obtained in step I;
P 1′以及P 2′为对步骤I获得的待定位的留置针图像采用权利要求2所述的留置针图像针尖定位方法中步骤E获得的两个反光层标记区域的中心点位置坐标; P 1 ′ and P 2 ′ are the position coordinates of the center points of the two reflective layer mark areas obtained in step E of the indwelling needle image tip positioning method of claim 2 for the indwelling needle image to be positioned obtained in step I;
Figure PCTCN2020133557-appb-000014
为针入皮肤的位置点与针尖位置点之间的图像距离,单位为像素点;
Figure PCTCN2020133557-appb-000015
为P 2′点至P 1′点之间的图像距离,单位为像素点;
Figure PCTCN2020133557-appb-000016
为P 2′点至P 1′点之间的实际距离,单位为mm。
Figure PCTCN2020133557-appb-000014
Is the image distance between the point where the needle penetrates the skin and the point where the needle tip is located, in pixels;
Figure PCTCN2020133557-appb-000015
Is the image distance from P 2 ′ to P 1 ′, in pixels;
Figure PCTCN2020133557-appb-000016
It is the actual distance from point P 2 ′ to point P 1 ′, and the unit is mm.
在本实施例中提供了一种简单有效的针尖深度获取的方法,如图7所示,根据两个反光层标记区域的分割结果可以得到这两个反光层的的中心点坐标,计算两个中心点之间的距离即可得到距离L2,L1表示两个反光层之间的实际距离,为已知量,那么角1可表示为:In this embodiment, a simple and effective method for acquiring the depth of the needle tip is provided. As shown in FIG. 7, the center point coordinates of the two reflective layers can be obtained according to the segmentation results of the two reflective layers, and the two reflective layers are calculated. The distance between the center points can be the distance L2, L1 represents the actual distance between the two reflective layers, which is a known quantity, then the angle 1 can be expressed as:
Figure PCTCN2020133557-appb-000017
Figure PCTCN2020133557-appb-000017
图7中,点P 4′为针头与皮肤的入针点,通过分割模型可以得到该点的位置,点P 3′即为已预测出的针头的位置,因此点P 4′到点P 3′的图像距离可计算得到;又因为角1等于角2,因此获得了式III,通过式III可以简单有效的获得针尖的深度信息。 In Figure 7, point P 4 ′ is the needle entry point between the needle and the skin. The position of this point can be obtained through the segmentation model. Point P 3 ′ is the predicted needle position, so point P 4 ′ to point P 3 The image distance of ′ can be calculated; and because the angle 1 is equal to the angle 2, the formula III is obtained, and the depth information of the needle tip can be obtained simply and effectively through the formula III.
在实施例三获得了针尖位置的基础上,结合图像中可以直接采集到的入针位置信息,采用相似三角形的方法按比例求得针尖的深度信息,本实施例中提供的针尖深度定位方法解决了传统技术中无法获得针尖深度信息的技术难题,并且准确性较高,且实时性较高,能够符合医务工作者在实际使用中的要求。On the basis of the needle tip position obtained in the third embodiment, combined with the needle insertion position information that can be directly collected in the image, the similar triangle method is used to obtain the needle tip depth information proportionally. The needle tip depth positioning method provided in this embodiment solves the problem It overcomes the technical difficulty of the traditional technology that the needle tip depth information cannot be obtained, and the accuracy is high, and the real-time performance is high, which can meet the requirements of medical workers in actual use.
实施例五:Embodiment five:
在本实施例中公开了一种留置针图像分割模型构建装置,装置包括图像采集模块、数据增强模块、标签获得模块以及模型训练模块;In this embodiment, a device for constructing an indwelling needle image segmentation model is disclosed. The device includes an image acquisition module, a data enhancement module, a label acquisition module, and a model training module;
图像采集模块用于获取多幅留置针图像,其中留置针图像中包括多个反光层区域与留置针针头区域;The image acquisition module is used to acquire multiple indwelling needle images, where the indwelling needle image includes multiple reflective layer areas and the indwelling needle needle area;
数据增强模块用于对获得的每一幅留置针图像进行数据增强,获得样本集;The data enhancement module is used to perform data enhancement on each indwelling needle image obtained to obtain a sample set;
