CN112184653A - Binocular endoscope-based focus three-dimensional size measuring and displaying method - Google Patents
Binocular endoscope-based focus three-dimensional size measuring and displaying method Download PDFInfo
- Publication number
- CN112184653A CN112184653A CN202011011490.7A CN202011011490A CN112184653A CN 112184653 A CN112184653 A CN 112184653A CN 202011011490 A CN202011011490 A CN 202011011490A CN 112184653 A CN112184653 A CN 112184653A
- Authority
- CN
- China
- Prior art keywords
- probe
- focus
- point
- dimensional
- measuring
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 239000000523 sample Substances 0.000 claims abstract description 79
- 238000005259 measurement Methods 0.000 claims abstract description 38
- 230000003902 lesion Effects 0.000 claims description 33
- 238000001514 detection method Methods 0.000 claims description 17
- 238000000691 measurement method Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 9
- 208000037062 Polyps Diseases 0.000 description 7
- 230000000052 comparative effect Effects 0.000 description 5
- 210000002784 stomach Anatomy 0.000 description 4
- 230000003190 augmentative effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000032798 delamination Effects 0.000 description 2
- 230000004438 eyesight Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002674 endoscopic surgery Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002496 gastric effect Effects 0.000 description 1
- 210000001035 gastrointestinal tract Anatomy 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Instruments For Viewing The Inside Of Hollow Bodies (AREA)
- Endoscopes (AREA)
Abstract
The invention discloses a binocular endoscope-based focus three-dimensional size measuring and displaying method which comprises five steps of probe point selection, probe end point identification, end point binocular matching, focus three-dimensional measurement, virtual scale display and the like. The invention solves the limitation of utilizing a physical scale or a virtual scale to comparatively measure the size of the focus, and simultaneously solves the problem that the three-dimensional reconstruction measuring method is easy to mismatch in weak texture areas such as a focus target and the like, so that the three-dimensional measuring result is inaccurate.
Description
Technical Field
The invention relates to the technical field of endoscopes, in particular to a focus three-dimensional size measuring and displaying method based on a binocular endoscope.
Background
In modern medical treatment, the endoscope enables clinicians to discover and identify focuses and other physiological characteristics in gastrointestinal tracts, and has positive significance for the treatment of disease conditions, and the 3D endoscope can provide three-dimensional information compared with the traditional endoscope and can better reflect the real situation of a scene, on one hand, the endoscope can enable the clinicians to feel the visual effect of a 3D picture in the operation process, and provide vivid visual perception to help the doctors to operate the endoscope more accurately, on the other hand, the 3D endoscope can integrate a three-dimensional measurement function, and can perform accurate three-dimensional measurement on focus targets such as polyps.
The focus three-dimensional measurement method in mainstream endoscopic surgery can be divided into comparative measurement and three-dimensional reconstruction measurement, wherein the comparative measurement comprises physical scale measurement and virtual scale measurement. The physical scale measuring mode is that a physical measuring scale system is added on an endoscope system, and the basic principle is that a reference object with a known size is placed beside a measured object such as a focus to carry out comparative measurement. One is to take a comparative measurement directly using a physical scale that extends into the lesion area through the endoscope instrument channel, and the other is to set the endoscope instrument as a measuring scale, for example, attached outside the endoscope catheter. The method has the advantages of simplicity and directness, but has the defects that a physical scale is in large-area contact with a focus in the measuring process, and is easy to hurt a patient, so that the requirement on the operation capability of a doctor is high, and on the other hand, the method has limited measuring accuracy, larger error and narrower application range, can only be used for simple linear length measurement, and is difficult to measure curve length or surface area and volume.
Patent CN104146711A uses a virtual scale to perform the measurement method. Collimated light beams generated by a special optical system are irradiated on the surface of a focus to form a light spot with a fixed size, and the light spot is used as a reference object to be compared with the focus, so that the size information of the focus is obtained. Patent CN110603004A proposes a method for generating a virtual scale by using endoscope instrument features and light planes, which includes using an instrument (e.g. forceps, snares), placing the instrument at the front end of a lesion target, obtaining its position and orientation in a 3D camera by recognizing the instrument features, then using an augmented display technology to superimpose the virtual scale on the instrument end point contacting the lesion target, and performing a comparative length measurement, and another method is using a light plane generation module to generate a light plane to intersect the lesion target, where the three-dimensional coordinates of each point of the intersection line on the 3D camera image are known, and using an augmented reality technology to attach scales on the intersecting lines for measurement.
