CN116912282A - Three-dimensional segmentation method, device, equipment and storage medium based on medical image - Google Patents
Three-dimensional segmentation method, device, equipment and storage medium based on medical image Download PDFInfo
- Publication number
- CN116912282A CN116912282A CN202310659317.5A CN202310659317A CN116912282A CN 116912282 A CN116912282 A CN 116912282A CN 202310659317 A CN202310659317 A CN 202310659317A CN 116912282 A CN116912282 A CN 116912282A
- Authority
- CN
- China
- Prior art keywords
- medical image
- medical
- image
- layer
- contour information
- 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.)
- Pending
Links
- 230000011218 segmentation Effects 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000004044 response Effects 0.000 claims abstract description 23
- 238000010845 search algorithm Methods 0.000 claims abstract description 18
- 238000013507 mapping Methods 0.000 claims abstract description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 24
- 230000008569 process Effects 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 238000006073 displacement reaction Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000013459 approach Methods 0.000 description 6
- 210000000689 upper leg Anatomy 0.000 description 6
- 238000009877 rendering Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 210000002303 tibia Anatomy 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 210000000988 bone and bone Anatomy 0.000 description 2
- 238000002591 computed tomography Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/41—Medical
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The present disclosure relates to a three-dimensional segmentation method, apparatus, device and storage medium based on medical images, wherein the method comprises: displaying a sequence of medical images of a medical object, the sequence of medical images comprising a plurality of layers of medical images; adjusting a window width of the medical image in response to a first operation in a first direction, and adjusting a window level of the medical image in response to a second operation in a second direction; updating gray values of all pixel points according to a preset mapping relation according to the window width, the window level and the original pixel values of all pixel points in the medical image; generating contour information in the multi-layer medical image by adopting a path search algorithm based on the updated medical image; and carrying out three-dimensional reconstruction according to the contour information in the multi-layer medical image to obtain a three-dimensional segmentation result of the medical object. According to the technical scheme of the present disclosure, on the basis of maintaining the precision of the manual segmentation mode, the segmentation speed and efficiency are improved.
Description
Technical Field
The disclosure relates to the technical field of image processing, and in particular relates to a three-dimensional segmentation method, device and equipment based on medical images and a storage medium.
Background
Medical image segmentation is to separate a foreground region of interest from an original medical image sequence by using a related image processing algorithm so as to facilitate subsequent processing tasks for the foreground region.
The medical image segmentation can be divided into automatic segmentation and manual segmentation according to an interactive mode, wherein in the automatic segmentation mode, a segmentation result is automatically output through a correlation algorithm according to preset relevant initial parameters of a region to be segmented, the correlation algorithm is a threshold segmentation method, a deep learning segmentation algorithm based on a deep neural network and the like, and the accuracy of the segmentation result of some specific data is required to be improved in the mode, and generalization is lacking; in the manual segmentation mode, a user manually sketches a region of interest in a medical image layer by layer based on an image sketching tool provided for the user, and the mode requires a large amount of manual operation intervention, so that the segmentation efficiency is low.
Disclosure of Invention
In order to solve the technical problems, the present disclosure provides a three-dimensional segmentation method, device, equipment and storage medium based on medical images.
In a first aspect, an embodiment of the present disclosure provides a three-dimensional segmentation method based on a medical image, including:
displaying a sequence of medical images of a medical object, the sequence of medical images comprising a plurality of layers of medical images;
adjusting a window width of the medical image in response to a first operation in a first direction, and adjusting a window level of the medical image in response to a second operation in a second direction;
updating gray values of all pixel points according to a preset mapping relation according to the window width, the window level and the original pixel values of all pixel points in the medical image; wherein, for the edges of a foreground region and a background region in the medical image, the gray value difference between the foreground region and the edge is larger than a preset threshold value by adjusting the window width and the window level, and the gray value difference between the background region and the edge is larger than the preset threshold value;
generating contour information in the multi-layer medical image by adopting a path search algorithm based on the updated medical image;
and carrying out three-dimensional reconstruction according to the contour information in the multi-layer medical image to obtain a three-dimensional segmentation result of the medical object.