标签获得模块用于标记样本集中的每一幅留置针图像中的每一个反光层区域以及留置针针头区域,获得包括反光层标记区域以及留置针针头标记区域的多幅标记留置针图像,获得第一标签集;The label acquisition module is used to mark each reflective layer area and the indwelling needle needle area in each indwelling needle image in the sample set, and obtain multiple marked indwelling needle images including the reflective layer mark area and the indwelling needle needle mark area, and obtain the first A set of labels;
获取样本集中的每一幅留置针图像中的每一个反光层标记区域的轮廓以及留置针针头区域的轮廓,获得包括多幅反光层标记区域的轮廓以及留置针针头区域的轮廓的多幅轮廓留置针图像,获得第二标签集;Obtain the contour of each reflective layer marking area and the contour of the indwelling needle needle area in each indwelling needle image in the sample set, and obtain multiple contour indwellings including the contours of multiple reflective layer marking areas and the contours of the indwelling needle needle area Pin image to obtain the second label set;
模型训练模块用于将样本集作为输入,将第一标签集以及第二标签集作为参考输出,训练全卷积神经网络,获得留置针图像分割模型;The model training module is used to take the sample set as the input, the first label set and the second label set as the reference output, train the full convolutional neural network, and obtain the indwelling needle image segmentation model;
其中全卷积神经网络的损失函数L为:The loss function L of the fully convolutional neural network is:
Figure PCTCN2020133557-appb-000018
Figure PCTCN2020133557-appb-000018
其中λ 1与λ 2为权重因子,λ 1与λ 2均大于0;x表示留置针图像中的第x个像素点,l mask(x)表示第x个像素点为第一标签,p mask(x;l mask(x))表示第x个像素点为第一标签的预测概率值;l contour(x)表示第x个像素点为第二标签,p contour(x;l contour(x))表示第x个像素点为第二标签的预测概率值。 Where λ 1 and λ 2 are weighting factors, λ 1 and λ 2 are both greater than 0; x represents the xth pixel in the indwelling needle image, l mask (x) represents the xth pixel is the first label, p mask (x;l mask (x)) represents the predicted probability value of the xth pixel as the first label; l contour (x) represents the xth pixel as the second label, p contour (x; l contour (x) ) Represents the predicted probability value of the xth pixel as the second label.
实施例六:Embodiment 6:
一种留置针图像针尖定位装置,其特征在于,装置包括图像获得模块、图像分割模块、信息获得模块、样本对比模块、位置点坐标获得模块以及针尖位置计算模块;An indwelling needle image needlepoint positioning device, characterized in that the device includes an image acquisition module, an image segmentation module, an information acquisition module, a sample comparison module, a position point coordinate acquisition module, and a needlepoint position calculation module;
图像获得模块用于获得待定位的留置针图像,其中待定位的留置针图像中包括多个反光层区域与留置针针头区域;The image acquisition module is used to obtain an image of the indwelling needle to be positioned, wherein the image of the indwelling needle to be positioned includes a plurality of reflective layer regions and the indwelling needle tip area;
图像分割模块将待定位的留置针图像输入至权利要求4留置针图像分割模型构建装置获得的留置针图像分割模型中,获得包括反光层标记区域以及留置针针头标记区域的标记留置针图像;The image segmentation module inputs the indwelling needle image to be positioned into the indwelling needle image segmentation model obtained by the indwelling needle image segmentation model construction device of claim 4, and obtains the marked indwelling needle image including the reflective layer marking area and the indwelling needle tip marking area;
信息获得模块用于从标记留置针图像中获得每一个反光层标记区域的形状信息以及位置信息,获得留置针针头标记区域的形状信息以及位置信息;The information obtaining module is used to obtain the shape information and position information of the marked area of each reflective layer from the mark indwelling needle image, and obtain the shape information and position information of the marked area of the indwelling needle needle;
样本对比模块用于根据每一个反光层标记区域的形状信息以及留置针针头标记区域的形状信息在留置针图像数据库中寻找相似度最高的一副图像作为样本图像;The sample comparison module is used to find the image with the highest similarity in the indwelling needle image database as the sample image according to the shape information of the marking area of each reflective layer and the shape information of the marking area of the indwelling needle needle;