The method has the advantages of no need of contacting with the focus, improved operation safety, and simple and convenient operation. The method has the disadvantages that the method also uses the idea of contrast measurement, doctors read the size of the focus by observing a cursor or a virtual scale, the error is large, the accuracy is low, and the curve length or the surface volume and the volume are difficult to measure.
Three-dimensional reconstruction measurement is a method for obtaining a three-dimensional size by three-dimensionally reconstructing left and right images of an endoscope, and generally, left and right views of a certain scene are obtained through a monocular or binocular camera, a disparity map is obtained according to a binocular matching algorithm, then, a depth map is obtained through calculation, three-dimensional coordinates of each point in the images are obtained, and three-dimensional measurement is performed. The method has the advantages that other instruments are not needed, the three-dimensional information can be quickly and directly obtained only through the visual information, the operation is simple and convenient, the precision of the three-dimensional measurement result is high, and the cost is low. The most important step of the method is that the same target needs to be matched in left and right views when the parallax is calculated, but the texture features are weak in an endoscope scene, the background is similar to the color of a focus target, and the phenomenon of mismatching is easy to occur, so that large errors are caused.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a focus three-dimensional size measuring and displaying method based on a binocular endoscope,
a focus three-dimensional size measuring and displaying method based on binocular endoscope, the method uses the probe end point of endoscope instrument channel entering into body as characteristic point to replace the point of focus weak texture area, and displays the measuring result through three-dimensional virtual scale, the method includes the following steps:
s1: selecting points by the probe, namely, selecting points by moving the probe according to the feature point selection specification in a binocular endoscope scene, and respectively measuring the linear length, curve length, surface area and volume of a focus;
s2: identifying probe end points, namely recording sequences formed by the probe end points and two-dimensional coordinates of the probe end points through an end point detection algorithm combining foreground detection and angular point detection;
s3: the end point is matched in a binocular mode, namely, the parallax of the recorded probe end point is obtained through binocular matching, and the depth value of the parallax is calculated through a trigonometry method to obtain the three-dimensional coordinate of the end point;
s4: measuring the three-dimensional size of the focus, namely measuring the three-dimensional size corresponding to the focus according to a measuring method of the linear length, the curve length, the surface area and the volume by utilizing a recorded sequence formed by the probe end points and the three-dimensional coordinates of the probe end points;
s5: and displaying by a virtual scale, namely displaying a corresponding three-dimensional measurement result of the focus by a straight line, a curve and a contour three-dimensional virtual scale.
Further, the specification of feature point selection in S1 is to move the probe according to the corresponding movement rule according to the requirement of measuring different dimensions of the lesion, specifically:
when measuring the linear length of the focus, respectively moving the probe head to two end points of the linear span and recording;
when the curve length of the focus is measured, controlling the probe head to move stably along a corresponding curve path and recording all detected probe end points;
when measuring the surface area and the volume of a focus, firstly moving the head of a probe to the central area of the focus, recording the end point of the probe as a central point, and then moving the head of the probe to the outer convex point and the inner concave point of the focus contour curve clockwise or anticlockwise and recording; in the recording process, if the included angle between the connecting line of the adjacent points and the central point is more than 90 degrees, the probe is added between the adjacent points of the outline curve according to the 45-degree interval for point selection and recording.
Further, the endpoint detection algorithm in S2 is specifically:
firstly, detecting a moving probe through a foreground detection algorithm, extracting a probe image, and carrying out morphological image processing of firstly corroding and then expanding to obtain a purer probe target;
then, detecting all the angular points of the probe image through an angular point detection algorithm, and extracting the middle points of intersecting lines of the probe image and a view frame of the endoscope camera;
and finally, calculating Euclidean distances between all the corners and the middle point of the intersection line, and recording the corner point farthest from the middle point, namely the end point of the probe.
Further, the method for measuring the surface area and the volume in S4 is an automatic layered measurement method, specifically:
firstly, connecting all recorded probe end points on a focus contour in sequence to form a closed polygon, and fitting the closed polygon into a plane serving as a reference plane;
then, relative to the reference surface, increasing or decreasing according to a fixed height to obtain a plane parallel to the reference surface, selecting an intersection point with the surface of the lesion on the plane, and forming a closed polygon by the intersection points to form a layered plane;
and finally, forming the prismatic table by two adjacent layered planes, calculating the side area and the volume of each prismatic table, and accumulating all calculation results to obtain the surface area and the volume of the focus.