In a second aspect, embodiments of the present disclosure provide a medical image-based three-dimensional segmentation apparatus, comprising:
a display module for displaying a sequence of medical images of a medical object, the sequence of medical images comprising a plurality of layers of medical images;
an adjustment module for adjusting a window width of the medical image in response to a first operation in a first direction, and adjusting a window level of the medical image in response to a second operation in a second direction;
the updating module is used for updating the gray value of each pixel point according to the window width, the window level and the original pixel value of each pixel point in the medical image and a preset mapping relation; wherein, for the edges of a foreground region and a background region in the medical image, the gray value difference between the foreground region and the edge is larger than a preset threshold value by adjusting the window width and the window level, and the gray value difference between the background region and the edge is larger than the preset threshold value;
the drawing module is used for generating contour information in the multi-layer medical image by adopting a path search algorithm based on the updated medical image;
and the segmentation module is used for carrying out three-dimensional reconstruction according to the contour information in the multi-layer medical image to obtain a three-dimensional segmentation result of the medical object.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor; a memory for storing the processor-executable instructions; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the medical image-based three-dimensional segmentation method according to the first aspect.
In a fourth aspect, embodiments of the present disclosure provide a computer-readable storage medium storing a computer program, which when executed by a processor, implements the medical image-based three-dimensional segmentation method according to the first aspect.
Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages: the method for segmenting the medical image sequence can be used for conducting skeleton segmentation on structures such as femur and tibia, the manual segmentation method simplifies user operation, and improves segmentation speed and efficiency on the basis of keeping manual segmentation mode accuracy.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
In order to more clearly illustrate the embodiments of the present disclosure or the solutions in the prior art, the drawings that are required for the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
Fig. 1 is a schematic flow chart of a three-dimensional segmentation method based on medical images according to an embodiment of the disclosure;
fig. 2 is a schematic diagram of a three-dimensional segmentation result of a bone structure according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of another medical image-based three-dimensional segmentation method provided by an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a display interface according to an embodiment of the disclosure;
FIG. 5 is a schematic view of a visualization effect of a sagittal gradient image of a femur provided by an embodiment of the present disclosure;
FIG. 6 is a schematic diagram of a contouring process provided by an embodiment of the present disclosure;
FIG. 7 is a schematic diagram of a contour interpolation process according to an embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of a three-dimensional segmentation apparatus based on medical images according to an embodiment of the disclosure.
Detailed Description
In order that the above objects, features and advantages of the present disclosure may be more clearly understood, a further description of aspects of the present disclosure will be provided below. It should be noted that, without conflict, the embodiments of the present disclosure and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced otherwise than as described herein; it will be apparent that the embodiments in the specification are only some, but not all, embodiments of the disclosure.
Fig. 1 is a schematic flow chart of a three-dimensional segmentation method based on a medical image according to an embodiment of the present disclosure, where the method provided by the embodiment of the present disclosure may be performed by a three-dimensional segmentation apparatus based on a medical image, and the apparatus may be implemented by using software and/or hardware and may be integrated on any electronic device with computing capability.
As shown in fig. 1, a medical image-based three-dimensional segmentation method provided by an embodiment of the present disclosure may include:
step 101, a sequence of medical images of a medical object is presented.
The method is used for manually segmenting the scene by the medical image and realizing three-dimensional segmentation of the medical object. Wherein the medical object may be various anatomical structures in a medical setting, such as a femur, tibia, etc.
In this embodiment, the medical image sequence is obtained by performing image scanning on the medical object in the specified direction, the medical image sequence includes a plurality of layers of medical images, the plurality of layers of medical images respectively correspond to the plurality of layers of cross sections, and all medical images in the image scanning range are superimposed to obtain the medical image sequence. Among them, medical images include, but are not limited to, MR (Magnetic Resonance, magnetic resonance examination) images, CT (Computed Tomography, electronic computed tomography examination) images.
Step 102, adjusting a window width of the medical image in response to a first operation in a first direction, and adjusting a window level of the medical image in response to a second operation in a second direction.
In this embodiment, the window width and the window level are adjusted based on the displayed medical image sequence, so that the displayed medical image changes the gray value. Since most displays display 8-bit images, i.e. 256 gray scales, and the interval span of the pixel values of the MR original image is usually much larger than the range, the image displayed at a single time can only express a part of gray value information, and the adjustment process in this embodiment is divided into two aspects of window width and window level, wherein the window width is the interval of the original pixel values displayed, and the window level is the median of the window width interval.
Wherein the first direction and the second direction are different directions, the first operation and the second operation include, but are not limited to, a mouse movement operation, a touch trajectory, and the like.