其中留置针图像数据库包括多幅经过权利要求4留置针图像分割模型构建装置获得的留置针图像分割模型输出的标记留置针图像;其中每幅标记留置针图像均对应一个比例参数
Figure PCTCN2020133557-appb-000019
其中P 1为任一个反光层标记区域的中心点坐标,P 2为另外一个反光层标记区域的中心点坐标,P 3为留置针针尖点坐标;
Figure PCTCN2020133557-appb-000020
为P 2点至P 1点之间的图像距离,单位为像素点,
Figure PCTCN2020133557-appb-000021
为P 3点至P 2点之间的图像距离,单位为像素点;
The indwelling needle image database includes a plurality of marked indwelling needle images output by the indwelling needle image segmentation model obtained by the indwelling needle image segmentation model construction device of claim 4; wherein each marked indwelling needle image corresponds to a scale parameter
Figure PCTCN2020133557-appb-000019
Where P 1 is the coordinates of the center point of any reflective layer marking area, P 2 is the coordinates of the center point of another reflective layer marking area, and P 3 is the coordinates of the tip point of the indwelling needle;
Figure PCTCN2020133557-appb-000020
Is the image distance from point P 2 to point P 1, in pixels,
Figure PCTCN2020133557-appb-000021
Is the image distance from point P 3 to point P 2 in pixels;
获得样本图像的比例参数K;Obtain the scale parameter K of the sample image;
位置点坐标获得模块用于根据获得的标记留置针图像中每一个反光层标记区域的位置信息,获得两个反光层标记区域的中心点位置坐标,分别为P 1′以及P 2′;其中两个反光层标记区域与样本图像计算比例参数K时选择的两个反光层标记区域的位置相同; The position point coordinate obtaining module is used to obtain the center point position coordinates of the two reflective layer marking areas according to the position information of each reflective layer marking area in the obtained marking indwelling needle image, which are respectively P 1 ′ and P 2 ′; two of them are The positions of the marking areas of the two reflective layers are the same as the positions of the two marking areas of the reflective layer selected when calculating the ratio parameter K of the sample image;
针尖位置计算模块用于采用式II获得待定位的留置针图像中的针尖位置点坐标P 3′: The needle tip position calculation module is used to obtain the needle tip position point coordinate P 3 ′ in the image of the indwelling needle to be positioned by using formula II:
Figure PCTCN2020133557-appb-000022
Figure PCTCN2020133557-appb-000022
其中,
Figure PCTCN2020133557-appb-000023
为P 2′点至P 1′点之间的图像距离,单位为像素点。
among them,
Figure PCTCN2020133557-appb-000023
It is the image distance from point P 2 ′ to point P 1 ′, and the unit is pixel point.
实施例七:Embodiment Seven:
在本实施例中公开了一种留置针图像针尖深度定位装置,用于获得留置针针尖的深度,其特征在于,装置包括图像获得模块、变换参数获得模块以及针尖深度获得模块;In this embodiment, an indwelling needle image tip depth positioning device is disclosed for obtaining the depth of the indwelling needle tip, characterized in that the device includes an image acquisition module, a transformation parameter acquisition module, and a needle tip depth acquisition module;
图像获得模块用于获得待定位的留置针图像,其中待定位的留置针图像中包括多个反光层区域与留置针针头区域;The image acquisition module is used to obtain an image of the indwelling needle to be positioned, wherein the image of the indwelling needle to be positioned includes a plurality of reflective layer regions and the indwelling needle tip area;
变换参数获得模块用于对留置针图像进行标定,获得坐标变换参数
Figure PCTCN2020133557-appb-000024
其中P 1为任一个反光层标记区域的中心点,P 2为另外一个反光层标记区域的中心点,
Figure PCTCN2020133557-appb-000025
为两个中心点之间的实际距离,单位为mm,
Figure PCTCN2020133557-appb-000026
为P 2点至P 1点之间的图像距离,单位为像素点;
The transformation parameter acquisition module is used to calibrate the indwelling needle image to obtain coordinate transformation parameters
Figure PCTCN2020133557-appb-000024
Where P 1 is the center point of any marking area of the reflective layer, P 2 is the center point of the marking area of the other reflective layer,
Figure PCTCN2020133557-appb-000025