Further, the virtual scale display of S5 is specifically as follows:
the straight virtual scale is used for calculating a pixel length value corresponding to the scale length of 1mm according to the three-dimensional length and the two-dimensional pixel length of a line segment formed by the end points of the two probes, generating a plurality of scale points on the line segment according to the scale of 1mm, and generating scale lines in the direction of the vertical line segment by taking the scale points as starting points;
the curve virtual scale is based on a straight line virtual scale and is formed by connecting a plurality of straight line virtual scales;
the outline virtual scale is a closed curve virtual scale formed by connecting a plurality of linear virtual scales end to end, and numerical values of layered contour lines, lesion surface areas and volumes are displayed in a lesion area.
The invention has the following beneficial effects:
the invention solves the dangerousness of utilizing a physical or virtual scale to comparatively measure the size of the focus and the limitation that only rough linear measurement can be carried out, compared with a three-dimensional reconstruction measuring method, the invention solves the problem that the three-dimensional measuring result is inaccurate because the weak texture regions such as the focus are easy to be mismatched, and improves the accuracy of measuring the three-dimensional size of the focus target.
The invention can accurately measure the three-dimensional size of the focus, provides a relatively accurate measurement value for a doctor, can generate a three-dimensional virtual scale to display the size information of the focus in real time, assists the doctor to judge, and has simple and convenient operation and reliable result.
Drawings
Fig. 1 is a flowchart of a binocular endoscope-based lesion three-dimensional size measurement and display method according to an embodiment of the present invention.
Fig. 2 is a schematic view of a binocular endoscope based on a binocular endoscope lesion three-dimensional size measuring and displaying method according to an embodiment of the present invention.
Fig. 3 is a schematic view of the linear measurement of the binocular endoscope based lesion three-dimensional size measurement and display method according to the embodiment of the present invention.
Fig. 4 is a curve measurement schematic diagram of a binocular endoscope-based lesion three-dimensional size measurement and display method according to an embodiment of the present invention.
Fig. 5 is a schematic surface area and volume measurement diagram of a binocular endoscope-based lesion three-dimensional size measurement and display method according to an embodiment of the present invention.
Fig. 6 is a schematic diagram of the stereoscopic vision and triangulation principle of the binocular endoscope-based lesion three-dimensional size measurement and display method according to the embodiment of the invention.
Fig. 7 is a schematic view of a straight virtual scale of a binocular endoscope-based lesion three-dimensional size measuring and displaying method according to an embodiment of the present invention.
Fig. 8 is a schematic view of a virtual ruler for measuring and displaying the three-dimensional size of a lesion based on a binocular endoscope according to an embodiment of the present invention.
Fig. 9 is a schematic diagram of a virtual contour scale and an automatic layered contour line of a binocular endoscope-based lesion three-dimensional size measuring and displaying method according to an embodiment of the present invention.
Fig. 10 is a schematic view of the measuring straight line length in the stomach model of the binocular endoscope-based lesion three-dimensional size measuring and displaying method according to the embodiment of the present invention.
Fig. 11 is a schematic three-dimensional virtual scale for measuring curve length in a stomach model according to the binocular endoscope-based lesion three-dimensional size measuring and displaying method of the present invention.
Fig. 12 is a schematic view of the binocular endoscope based lesion three-dimensional size measuring and displaying method of the present invention comparing the measurement accuracy with a real scale.
Fig. 13 is a schematic view of the binocular endoscope based lesion three-dimensional size measuring and displaying method of the present invention comparing the measurement accuracy with a real flexible scale.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments, and the objects and effects of the present invention will become more apparent, it being understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.