As an example, taking a mouse pointer as an example, by providing a switch for activating/deactivating an adjustment function, after a user activates the switch, the displayed medical image is adjusted by a drag event of the mouse, and when a movement operation of the mouse pointer is detected, the window width of the medical image is adjusted according to the displacement of the mouse pointer in the horizontal direction, and the window level of the medical image is adjusted according to the displacement of the mouse pointer in the vertical direction. In this example, the control window width increases when the mouse pointer moves rightward in the horizontal direction, the control window width decreases when the horizontal direction moves leftward, the control window level increases when the vertical direction moves upward, and the control window level decreases when the vertical direction moves downward.
As another example, taking a touch screen as an example, a user slides on the touch screen with a stylus or a finger, adjusts a displayed medical image with movement of a touch point, adjusts a window width of the medical image according to displacement of the touch point in a horizontal direction when a movement operation of the touch point is detected, and adjusts a window level of the medical image according to displacement of the touch point in a vertical direction.
Step 103, updating the gray value of each pixel point according to the preset mapping relation according to the window width, the window level and the original pixel value of each pixel point in the medical image.
In this embodiment, after the window width and the window level are adjusted, the medical image is displayed according to the updated gray values, and for the edges of the foreground region and the background region in the medical image, the gray value difference between the foreground region and the edge is greater than a preset threshold value and the gray value difference between the background region and the edge is greater than a preset threshold value by adjusting the window width and the window level, at this time, the medical image is adjusted to a state in which the gray values of the foreground region and the background region are similar, and the visible obvious difference exists between the edge region and the foreground region and the background region.
As an example, the mapping between window width and window level for the original pixel value to the image gray value is as follows:
where WW represents window width, WC represents window level, P represents original pixel value, and g represents gray value.
Step 104, generating contour information in the multi-layer medical image by adopting a path searching algorithm based on the updated medical image.
In this embodiment, after the displayed medical image is updated through the above steps, the foreground edge portion in the medical image is clear and obvious, and then contour information of the medical object is generated in the updated medical image based on the path search algorithm. Optionally, gradient transformation is performed based on the updated medical image, a gradient image is generated and stored in the memory, and the gradient image is processed by adopting a path search algorithm in response to a third operation on the displayed medical image, so as to generate contour information in the medical image, wherein the third operation is used for drawing a contour in the medical image.
And 105, performing three-dimensional reconstruction according to the contour information in the multi-layer medical image to obtain a three-dimensional segmentation result of the medical object.
In this embodiment, the contour information in the multi-layer medical image characterizes the contour of the multi-layer cross section of the medical object, and the three-dimensional segmentation result of the medical object is obtained by performing three-dimensional reconstruction through the contour information.
As an example, the above steps are performed on each layer of medical image, so as to obtain contour information in each layer of medical image, and further, three-dimensional reconstruction is performed according to the contour information in each layer of medical image, so as to obtain a three-dimensional segmentation result of the medical object. For example, a three-dimensional segmentation of a bone structure is shown with reference to fig. 2.
According to the technical scheme of the embodiment of the disclosure, through displaying a medical image sequence of a medical object, adjusting window width and window level of the medical image based on user operation, updating gray values of all pixel points according to a preset mapping relation according to original pixel values of all pixel points in the window width, the window level and the medical image, enabling a user to observe a region of interest and automatically determine the gray image which is displayed after adjustment, enabling edges of a foreground to be clear and obvious, improving accuracy of a foreground information enhancing process, generating contour information in a multi-layer medical image based on the updated medical image by adopting a path search algorithm, and carrying out three-dimensional reconstruction according to the contour information in the multi-layer medical image to obtain a three-dimensional segmentation result of the medical object.
Based on the above embodiments, fig. 3 is a schematic diagram of another three-dimensional segmentation method based on medical images according to an embodiment of the disclosure, as shown in fig. 3, and the method includes:
step 301, a sequence of medical images of a medical object is presented.
In this embodiment, the display interface is divided into four regions, where a sagittal medical image is displayed in a first region of the display interface, a coronal medical image is displayed in a second region of the display interface, and an axial medical image is displayed in a third region of the display interface, so that an imported medical image sequence can be displayed layer by layer from three directions of the sagittal, coronal, and axial positions, and a three-dimensional segmentation result is displayed in a fourth region of the display interface, and the display interface is shown in fig. 4.
Step 302, adjusting a window width of the medical image in response to a first operation in a first direction, and adjusting a window level of the medical image in response to a second operation in a second direction.
Step 303, updating the gray value of each pixel point according to the preset mapping relation according to the window width, the window level and the original pixel value of each pixel point in the medical image.
The explanation of the previous embodiments for steps 102, 103 applies equally to steps 302, 303.
Step 304, contour information in the K-layer medical image is generated using a path search algorithm.