Is the actual distance between two center points, the unit is mm,
Figure PCTCN2020133557-appb-000026
Is the image distance from point P 2 to point P 1 in pixels;
用于采用式III获得留置针针尖的深度H,单位为mm:Used to obtain the depth H of the tip of the indwelling needle using formula III, the unit is mm:
Figure PCTCN2020133557-appb-000027
Figure PCTCN2020133557-appb-000027
其中P 4′为对待定位的留置针图像采用权利要求5留置针图像针尖定位装置中信息获得模块获得的留置针针头标记区域的位置信息中的针入皮肤的位置点的坐标; Where P 4 ′ is the coordinates of the position point where the needle penetrates the skin in the position information of the needle mark area of the indwelling needle obtained by the information obtaining module of the indwelling needle image needle tip positioning device of claim 5 in the indwelling needle image to be positioned;
P 3′为对待定位的留置针图像采用权利要求5留置针图像针尖定位装置获得的针尖位置点坐标; P 3 ′ is the position point coordinates of the needle tip obtained by the indwelling needle image needle tip positioning device of claim 5 for the indwelling needle image to be positioned;
P 1′以及P 2′为对获得的待定位的留置针图像采用权利要求2留置针图像针尖定位装置中位置点坐标获得模块获得的两个反光层标记区域的中心点位置坐标; P 1 ′ and P 2 ′ are the position coordinates of the center points of the two reflective layer mark areas obtained by the position point coordinate obtaining module of the indwelling needle image needle point positioning device of claim 2 for the obtained indwelling needle image to be positioned;
Figure PCTCN2020133557-appb-000028
为针入皮肤的位置点与针尖位置点之间的图像距离,单位为像素点;
Figure PCTCN2020133557-appb-000029
为P 2′点至P 1′点之间的图像距离,单位为像素点;
Figure PCTCN2020133557-appb-000030
为P 2′点至P 1′点之间的实际距离,单位为mm。
Figure PCTCN2020133557-appb-000028
Is the image distance between the point where the needle penetrates the skin and the point where the needle tip is located, in pixels;
Figure PCTCN2020133557-appb-000029
Is the image distance from P 2 ′ to P 1 ′, in pixels;
Figure PCTCN2020133557-appb-000030
It is the actual distance from point P 2 ′ to point P 1 ′, and the unit is mm.
实施例八:Embodiment 8:
在本实施例中提供了一种留置针针尖定位系统,包括图像采集识别装置以及留置针,留置针包括留置针本体1,留置针本体1包括针头1-1,在留置针本体1上设置有反光层2;In this embodiment, an indwelling needle tip positioning system is provided, which includes an image acquisition and recognition device and an indwelling needle. The indwelling needle includes an indwelling needle body 1, and the indwelling needle body 1 includes a needle 1-1, and the indwelling needle body 1 is provided with Reflective layer 2;
图像采集识别装置包括图像采集模块、如实施例六中的留置针图像针尖定位装置、如实施例七中的留置针图像针尖深度定位装置、血管成像模块、图像投影模块、光源模块以及供电模块;The image acquisition and recognition device includes an image acquisition module, the indwelling needle image tip positioning device in the sixth embodiment, the indwelling needle image tip depth positioning device in the seventh embodiment, a blood vessel imaging module, an image projection module, a light source module, and a power supply module;
其中供电模块用于向图像采集模块、留置针图像针尖定位装置、留置针图像针尖深度定位装置、血管成像模块、图像投影模块以及光源模块供电;The power supply module is used to supply power to the image acquisition module, the image needle tip positioning device of the indwelling needle, the image needle tip depth positioning device of the indwelling needle, the blood vessel imaging module, the image projection module and the light source module;
光源模块用于向皮肤投射红外光;The light source module is used to project infrared light to the skin;
图像采集模块用于在红外光环境下采集待定位的留置针图像,其中待定位的留置针图像中包括多个反光层区域与留置针针头区域;The image acquisition module is used to collect an image of the indwelling needle to be positioned in an infrared light environment, where the image of the indwelling needle to be positioned includes a plurality of reflective layer areas and the indwelling needle tip area;
留置针图像针尖定位装置用于输入待定位的留置针图像,输出留置针图像中 的针尖位置点坐标;The indwelling needle image needle point positioning device is used to input the indwelling needle image to be positioned, and output the needle point position point coordinates in the indwelling needle image;