The invention relates to a binocular endoscope-based focus three-dimensional size measuring and displaying method, which is characterized in that a probe end point entering a body through an endoscope instrument channel is used as a characteristic point to replace a point of a focus weak texture area, and a measuring result is displayed through a three-dimensional virtual scale, as shown in figure 1, the method specifically comprises the following steps:
s1: selecting points by the probe, namely, selecting points by moving the probe according to the feature point selection specification in a binocular endoscope scene, and respectively measuring the linear length, curve length, surface area and volume of a focus;
the binocular endoscopic configuration used in this example is shown in fig. 2, where 101 is the left camera, 102 is the right camera, 103 is the light source, 105 is the endoscopic instrument channel, and 106 is the probe. Fig. 3 is a schematic view of the measurement of the linear width or length dimension of a lesion target, 110 representing an image of a polyp in a binocular endoscopic scene, where the probe head is moved to two end points of a linear span, respectively, and the probe is controlled to slightly reciprocate in the linear direction; FIG. 4 is a schematic illustration of measuring the length of a curve of a polyp surface controlling the smooth movement of the probe head along the curved path to be measured; fig. 5 is a schematic diagram for measuring the surface area and volume of the polyp, 113 is an automatic layering contour line, 114 is the highest point of the polyp area, 9 points with large polyp contour curve fluctuation are selected, the head of the probe is moved to the points respectively, the probe is controlled to slightly move back and forth in the corresponding direction, and the end point of the probe is recorded.
S2: the probe endpoint identification is to record a sequence formed by probe endpoints and two-dimensional coordinates of the probe endpoints through an endpoint detection algorithm combining foreground detection and angular point detection, and specifically comprises the following steps:
the method comprises the following steps of taking a moving probe as a moving foreground target, detecting the moving probe through a foreground detection algorithm based on a Gaussian Mixture Model (GMM), extracting a probe image, and performing morphological image processing operations such as dilation corrosion to obtain a purer probe target image;
detecting all corners of the probe target image by using a Harris corner detection algorithm, and extracting the middle point of an intersection line of the probe image and a view frame of a camera of the endoscope; and calculating Euclidean distances between all corner points and the middle point of the intersecting line, and recording the corner point farthest from the middle point, namely the end point of the probe, namely 111 in the figures 3-5.
S3: the end point is matched in a binocular mode, namely, the parallax of the recorded probe end point is obtained through binocular matching, and the depth value of the parallax is calculated through a trigonometry method to obtain the three-dimensional coordinate of the end point;
in this example, the end points of the left and right views are binocular matched by an SGBM (Semi-global Matching) binocular Matching algorithm, fig. 6 is a schematic diagram of binocular stereo vision, and the abscissa of the object point P on the imaging planes of the left and right cameras 101 and 102 is xl，xrAfter epipolar line correction is completed, the imaging points on the left and right views have horizontal parallax and no vertical parallax, the baseline distance of the left and right cameras is B, the focal length is f, and the distance is calculated according to the triangleThe measurement method calculates the formula:
and calculating the depth value of the object point P, and calculating to obtain the three-dimensional coordinate of the object point P according to the parameters calibrated by the two eyes.
S4: measuring the three-dimensional size of the focus, namely measuring the three-dimensional size corresponding to the focus according to a measuring method of the linear length, the curve length, the surface area and the volume by utilizing a recorded sequence formed by the probe end points and the three-dimensional coordinates of the probe end points;
the linear distance measurement specifically comprises the following steps: two characteristic points are selected, and the Euclidean distance between the two points is calculated through coordinate values of the two points.
The curve distance measurement specifically comprises: and moving the probe along the curve track of the polyp surface, recording all detected probe end points, obtaining the distance between adjacent points by a linear distance measuring method, and accumulating the lengths of all adjacent line segments to obtain the length of the curve.
The surface area and volume measuring method is an automatic layering measuring method, and specifically comprises the following steps:
firstly, connecting all recorded probe end points on a focus contour in sequence to form a closed polygon, forming a triangle by every two adjacent points on the polygon and an initial point, and calculating the area of the triangle by a Helen formula:
wherein a, b and c are the side length of the triangle, and p is half of the perimeter of the triangle. And accumulating the areas of all the triangles to obtain the area of the polygon. And fits the polygon to the reference plane.
Then, a plane parallel to the reference plane is obtained by increasing or decreasing the fixed height of 1mm with respect to the reference plane, and the intersection points with the lesion surface are selected on the plane, and the closed polygons formed by them constitute the layered plane.
And finally, forming the prismatic table by two adjacent layered planes, calculating the side area and the volume of each prismatic table, and accumulating all calculation results to obtain the surface area and the volume of the focus.