In this embodiment, the medical image sequence is composed of N layers of medical images, N being larger than K. And for each layer of medical image, carrying out gradient transformation based on the updated medical image, generating a gradient image, storing the gradient image in a memory, and responding to a third operation on the displayed medical image, processing the gradient image by adopting a path search algorithm to generate contour information in the medical image.
Optionally, creating a blank image with the same size as the medical image, calculating a gradient of each pixel point in the updated medical image in the horizontal direction and the vertical direction for the pixel point to form a gradient vector, and further giving a modulus value of the gradient vector to the pixel point at the same position in the blank image, wherein the gradient expression is as follows:
wherein I (x, y) represents a gray value at the (x, y) position, gx, gy represent a gradient in the horizontal direction and a gradient in the vertical direction, respectively,is the gradient vector at the current position. In an actual implementation process, the gradient image may be stored in the memory only as an intermediate result, as input data for the next path search algorithm. The visualization effect of the sagittal gradient image of the femur is shown in fig. 5, in which detail textures inside the foreground and the background can be identified, and the edge contour of the femur is clearly visible.
In one embodiment of the present disclosure, the path search algorithm employs an Astar algorithm to draw a path from a starting position to a current position of the mouse pointer by acquiring the starting position selected in the medical image and the current position of the mouse pointer, taking the opposite image of the gradient image, the starting position, and the current position as inputs to the Astar algorithm.
As an example, by providing a switch with a contour drawing function, after a user activates the switch, a layer of medical image is selected, and a double click operation is performed at a position of a foreground edge in the medical image, a starting position is determined, and then a mouse pointer is controlled to slide along the foreground edge, an Astar algorithm is introduced in the sliding process, the Astar algorithm is an algorithm for searching a shortest path, and can calibrate an energy shortest path from the starting position to a current position in real time, the Astar algorithm takes an opposite image of a gradient image, the starting position and the current position of the mouse pointer as inputs, and outputs an energy shortest path, wherein a pixel value of each pixel in the opposite image is an opposite number of an original gradient image. Specifically, candidate nodes to be determined as nodes on the shortest path and the determined nodes on the shortest path are respectively stored, energy accumulation from a starting node to a current node is stored in a node data structure, a heuristic function h is a Manhattan distance from the current node to a termination node, f is the sum of g and h, and an energy accumulation process expression is as follows:
wherein OppositeGi represents the pixel value of the gradient opposite image at the node i position, the path value is 1 (when the current node is four neighborhoods of the previous node) or(when the current node is eight neighbors of the previous node). Because the gray value of the gradient image at the foreground edge is higher than that of other areas, the pixel value of the opposite image corresponding position is lower, the energy g approaches to the minimum when the path approaches to the foreground edge, and for the heuristic function h, the value of the heuristic function is decreased when the path approaches to the termination node gradually, and f approaches to the minimum value continuously along with iteration, so that the path approaches to the foreground edge and approaches to the end point simultaneously.
Further, during the interaction of drawing the outline, in response to the clicking operation at the current position, saving the drawn path and taking the clicking position as a new starting position, and when the mouse pointer is detected to continue sliding, taking the opposite image of the gradient image, the new starting position and the current position of the mouse pointer as inputs of an Astar algorithm to draw the path from the new starting position to the current position of the mouse pointer. In this example, during the interaction, the user may click the mouse as needed to lock the generated path, and reset the click position to the start position at the same time, and when the mouse pointer continues to slide, execute the Astar algorithm again to calibrate the next path until the current contour is closed. Fig. 6 is a schematic diagram of a contour drawing process in which discrete point spatial coordinates on a contour are sequentially recorded in real time.
And 305, obtaining the contour information in the N layers of medical images by adopting an interpolation algorithm based on the contour information in the K layers of medical images and the positions of the K layers of medical images in the medical image sequence.
And 306, performing three-dimensional reconstruction according to the contour information in the N layers of medical images to obtain a three-dimensional segmentation result of the medical object.
In this embodiment, for the N-layer medical image, the contour information of the K-layer medical image is obtained by executing the above steps, and then, based on the contour information in the K-layer medical image and the position of the K-layer medical image in the medical image sequence, the contour information in the N-layer medical image is obtained by adopting an interpolation algorithm, and the three-dimensional reconstruction is performed according to the contour information in the N-layer medical image, so as to obtain the three-dimensional segmentation result of the medical object.