留置针图像针尖深度定位装置用于输入待定位的留置针图像,输出留置针图像中的针尖深度;The indwelling needle image needle tip depth positioning device is used to input the indwelling needle image to be positioned, and output the needle tip depth in the indwelling needle image;
血管成像模块用于获得血管图像;The blood vessel imaging module is used to obtain blood vessel images;
图像投影模块用于将所述的血管图像投影在皮肤上;The image projection module is used to project the blood vessel image on the skin;
图像投影模块还用于根据针尖位置点坐标,将针尖叠加投影在血管图像上;The image projection module is also used to superimpose and project the needle tip on the blood vessel image according to the coordinates of the needle tip position;
图像投影模块还用于将针尖深度投影在皮肤上。The image projection module is also used to project the needle tip depth on the skin.
在本实施例中留置针为实施例一中提供的在影像环境下实现针尖定位的留置针。In this embodiment, the indwelling needle is the indwelling needle provided in the first embodiment for realizing the needle tip positioning under the image environment.
本实施例中提供的留置针针尖定位系统实现的功能有:The functions realized by the indwelling needle tip positioning system provided in this embodiment are:
1、将血管位置投影在皮肤上;1. Project the position of the blood vessel on the skin;
2、将针尖的位置与血管位置叠加投影在皮肤上,以使得医务人员可以实时地在患者的皮肤上查看到针尖在血管中的位置;2. The position of the needle tip and the position of the blood vessel are superimposed and projected on the skin, so that the medical staff can view the position of the needle tip in the blood vessel on the patient's skin in real time;
3、将针尖的深度信息投影到皮肤上,以使得义务人员可以实时地看到针尖的深度。3. Project the depth information of the needle tip onto the skin so that volunteers can see the depth of the needle tip in real time.
在本实施例中通过血管成像模块实现血管图像的获得,血管成像模块采用现有技术中已经成熟的血管成像仪,该血管成像仪也是利用了血管在红外的照射下在图像中呈现出不同的颜色实现的血管图像的获得。In this embodiment, the blood vessel imaging module is used to obtain the blood vessel image. The blood vessel imaging module adopts a mature blood vessel imager in the prior art. The blood vessel imager also uses the blood vessels to show different images in the image under infrared irradiation. Color-realized blood vessel image acquisition.
在本实施例中留置针图像针尖定位装置、留置针针尖深度定位装置以及血管成像装置可以集成在一个微处理器中进行实现。In this embodiment, the image needle tip positioning device of the indwelling needle, the needle tip depth positioning device of the indwelling needle, and the blood vessel imaging device can be integrated in a microprocessor for implementation.
可选地,图像采集模块为近红外灵敏的感光模组。Optionally, the image acquisition module is a near-infrared sensitive photosensitive module.
在本实施例中,图像采集模块为OV2710DVP模组。In this embodiment, the image acquisition module is the OV2710DVP module.
可选地,光源模块包括光学镜片以及近红外光源,其中所述的近红外光源为波长为700nm-1700nm的近红外光源。Optionally, the light source module includes an optical lens and a near-infrared light source, wherein the near-infrared light source is a near-infrared light source with a wavelength of 700 nm to 1700 nm.
作为一种最优的实施方式,近红外光源选择波长为850nm或940nm的近红外光源。As an optimal implementation, the near-infrared light source selects a near-infrared light source with a wavelength of 850 nm or 940 nm.
在本实施例中,图像投影模块在将针尖的位置与血管位置叠加投影在皮肤上时,设置一个标记点代表针尖位置投影在皮肤上,该标记点可以是圆形、三角形、星型等,颜色可以是红色、绿色等能够在皮肤上显示的任意颜色。In this embodiment, when the image projection module superimposes the needle tip position and the blood vessel position on the skin, it sets a marker point to represent the needle tip position projected on the skin. The marker point can be a circle, a triangle, a star, etc. The color can be any color that can be displayed on the skin, such as red and green.
在本实施例中,图像采集识别装置还包括风扇、按键模块等。In this embodiment, the image acquisition and recognition device further includes a fan, a button module, and the like.