The perimeter and the area of the bottom surface of each layer are calculated according to the method, finally the volume is calculated according to a contour line method, and the surface area is calculated according to a circular truncated cone and cone side area formula, as shown in the following formula:
wherein n represents the number of delamination layers, h represents the delamination height, i.e. 1mm, ciIs the profile perimeter of the ith layer, siIs the area of the i-th layer,/iThe length of the bus of the ith layer is obtained by calculating the Euclidean distance between two points with the same x coordinate on the upper and lower bottom surface contours of a certain layer.
S5: displaying by a virtual scale, namely displaying a corresponding three-dimensional measurement result of the focus by a straight line, a curve and a contour three-dimensional virtual scale, specifically:
the linear virtual scale is used for calculating a pixel length value corresponding to the 1mm scale length according to the three-dimensional length and the two-dimensional pixel length of a line segment formed by the end points of the two probes, generating a plurality of scale points on the line segment according to the 1mm scale, and generating scale marks in the direction of the vertical line segment by taking the scale points as starting points. Fig. 7 is a schematic view of a virtual scale for measuring the length of a straight line.
The curve virtual scale is based on a straight line virtual scale and is formed by connecting a plurality of straight line virtual scales; fig. 8 is a schematic diagram of a virtual scale for curve length measurement.
The outline virtual scale is a closed curve virtual scale formed by connecting a plurality of linear virtual scales end to end, and numerical values of layered contour lines, lesion surface areas and volumes are displayed in a lesion area. As shown in fig. 9, a schematic diagram of a virtual scale for surface area and volume measurement is shown, 115 is a profile virtual gauge, and the scale of the profile virtual gauge is 1 mm.
Fig. 10 and 11 are schematic diagrams of a three-dimensional virtual scale for measuring the linear length and the curve length in the stomach model by the method of the invention. FIG. 12 is a graph comparing the accuracy of measuring a straight line of a gastric model using the method of the present invention with a real scale, and it can be seen from the graph that the length of the straight line measured using the method of the present invention is substantially the same as the real scale with high accuracy. FIG. 13 is a graph comparing the accuracy of curves measured using the method of the present invention and a real flexible scale for a model of the stomach, from which it can be seen that the length of the curve measured using the method of the present invention is also very close to the flexible scale, and the accuracy is also very high.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and although the invention has been described in detail with reference to the foregoing examples, it will be apparent to those skilled in the art that various changes in the form and details of the embodiments may be made and equivalents may be substituted for elements thereof. All modifications, equivalents and the like which come within the spirit and principle of the invention are intended to be included within the scope of the invention.
Claims (5)
1. A focus three-dimensional size measuring and displaying method based on binocular endoscope is characterized in that the method uses the probe end point of endoscope instrument channel entering into body as characteristic point to replace the point of focus weak texture area, and displays the measuring result through three-dimensional virtual scale, the method includes the following steps:
s1: and (4) probe point selection, namely, the probe is moved according to the feature point selection specification in a binocular endoscope scene to select points, and the measurement of the linear length, the curve length, the surface area and the volume of the focus is realized respectively.
S2: identifying probe end points, namely recording sequences formed by the probe end points and two-dimensional coordinates of the probe end points through an end point detection algorithm combining foreground detection and angular point detection;
s3: the end point is matched in a binocular mode, namely, the parallax of the recorded probe end point is obtained through binocular matching, and the depth value of the parallax is calculated through a trigonometry method to obtain the three-dimensional coordinate of the end point;
s4: measuring the three-dimensional size of the focus, namely measuring the three-dimensional size corresponding to the focus according to a measuring method of the linear length, the curve length, the surface area and the volume by utilizing a recorded sequence formed by the probe end points and the three-dimensional coordinates of the probe end points;
s5: and displaying by a virtual scale, namely displaying a corresponding three-dimensional measurement result of the focus by a straight line, a curve and a contour three-dimensional virtual scale.
2. The binocular endoscope based lesion three-dimensional size measuring and displaying method according to claim 1, wherein the feature point selection criterion in S1 is to move the probe according to the corresponding movement rule according to the requirement of measuring the lesion different dimension sizes, and specifically comprises:
when measuring the linear length of the focus, respectively moving the probe head to two end points of the linear span and recording;
when the curve length of the focus is measured, controlling the probe head to move stably along a corresponding curve path and recording all detected probe end points;
when measuring the surface area and the volume of a focus, firstly moving the head of a probe to the central area of the focus, recording the end point of the probe as a central point, and then moving the head of the probe to the outer convex point and the inner concave point of the focus contour curve clockwise or anticlockwise and recording; in the recording process, if the included angle between the connecting line of the adjacent points and the central point is more than 90 degrees, the probe is added between the adjacent points of the outline curve according to the 45-degree interval for point selection and recording.