As an example, in the contour interpolation process, contour information of all medical images between two layers of medical images with known contour information is calculated point by point according to the space coordinates of discrete points stored in the above steps, and the calculation formula is as follows:
wherein P is a point on the manually drawn contour in the first medical image, Q is a point corresponding to P on the manually drawn contour in the second medical image, the first medical image and the second medical image are two adjacent layers in the K layers of medical images, R is a point corresponding to P and Q in the interpolation contour, lambda is a proportion of a space between two layers of manually drawn contours divided by the contour generated by interpolation, and the proportion can be obtained according to the positions of the first medical image and the second medical image in the medical image sequence and the position of the medical image currently subjected to interpolation in the medical image sequence. Because the femur or tibia and other structures have the characteristic of similar appearance in a certain range of a certain azimuth, the contour information of other layers of medical images is generated by interpolation by selecting a plurality of range intervals with similar structures and manually drawing the contour, so that the efficient and accurate manual segmentation process is realized. The interpolation process between every two adjacent layers of medical images in the K layers of medical images is shown in fig. 7. After the contour information of each layer of medical image is obtained, the contour information is used for MPR (Multi Plane Reconstruction, multi-plane reconstruction), the MPR is used for superposing all images in an image scanning range, and then the image reconstruction is carried out on tissues in an image description range from other directions in a coronal position, a sagittal position or any other angle oblique position.
In the embodiment of the disclosure, the A-star algorithm is used for assisting in contour drawing, so that the speed and the accuracy of a manual contour drawing process are improved, and by providing a spatial contour interpolation algorithm, a user does not need to draw contours layer by layer, but only needs to draw key layers of contours, other layers are automatically generated by the algorithm, and the processing speed is improved.
Fig. 8 is a schematic structural diagram of a three-dimensional segmentation apparatus based on medical images according to an embodiment of the disclosure, and as shown in fig. 8, the three-dimensional segmentation apparatus based on medical images includes: the device comprises a display module 81, an adjustment module 82, an updating module 83, a drawing module 84 and a segmentation module 85.
Wherein the display module 81 is configured to display a medical image sequence of a medical object, the medical image sequence comprising a plurality of layers of medical images.
An adjustment module 82 for adjusting a window width of the medical image in response to a first operation in a first direction and adjusting a window level of the medical image in response to a second operation in a second direction.
The updating module 83 is configured to update a gray value of each pixel point according to a preset mapping relationship according to the window width, the window level, and the original pixel value of each pixel point in the medical image; and for the edges of the foreground region and the background region in the medical image, the gray value difference between the foreground region and the edges is larger than a preset threshold value by adjusting the window width and the window level, and the gray value difference between the background region and the edges is larger than the preset threshold value.
A rendering module 84 for generating contour information in the multi-layered medical image using a path search algorithm based on the updated medical image.
The segmentation module 85 is configured to perform three-dimensional reconstruction according to the contour information in the multi-layer medical image, so as to obtain a three-dimensional segmentation result of the medical object.
In one embodiment of the present disclosure, the adjustment module 82 is specifically configured to: when the movement operation of the mouse pointer is detected, adjusting the window width of the medical image according to the displacement of the mouse pointer in the horizontal direction; when a movement operation of the mouse pointer is detected, the window level of the medical image is adjusted according to the displacement of the mouse pointer in the vertical direction.
In one embodiment of the present disclosure, the rendering module 84 is specifically configured to: performing gradient transformation based on the updated medical image, generating a gradient image and storing the gradient image into a memory; and in response to a third operation on the displayed medical image, processing the gradient image by adopting a path search algorithm to generate contour information in the medical image.
In one embodiment of the present disclosure, the rendering module 84 is specifically configured to: acquiring a selected starting position in a medical image and a current position of a mouse pointer; the opposite image of the gradient image, the starting position and the current position are used as inputs to the Astar algorithm to draw a path from the starting position to the current position.
In one embodiment of the present disclosure, the rendering module 84 is specifically configured to: responding to clicking operation at the current position, saving the drawn path and taking the clicking position as a new starting position; when the mouse pointer is detected to continue sliding, the opposite image of the gradient image, the new starting position and the current position of the mouse pointer are used as inputs of an Astar algorithm to draw a path from the new starting position to the current position of the mouse pointer.
In one embodiment of the present disclosure, the medical image sequence is an N-layer medical image, and the segmentation module 85 is specifically configured to: for K layers of medical images in N layers of medical images, acquiring contour information in the K layers of medical images, wherein N is larger than K; based on the contour information in the K-layer medical image and the position of the K-layer medical image in the medical image sequence, obtaining the contour information in the N-layer medical image by adopting an interpolation algorithm; and carrying out three-dimensional reconstruction according to the contour information in the N layers of medical images to obtain a three-dimensional segmentation result of the medical object.