Claims (9)

  1. 一种在影像环境下实现针尖定位的留置针,包括留置针本体(1),所述的留置针本体(1)包括针头(1-1),其特征在于,在所述的留置针本体(1)上设置有定位层(2);所述的定位层(2)包括反光层(2-1),所述的反光层(2-1)在影像环境下显示为高亮区域。An indwelling needle for realizing needle tip positioning in an image environment, comprising an indwelling needle body (1), the indwelling needle body (1) includes a needle (1-1), and is characterized in that the indwelling needle body ( 1) is provided with a positioning layer (2); the positioning layer (2) includes a reflective layer (2-1), and the reflective layer (2-1) is displayed as a highlight area in an image environment.
  2. 如权利要求1所述的在影像环境下实现针尖定位的留置针,其特征在于,所述的定位层(2)还包括吸光层(2-2),所述的吸光层(2-2)在影像环境下显示为阴影区域,所述的反光层(2-1)与所述的吸光层(2-2)沿着所述针头(1-1)长度方向交错设置。The indwelling needle for realizing needle tip positioning in an imaging environment according to claim 1, wherein the positioning layer (2) further comprises a light-absorbing layer (2-2), and the light-absorbing layer (2-2) It is displayed as a shaded area in an image environment, and the light-reflecting layer (2-1) and the light-absorbing layer (2-2) are staggered along the length direction of the needle (1-1).
  3. 如权利要求2所述的在影像环境下实现针尖定位的留置针,其特征在于,所述的反光层(2-1)的形状与吸光层(2-2)的形状均为轴对称图形;The indwelling needle for realizing needle tip positioning in an image environment according to claim 2, wherein the shape of the light-reflecting layer (2-1) and the shape of the light-absorbing layer (2-2) are both axially symmetrical figures;
    所述的反光层(2-1)与吸光层(2-2)的对称轴与所述的针头(1-1)斜面平行于水平面朝向上方时所在的直线处于同一条直线或与平行设置。The symmetry axis of the light-reflecting layer (2-1) and the light-absorbing layer (2-2) is in the same straight line or parallel to the line on which the inclined plane of the needle (1-1) is parallel to the horizontal plane and faces upward. Set up.
  4. 如权利要求3所述的在影像环境下实现针尖定位的留置针,其特征在于,所述的反光层(2-1)与所述的吸光层(2-2)均为矩形。The indwelling needle for realizing needle tip positioning in an image environment according to claim 3, characterized in that the light-reflecting layer (2-1) and the light-absorbing layer (2-2) are both rectangular.
  5. 如权利要求4所述的在影像环境下实现针尖定位的留置针,其特征在于,所述的留置针本体(1)还包括沿着所述针头(1-1)长度方向设置的底部(1-2)、套管(1-3)以及针套筒(1-4),所述的针头(1-1)安装在所述的针套筒(1-4)上;The indwelling needle for realizing needle tip positioning in an imaging environment according to claim 4, characterized in that, the indwelling needle body (1) further comprises a bottom (1) arranged along the length direction of the needle (1-1) -2), a sleeve (1-3) and a needle sleeve (1-4), the needle (1-1) is installed on the needle sleeve (1-4);
    所述的定位层(2)沿着所述底部(1-2)、套管(1-3)和/或针套 筒(1-4)的外圆周设置。The positioning layer (2) is arranged along the outer circumference of the bottom (1-2), the sleeve (1-3) and/or the needle sleeve (1-4).
  6. 如权利要求5所述的在影像环境下实现针尖定位的留置针,其特征在于,所述的定位层(2)沿着所述针套筒(1-4)的外圆周设置。The indwelling needle for realizing needle tip positioning in an image environment according to claim 5, wherein the positioning layer (2) is arranged along the outer circumference of the needle sleeve (1-4).
  7. 如权利要求6所述的在影像环境下实现针尖定位的留置针,其特征在于,所述的留置针本体(1)还包括针柄(1-5),所述的定位层(2)还沿着所述的针柄的长度方向设置。The indwelling needle for realizing needle tip positioning in an image environment according to claim 6, characterized in that the indwelling needle body (1) further comprises a needle handle (1-5), and the positioning layer (2) is also It is arranged along the length of the needle handle.
  8. 如权利要求2所述的在影像环境下实现针尖定位的留置针,其特征在于,所述的定位层(2)包括多个反光层(2-1)以及多个吸光层(2-2),所述的多个反光层(2-1)的面积沿着留置针长度方向逐渐增大或减小。The indwelling needle for realizing needle tip positioning in an imaging environment according to claim 2, wherein the positioning layer (2) includes a plurality of light-reflecting layers (2-1) and a plurality of light-absorbing layers (2-2) The area of the plurality of reflective layers (2-1) gradually increases or decreases along the length direction of the indwelling needle.
  9. 如权利要求8所述的在影像环境下实现针尖定位的留置针,其特征在于,所述的多个反光层(2-1)中最大面积的反光层(2-1)面积的数值y为:The indwelling needle for realizing needle tip positioning in an image environment according to claim 8, wherein the value y of the area of the largest area of the reflective layer (2-1) among the plurality of reflective layers (2-1) is :
    Figure PCTCN2020133557-appb-100001
    Figure PCTCN2020133557-appb-100001
    其中a、b、h 1、h 2、p、q 1以及q 2均为常数参数,x为反光层(2-1)的反光度;a>0,b>0,h 1<0,h 2<0,p>0,q 1>0,q 2>0。 Among them, a, b, h 1 , h 2 , p, q 1 and q 2 are all constant parameters, and x is the reflectance of the reflective layer (2-1); a>0, b>0, h 1 <0, h 2 <0, p>0, q 1 >0, q 2 >0.
PCT/CN2020/133557 2019-12-10 2020-12-03 Indwelling needle that achieves needle tip positioning in image environment WO2021115190A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911257589.2A CN110841139A (en) 2019-12-10 2019-12-10 Remaining needle capable of realizing needle tip positioning in image environment
CN201911257589.2 2019-12-10

Publications (1)

Publication Number Publication Date
WO2021115190A1 true WO2021115190A1 (en) 2021-06-17

Family

ID=69608513

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/133557 WO2021115190A1 (en) 2019-12-10 2020-12-03 Indwelling needle that achieves needle tip positioning in image environment

Country Status (2)

Country Link
CN (1) CN110841139A (en)
WO (1) WO2021115190A1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110841139A (en) * 2019-12-10 2020-02-28 深圳市中科微光医疗器械技术有限公司 Remaining needle capable of realizing needle tip positioning in image environment
CN112101575B (en) * 2020-11-04 2021-04-30 江苏集萃微纳自动化系统与装备技术研究所有限公司 Three-dimensional positioning method of micromanipulation platform for cell injection

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002064188A2 (en) * 2001-02-12 2002-08-22 Board Of Trustees Of The University Of Arkansas Infrared assisted monitoring of a catheter
WO2008098241A1 (en) * 2007-02-09 2008-08-14 Vustik, Inc. Infrared-visible needle
CN102481098A (en) * 2009-07-09 2012-05-30 贝克顿·迪金森公司 A system and method for visualizing needle entry into a body
CN102846308A (en) * 2011-06-28 2013-01-02 克里斯蒂数字系统美国有限公司 Method and apparatus for detection of catheter location for intravenous access
CN203619992U (en) * 2013-12-09 2014-06-04 苏州鱼跃医疗科技有限公司 Remaining needle
CN110841139A (en) * 2019-12-10 2020-02-28 深圳市中科微光医疗器械技术有限公司 Remaining needle capable of realizing needle tip positioning in image environment
CN110992388A (en) * 2019-12-10 2020-04-10 深圳市中科微光医疗器械技术有限公司 Remaining needle image segmentation model construction and needle tip positioning method, device and system
CN211485996U (en) * 2019-12-10 2020-09-15 深圳市中科微光医疗器械技术有限公司 Needle tip positioning system of remaining needle
CN212141071U (en) * 2019-12-10 2020-12-15 深圳市中科微光医疗器械技术有限公司 Remaining needle capable of realizing needle tip positioning in image environment

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002064188A2 (en) * 2001-02-12 2002-08-22 Board Of Trustees Of The University Of Arkansas Infrared assisted monitoring of a catheter
WO2008098241A1 (en) * 2007-02-09 2008-08-14 Vustik, Inc. Infrared-visible needle
CN102481098A (en) * 2009-07-09 2012-05-30 贝克顿·迪金森公司 A system and method for visualizing needle entry into a body
CN102846308A (en) * 2011-06-28 2013-01-02 克里斯蒂数字系统美国有限公司 Method and apparatus for detection of catheter location for intravenous access
CN203619992U (en) * 2013-12-09 2014-06-04 苏州鱼跃医疗科技有限公司 Remaining needle
CN110841139A (en) * 2019-12-10 2020-02-28 深圳市中科微光医疗器械技术有限公司 Remaining needle capable of realizing needle tip positioning in image environment
CN110992388A (en) * 2019-12-10 2020-04-10 深圳市中科微光医疗器械技术有限公司 Remaining needle image segmentation model construction and needle tip positioning method, device and system
CN211485996U (en) * 2019-12-10 2020-09-15 深圳市中科微光医疗器械技术有限公司 Needle tip positioning system of remaining needle
CN212141071U (en) * 2019-12-10 2020-12-15 深圳市中科微光医疗器械技术有限公司 Remaining needle capable of realizing needle tip positioning in image environment

Also Published As

Publication number Publication date
CN110841139A (en) 2020-02-28

Similar Documents

Publication Publication Date Title
WO2021115191A1 (en) Indwelling needle image segmentation model construction method, apparatus and system, and needle tip positioning method, apparatus and system
WO2021115190A1 (en) Indwelling needle that achieves needle tip positioning in image environment
JP6302070B2 (en) Instrument tracking using markers
EP1196081B1 (en) Integrated imaging apparatus
EP2007273B1 (en) Vein navigation device
CN107456278A (en) A kind of ESS air navigation aid and system
US20150051460A1 (en) System and method for locating blood vessels and analysing blood
Nuthmann On the visual span during object search in real-world scenes
CN109637660B (en) Tongue diagnosis analysis method and system based on deep convolutional neural network
CN107041729A (en) Binocular near infrared imaging system and blood vessel recognition methods
WO2014125492A1 (en) Device, system and method for blood vessel imaging and marking
US20210307838A1 (en) Surgical navigation method and system
CN212141071U (en) Remaining needle capable of realizing needle tip positioning in image environment
CN106714681A (en) Systems, devices, and methods for tracking and compensating for patient motion during a medical imaging scan
WO2008136644A2 (en) Apparatus and method for recognizing subcutaneous vein pattern
JP4561320B2 (en) Blood vessel and injection needle position presentation device
Paquit et al. 3D and multispectral imaging for subcutaneous veins detection
CN104688184A (en) Vein imaging method for visible-light skin images
CN107270818A (en) It is a kind of to utilize the method for monitoring CCD the real time measures laser probe and plane of illumination spacing walk-off angle degree
JP2000182050A (en) Individual identifying device for animal
CN107397534A (en) A kind of integrated vein blood vessel identifying system and method
CN108703745A (en) Vein developing method based on structure light and vein imaging system
CN202078301U (en) Vessel finder
CN112183518B (en) Automatic vein target determination method, device and equipment
Jin et al. A robust method of eye torsion measurement for medical applications

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20900508

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20900508

Country of ref document: EP

Kind code of ref document: A1