3. The binocular endoscope based lesion three-dimensional size measuring and displaying method according to claim 1, wherein the endpoint detection algorithm in S2 is specifically:
firstly, detecting a moving probe through a foreground detection algorithm, extracting a probe image, and carrying out morphological image processing of firstly corroding and then expanding to obtain a purer probe target;
then, detecting all the angular points of the probe image through an angular point detection algorithm, and extracting the middle points of intersecting lines of the probe image and a view frame of the endoscope camera;
and finally, calculating Euclidean distances between all the corners and the middle point of the intersection line, and recording the corner point farthest from the middle point, namely the end point of the probe.
4. The binocular endoscope based lesion three-dimensional size measuring and displaying method according to claim 1, wherein the surface area and volume measuring method in S4 is an automatic layering measurement method, specifically:
firstly, connecting all recorded probe end points on a focus contour in sequence to form a closed polygon, and fitting the closed polygon into a plane serving as a reference plane;
then, relative to the reference surface, increasing or decreasing according to a fixed height to obtain a plane parallel to the reference surface, selecting an intersection point with the surface of the lesion on the plane, and forming a closed polygon by the intersection points to form a layered plane;
and finally, forming the prismatic table by two adjacent layered planes, calculating the side area and the volume of each prismatic table, and accumulating all calculation results to obtain the surface area and the volume of the focus.
5. The binocular endoscope based lesion three-dimensional size measuring and displaying method according to claim 1, wherein the virtual scale display of S5 is specifically:
the straight virtual scale is used for calculating a pixel length value corresponding to the scale length of 1mm according to the three-dimensional length and the two-dimensional pixel length of a line segment formed by the end points of the two probes, generating a plurality of scale points on the line segment according to the scale of 1mm, and generating scale lines in the direction of the vertical line segment by taking the scale points as starting points;
the curve virtual scale is based on a straight line virtual scale and is formed by connecting a plurality of straight line virtual scales;
the outline virtual scale is a closed curve virtual scale formed by connecting a plurality of linear virtual scales end to end, and numerical values of layered contour lines, lesion surface areas and volumes are displayed in a lesion area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011011490.7A CN112184653B (en) | 2020-09-23 | 2020-09-23 | Binocular endoscope-based focus three-dimensional size measuring and displaying method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011011490.7A CN112184653B (en) | 2020-09-23 | 2020-09-23 | Binocular endoscope-based focus three-dimensional size measuring and displaying method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112184653A true CN112184653A (en) | 2021-01-05 |
| CN112184653B CN112184653B (en) | 2022-06-10 |
Family
ID=73956015
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011011490.7A Active CN112184653B (en) | 2020-09-23 | 2020-09-23 | Binocular endoscope-based focus three-dimensional size measuring and displaying method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112184653B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115311244A (en) * | 2022-08-23 | 2022-11-08 | 北京医准智能科技有限公司 | Method and device for determining lesion size, electronic equipment and storage medium |
| US20220375114A1 (en) * | 2021-05-24 | 2022-11-24 | Stryker Corporation | Systems and methods for generating three-dimensional measurements using endoscopic video data |
| CN116030118A (en) * | 2023-03-29 | 2023-04-28 | 杭州太美星程医药科技有限公司 | Method and device for determining focal short diameter, electronic equipment and storage medium |
| WO2024109610A1 (en) * | 2022-11-21 | 2024-05-30 | 杭州海康慧影科技有限公司 | Endoscope system, and apparatus and method for measuring spacing between in-vivo tissue features |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6101408A (en) * | 1996-08-22 | 2000-08-08 | Western Research Company, Inc. | Probe and method to obtain accurate area measurements from cervical lesions |
| CN203328720U (en) * | 2013-05-08 | 2013-12-11 | 上海大图医疗科技有限公司 | Non-contact three-dimensional ultrasound imaging system based on computer vision technology |