In one embodiment of the present disclosure, the display module 81 is specifically configured to: displaying a sagittal medical image in a first region of the display interface, displaying a coronal medical image in a second region of the display interface, and displaying an axial medical image in a third region of the display interface; the display module 81 is further configured to display the three-dimensional segmentation result in a fourth area of the display interface.
The three-dimensional segmentation device based on the medical image provided by the embodiment of the disclosure can execute any three-dimensional segmentation method based on the medical image provided by the embodiment of the disclosure, and has the corresponding functional modules and beneficial effects of the execution method. Details of the embodiments of the apparatus of the present disclosure that are not described in detail may refer to descriptions of any of the embodiments of the method of the present disclosure.
The embodiment of the disclosure also provides an electronic device, which comprises one or more processors and a memory. The processor may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device to perform the desired functions. The memory may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. Volatile memory can include, for example, random Access Memory (RAM) and/or cache memory (cache) and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on a computer readable storage medium and a processor may execute the program instructions to implement the methods of embodiments of the present disclosure above and/or other desired functions. Various contents such as an input signal, a signal component, a noise component, and the like may also be stored in the computer-readable storage medium.
In one example, the electronic device may further include: input devices and output devices, which are interconnected by a bus system and/or other forms of connection mechanisms. In addition, the input device may include, for example, a keyboard, a mouse, and the like. The output device may output various information including the determined distance information, direction information, etc., to the outside. The output means may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc. In addition, the electronic device may include any other suitable components, such as a bus, input/output interface, etc., depending on the particular application.
In addition to the methods and apparatus described above, embodiments of the present disclosure may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform any of the methods provided by the embodiments of the present disclosure.
The computer program product may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform any of the methods provided by the embodiments of the present disclosure.
A computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing is merely a specific embodiment of the disclosure to enable one skilled in the art to understand or practice the disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown and described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A medical image-based three-dimensional segmentation method, comprising:
displaying a sequence of medical images of a medical object, the sequence of medical images comprising a plurality of layers of medical images;
adjusting a window width of the medical image in response to a first operation in a first direction, and adjusting a window level of the medical image in response to a second operation in a second direction;
updating gray values of all pixel points according to a preset mapping relation according to the window width, the window level and the original pixel values of all pixel points in the medical image; wherein, for the edges of a foreground region and a background region in the medical image, the gray value difference between the foreground region and the edge is larger than a preset threshold value by adjusting the window width and the window level, and the gray value difference between the background region and the edge is larger than the preset threshold value;
generating contour information in the multi-layer medical image by adopting a path search algorithm based on the updated medical image;
and carrying out three-dimensional reconstruction according to the contour information in the multi-layer medical image to obtain a three-dimensional segmentation result of the medical object.
2. The method of claim 1, wherein the adjusting the window width of the medical image in response to the first operation in the first direction comprises:
when detecting a movement operation of a mouse pointer, adjusting a window width of the medical image according to the displacement of the mouse pointer in the horizontal direction;
the adjusting the window level of the medical image in response to a second operation in a second direction includes:
when a movement operation of a mouse pointer is detected, a window level of the medical image is adjusted according to a displacement of the mouse pointer in a vertical direction.
3. The method of claim 1, wherein generating profile information in each layer of medical image using a path search algorithm based on the updated medical image comprises:
performing gradient transformation based on the updated medical image, generating a gradient image and storing the gradient image into a memory;
and responding to a third operation on the displayed medical image, and adopting a path search algorithm to process the gradient image so as to generate contour information in the medical image.
4. The method of claim 3, wherein the processing the gradient image with a path search algorithm in response to a third operation on the presented medical image to generate profile information in the medical image comprises:
acquiring a selected starting position and a current position of a mouse pointer in the medical image;
the opposite image of the gradient image, the starting position and the current position are used as inputs of an Astar algorithm to draw a path from the starting position to the current position.
5. The method of claim 4, wherein processing the gradient image with a path search algorithm in response to a third operation on the presented medical image to generate profile information in the medical image comprises:
responding to clicking operation at the current position, saving the drawn path and taking the clicking position as a new starting position;
when the mouse pointer is detected to continue sliding, taking the opposite image of the gradient image, the new starting position and the current position of the mouse pointer as inputs of an Astar algorithm to draw a path from the new starting position to the current position of the mouse pointer.
6. The method of claim 1, wherein the sequence of medical images is an N-layer medical image, the performing three-dimensional reconstruction according to contour information in the multi-layer medical image to obtain a three-dimensional segmentation result of the medical object, comprising:
acquiring contour information in the K-layer medical image for the K-layer medical image in the N-layer medical image, wherein N is larger than K;
based on the contour information in the K-layer medical image and the position of the K-layer medical image in the medical image sequence, obtaining the contour information in the N-layer medical image by adopting an interpolation algorithm;
and carrying out three-dimensional reconstruction according to the contour information in the N layers of medical images to obtain a three-dimensional segmentation result of the medical object.
7. The method of claim 1, wherein the presenting the sequence of medical images of the medical object comprises:
displaying a sagittal medical image in a first region of a display interface, displaying a coronal medical image in a second region of the display interface, and displaying an axial medical image in a third region of the display interface;
after obtaining the three-dimensional segmentation result of the medical object, the method further comprises:
and displaying the three-dimensional segmentation result in a fourth area of the display interface.
8. A medical image-based three-dimensional segmentation apparatus, comprising:
a display module for displaying a sequence of medical images of a medical object, the sequence of medical images comprising a plurality of layers of medical images;
an adjustment module for adjusting a window width of the medical image in response to a first operation in a first direction, and adjusting a window level of the medical image in response to a second operation in a second direction;
the updating module is used for updating the gray value of each pixel point according to the window width, the window level and the original pixel value of each pixel point in the medical image and a preset mapping relation; wherein, for the edges of a foreground region and a background region in the medical image, the gray value difference between the foreground region and the edge is larger than a preset threshold value by adjusting the window width and the window level, and the gray value difference between the background region and the edge is larger than the preset threshold value;
the drawing module is used for generating contour information in the multi-layer medical image by adopting a path search algorithm based on the updated medical image;
and the segmentation module is used for carrying out three-dimensional reconstruction according to the contour information in the multi-layer medical image to obtain a three-dimensional segmentation result of the medical object.
9. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
the processor is configured to read the executable instructions from the memory and execute the instructions to implement the medical image-based three-dimensional segmentation method according to any one of the preceding claims 1-7.
10. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the medical image-based three-dimensional segmentation method according to any one of the preceding claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310659317.5A CN116912282A (en) | 2023-06-05 | 2023-06-05 | Three-dimensional segmentation method, device, equipment and storage medium based on medical image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310659317.5A CN116912282A (en) | 2023-06-05 | 2023-06-05 | Three-dimensional segmentation method, device, equipment and storage medium based on medical image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116912282A true CN116912282A (en) | 2023-10-20 |
Family
ID=88357130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310659317.5A Pending CN116912282A (en) | 2023-06-05 | 2023-06-05 | Three-dimensional segmentation method, device, equipment and storage medium based on medical image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116912282A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1584936A (en) * | 2004-06-07 | 2005-02-23 | 东软飞利浦医疗设备系统有限责任公司 | Three-dimensional dividing method for medical images |
| CN102485179A (en) * | 2010-12-02 | 2012-06-06 | 深圳迈瑞生物医疗电子股份有限公司 | Image window width/window position regulation method, device and medical image equipment |
| CN106709929A (en) * | 2016-12-30 | 2017-05-24 | 上海联影医疗科技有限公司 | Method and device for displaying interesting region of medical image |
| CN107833231A (en) * | 2017-11-22 | 2018-03-23 | 上海联影医疗科技有限公司 | Medical image display method, device and computer-readable storage medium |
| CN107908323A (en) * | 2017-11-10 | 2018-04-13 | 上海联影医疗科技有限公司 | Medical image display method, device and computer-readable storage medium |
| CN108334733A (en) * | 2017-09-01 | 2018-07-27 | 上海联影医疗科技有限公司 | Medical image display method, display system and computer readable storage medium |
| CN108470322A (en) * | 2018-03-09 | 2018-08-31 | 北京小米移动软件有限公司 | Handle the method, apparatus and readable storage medium storing program for executing of facial image |
| CN109509199A (en) * | 2018-10-10 | 2019-03-22 | 华南理工大学 | A kind of medical image Organizational Intelligence dividing method based on three-dimensional reconstruction |
| CN110619672A (en) * | 2019-09-12 | 2019-12-27 | 慧影医疗科技（北京）有限公司 | Figure edge line selecting method, machine readable storage medium and data processing equipment |
| CN114565590A (en) * | 2022-03-03 | 2022-05-31 | 北京安德医智科技有限公司 | Blood vessel data set amplification method and device, electronic device and storage medium |
-
2023
- 2023-06-05 CN CN202310659317.5A patent/CN116912282A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1584936A (en) * | 2004-06-07 | 2005-02-23 | 东软飞利浦医疗设备系统有限责任公司 | Three-dimensional dividing method for medical images |
| CN102485179A (en) * | 2010-12-02 | 2012-06-06 | 深圳迈瑞生物医疗电子股份有限公司 | Image window width/window position regulation method, device and medical image equipment |
| CN106709929A (en) * | 2016-12-30 | 2017-05-24 | 上海联影医疗科技有限公司 | Method and device for displaying interesting region of medical image |
| CN108334733A (en) * | 2017-09-01 | 2018-07-27 | 上海联影医疗科技有限公司 | Medical image display method, display system and computer readable storage medium |
| CN107908323A (en) * | 2017-11-10 | 2018-04-13 | 上海联影医疗科技有限公司 | Medical image display method, device and computer-readable storage medium |
| CN107833231A (en) * | 2017-11-22 | 2018-03-23 | 上海联影医疗科技有限公司 | Medical image display method, device and computer-readable storage medium |
| CN108470322A (en) * | 2018-03-09 | 2018-08-31 | 北京小米移动软件有限公司 | Handle the method, apparatus and readable storage medium storing program for executing of facial image |
| CN109509199A (en) * | 2018-10-10 | 2019-03-22 | 华南理工大学 | A kind of medical image Organizational Intelligence dividing method based on three-dimensional reconstruction |
| CN110619672A (en) * | 2019-09-12 | 2019-12-27 | 慧影医疗科技（北京）有限公司 | Figure edge line selecting method, machine readable storage medium and data processing equipment |
| CN114565590A (en) * | 2022-03-03 | 2022-05-31 | 北京安德医智科技有限公司 | Blood vessel data set amplification method and device, electronic device and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 吕洁 等: "交互式医学图像分割算法", 《计算机仿真》, vol. 27, no. 12, 31 December 2010 (2010-12-31), pages 1 * |
| 陈广新 等: "股骨3D模型构建在股骨头置换手术中的应用研究", 《软件》, no. 12, 15 December 2017 (2017-12-15), pages 83 - 88 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6636678B2 (en) | Learning to annotate objects in images | |
| JP2021530061A (en) | Image processing methods and their devices, electronic devices and computer-readable storage media | |
| RU2540829C2 (en) | Interactive iterative closest point algorithm for organ segmentation | |
| Falcao et al. | A 3D generalization of user-steered live-wire segmentation | |
| CN106663309B (en) | Method and storage medium for user-guided bone segmentation in medical imaging | |
| JP4584575B2 (en) | Image processing method for interacting with 3D surface displayed in 3D image | |
| US8983189B2 (en) | Method and systems for error correction for three-dimensional image segmentation | |
| EP3644277A1 (en) | Image processing system, image processing method, and program | |
| JPH09101970A (en) | Method and device for retrieving image | |
| Tian et al. | Joint temporal context exploitation and active learning for video segmentation | |
| WO2015166871A1 (en) | Method for registering source image with target image | |
| AU2019200269B2 (en) | An interactive user interface and its corresponding engine for improving image completion quality | |
| US9892485B2 (en) | System and method for mesh distance based geometry deformation | |
| CN113168914B (en) | Interactive iterative image annotation | |
| CN113129362B (en) | Method and device for acquiring three-dimensional coordinate data | |
| CN112907750A (en) | Indoor scene layout estimation method and system based on convolutional neural network | |
| CN116912282A (en) | Three-dimensional segmentation method, device, equipment and storage medium based on medical image | |
| CN109308703B (en) | Intelligent contouring of anatomical structures using structured user click-through points | |
| Bornik et al. | Interactive editing of segmented volumetric datasets in a hybrid 2D/3D virtual environment | |
| US20190287225A1 (en) | Patch validity test | |
| Blezek et al. | Center line algorithm for virtual endoscopy based on chamfer distance transform and Dijkstra's single-source shortest-path algorithm | |
| EP4425427A1 (en) | Method for automated processing of volumetric medical images | |
| Khan et al. | A convex selective segmentation model based on a piece-wise constant metric-guided edge detector function | |
| Shen et al. | [Retracted] Application of Three‐Dimensional Image Reconstruction Technology in Neurogenic Intestinal Nursing Tasks | |
| Kundu et al. | Comparative analysis of non-rigid registration techniques for liver surface registration |
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 |