| US20180240246A1 (en) * | 2011-03-04 | 2018-08-23 | General Electric Company | Method and device for measuring features on or near an object |
| CN109443207A (en) * | 2018-11-19 | 2019-03-08 | 华中科技大学 | A kind of light pen robot in-situ measurement system and method |
| CN110986827A (en) * | 2019-12-25 | 2020-04-10 | 浙江工业大学 | Axle part size measuring device based on DIC |
-
2020
- 2020-09-23 CN CN202011011490.7A patent/CN112184653B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6101408A (en) * | 1996-08-22 | 2000-08-08 | Western Research Company, Inc. | Probe and method to obtain accurate area measurements from cervical lesions |
| US20180240246A1 (en) * | 2011-03-04 | 2018-08-23 | General Electric Company | Method and device for measuring features on or near an object |
| CN203328720U (en) * | 2013-05-08 | 2013-12-11 | 上海大图医疗科技有限公司 | Non-contact three-dimensional ultrasound imaging system based on computer vision technology |
| CN109443207A (en) * | 2018-11-19 | 2019-03-08 | 华中科技大学 | A kind of light pen robot in-situ measurement system and method |
| CN110986827A (en) * | 2019-12-25 | 2020-04-10 | 浙江工业大学 | Axle part size measuring device based on DIC |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220375114A1 (en) * | 2021-05-24 | 2022-11-24 | Stryker Corporation | Systems and methods for generating three-dimensional measurements using endoscopic video data |
| US11928834B2 (en) * | 2021-05-24 | 2024-03-12 | Stryker Corporation | Systems and methods for generating three-dimensional measurements using endoscopic video data |
| CN115311244A (en) * | 2022-08-23 | 2022-11-08 | 北京医准智能科技有限公司 | Method and device for determining lesion size, electronic equipment and storage medium |
| WO2024109610A1 (en) * | 2022-11-21 | 2024-05-30 | 杭州海康慧影科技有限公司 | Endoscope system, and apparatus and method for measuring spacing between in-vivo tissue features |
| CN116030118A (en) * | 2023-03-29 | 2023-04-28 | 杭州太美星程医药科技有限公司 | Method and device for determining focal short diameter, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112184653B (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112184653B (en) | Binocular endoscope-based focus three-dimensional size measuring and displaying method | |
| CN106952347B (en) | Ultrasonic surgery auxiliary navigation system based on binocular vision | |
| US11412993B2 (en) | System and method for scanning anatomical structures and for displaying a scanning result | |
| US10543045B2 (en) | System and method for providing a contour video with a 3D surface in a medical navigation system | |
| KR101799281B1 (en) | Endoscope for minimally invasive surgery | |
| US20220387130A1 (en) | Augmented reality headset for medical imaging | |
| US11896441B2 (en) | Systems and methods for measuring a distance using a stereoscopic endoscope | |
| Lathrop et al. | Minimally invasive holographic surface scanning for soft-tissue image registration | |
| CN103948432A (en) | Algorithm for augmented reality of three-dimensional endoscopic video and ultrasound image during operation | |
| JPH09511430A (en) | Three-dimensional data set registration system and registration method | |
| CN104408762A (en) | Method for obtaining object image information and three-dimensional model by using monocular unit and two-dimensional platform | |
| CN107595388A (en) | A kind of near infrared binocular visual stereoscopic matching process based on witch ball mark point | |
| CN107249427A (en) | Medical treatment device, medical image generation method and medical image generation program | |
| CN106236264A (en) | The gastrointestinal procedures air navigation aid of optically-based tracking and images match and system | |
| US11179218B2 (en) | Systems and methods for multi-modal sensing of depth in vision systems for automated surgical robots | |
| JP2020516408A (en) | Endoscopic measurement method and instrument | |
| CN113240726A (en) | Real-time measurement method for optical target size under endoscope | |
| CN108113629B (en) | Hard tube endoscope rotation angle measuring method and device | |
| Lee et al. | An optimized in vivo multiple-baseline stereo imaging system for skin wrinkles | |
| Malian et al. | Medphos: A new photogrammetric system for medical measurement | |
| JP4750197B2 (en) | Endoscope device | |
| Hyun et al. | Feasibility of obtaining quantitative 3-dimensional information using conventional endoscope: a pilot study | |
| CN111870211A (en) | Three-dimensional endoscope with instrument pose navigation function and navigation method thereof | |
| TW201818347A (en) | The method of complete endoscopic MIS instrument 3D position estimation using a single 2D image | |
| CN106236263A (en) | The gastrointestinal procedures air navigation aid decomposed based on scene and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |