CN115760813A - Screw channel generation method, device, equipment, medium and program product - Google Patents
Screw channel generation method, device, equipment, medium and program product Download PDFInfo
- Publication number
- CN115760813A CN115760813A CN202211487676.9A CN202211487676A CN115760813A CN 115760813 A CN115760813 A CN 115760813A CN 202211487676 A CN202211487676 A CN 202211487676A CN 115760813 A CN115760813 A CN 115760813A
- Authority
- CN
- China
- Prior art keywords
- screw
- screw channel
- candidate
- determining
- channels
- 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
Images
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The application relates to a screw channel generation method, device, equipment, medium and program product. The method comprises the following steps: performing segmentation processing on the target medical image to obtain a three-dimensional image of the interested part; determining a plurality of feasible screw channels meeting safety conditions in the three-dimensional image; for each of the feasible screw channels, determining an optimized screw channel in the vicinity of the location where the feasible screw channel is located; a target screw channel is determined from a plurality of the optimized screw channels. According to the method and the device, the screw channel can be automatically generated, the risk of mistake in manual screw channel selection is avoided, and the accuracy of screw channel selection is improved.
Description
Technical Field
The present application relates to the field of digital analysis technologies, and in particular, to a method, an apparatus, a device, a medium, and a program product for generating a screw channel.
Background
According to statistics, the pelvic fracture accounts for about 1.5% of all fractures, screws are embedded into the pelvis fracture at present, but the physiological structure around the pelvis, particularly at the sacroiliac joint, is complex, and the risk of damaging pelvic organ, blood vessel and nerve exists, so that the selection of screw channels is particularly important.
In the conventional technology, a professional determines a screw channel according to a pelvis structure diagram and experience, but the method is very dependent on the experience of the professional, and the pelvis of each individual has differences in sex, age, race and the like, so that the difficulty in selecting the screw channel is high, and the risk of error of the selected screw channel exists, so that the conventional screw channel selecting method has the problem of low accuracy.
Disclosure of Invention
In view of the above, it is necessary to provide a screw channel generation method, device, apparatus, medium, and program product capable of automatically generating a screw channel and further improving accuracy of selecting the screw channel.
In a first aspect, the present application provides a screw channel generation method. The method comprises the following steps: segmenting a target medical image to obtain a three-dimensional image of a region of interest; determining a plurality of feasible screw channels which accord with safety conditions in the three-dimensional image; for each feasible screw channel, determining an optimized screw channel near the position where the feasible screw channel is located; a target screw channel is determined from the plurality of optimized screw channels.
In one embodiment, the method further comprises: carrying out contour recognition processing on the three-dimensional image to obtain a contour of the interested part; correspondingly, an optimized screw channel is determined near the position where the feasible screw channel is located, comprising: based on the contour of the region of interest, an optimized screw channel is determined near the location where the feasible screw channel is located.
In one embodiment, determining an optimized screw channel based on the contour of the site of interest in the vicinity of where the feasible screw channel is located comprises: determining a plurality of first candidate end points in the vicinity of the first end points of the feasibility screw channels, generating a plurality of first candidate screw channels based on the second end points of the feasibility screw channels and the plurality of first candidate end points; determining a first target candidate screw channel from a feasible screw channel and a plurality of first candidate screw channels based on the outline of the interested part, wherein a first target candidate endpoint corresponding to the first target candidate screw channel may be the first endpoint and may also be the first candidate endpoint; determining a plurality of second candidate end points near the second end points of the feasible screw channels, and generating a plurality of second candidate screw channels based on the first target candidate end points corresponding to the first target candidate screw channels and the second candidate end points; determining a second target candidate screw channel from the first target candidate screw channel and a plurality of second candidate screw channels based on the outline of the interested part, wherein the second target candidate endpoint corresponding to the second target candidate screw channel may be a second endpoint and may also be a second candidate endpoint; and determining an optimized screw channel based on a first target candidate endpoint corresponding to the first target candidate screw channel and a second target candidate endpoint corresponding to the second target candidate screw channel.
In one embodiment, determining a first target candidate screw channel from the feasible screw channel and a plurality of first candidate screw channels based on the contour of the site of interest comprises: determining a plurality of first safety screw channels satisfying a safety condition from the plurality of first candidate screw channels; a first target candidate screw channel is determined from the feasibility screw channel and the plurality of first safety screw channels based on a minimum distance between the centerlines of the feasibility screw channel and each of the first safety screw channels to the contour surface of the site of interest.
In one embodiment, determining a second target candidate screw channel from the first target candidate screw channel and a plurality of second candidate screw channels based on the contour of the region of interest comprises: determining a plurality of second safety screw channels satisfying a safety condition from the plurality of second candidate screw channels; a second target candidate screw channel is determined from the first target candidate screw channel and the plurality of second safety screw channels based on a minimum distance between the centerlines of the first target candidate screw channel and each of the second safety screw channels to the contour plane of the site of interest.
In one embodiment, determining a target screw channel from a plurality of optimized screw channels comprises: a target screw channel is determined from the plurality of optimized screw channels based on a minimum distance between a centerline of each optimized screw channel to the contoured surface of the site of interest.
In one embodiment, determining a plurality of feasible safety-compliant screw channels in a three-dimensional image includes: determining a first screw endpoint region and a second screw endpoint region in the three-dimensional image; generating a plurality of initial screw channels from endpoints in the first screw endpoint region and endpoints in the second screw endpoint region; a plurality of feasible screw channels meeting the safety condition are determined from the initial screw channels.
In one embodiment, the security conditions include: the screw channel is located entirely inside the region of interest.
In a second aspect, the present application further provides a screw channel generating device. The device comprises: the segmentation module is used for carrying out segmentation processing on the target medical image to obtain a three-dimensional image of the interested part; the system comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for determining a plurality of feasible screw channels which accord with safety conditions in a three-dimensional image; a second determination module for determining, for each feasible screw channel, an optimized screw channel in the vicinity of the location of the feasible screw channel; a third determination module to determine a target screw channel from the plurality of optimized screw channels.
In one embodiment, the apparatus further includes a processing module, configured to perform contour recognition processing on the three-dimensional image to obtain a contour of the region of interest; a second determination module for determining an optimized screw channel around where the feasible screw channel is located based on the contour of the region of interest.
In one embodiment, the system includes a second determination module to determine a plurality of first candidate end points near a first end point of the feasibility screw channel, the plurality of first candidate screw channels being generated based on a second end point of the feasibility screw channel and the plurality of first candidate end points; determining a first target candidate screw channel from the feasible screw channel and a plurality of first candidate screw channels based on the contour of the interested part, wherein the first target candidate endpoint may be a first endpoint and may also be a first candidate endpoint; determining a plurality of second candidate end points near the second end points of the feasible screw channels, and generating a plurality of second candidate screw channels based on the first target candidate end points corresponding to the first target candidate screw channels and the second candidate end points; determining a second target candidate screw channel from the first target candidate screw channel and a plurality of second candidate screw channels based on the outline of the interested part, wherein the second target candidate endpoint corresponding to the second target candidate screw channel may be a second endpoint and may also be a second candidate endpoint; and determining an optimized screw channel based on a first target candidate endpoint corresponding to the first target candidate screw channel and a second target candidate endpoint corresponding to the second target candidate screw channel.
In one embodiment, the second determination module is further configured to determine a plurality of first safety screw channels satisfying a safety condition from the plurality of first candidate screw channels; a first target candidate screw channel is determined from the feasibility screw channel and the plurality of first safety screw channels based on a minimum distance between the centerlines of the feasibility screw channel and each of the first safety screw channels to the contour surface of the site of interest.
In one embodiment, the second determining module is further configured to determine a plurality of second safety screw channels satisfying the safety condition from the plurality of second candidate screw channels; a second target candidate screw channel is determined from the first target candidate screw channel and the plurality of second safety screw channels based on a minimum distance between the centerlines of the first target candidate screw channel and each of the second safety screw channels to the contoured surface of the site of interest.
In one embodiment, the third determining module is configured to determine a target screw channel from the plurality of optimized screw channels according to a minimum distance between a centerline of each optimized screw channel and a contour of the region of interest.
In one embodiment, the device comprises a first determining module, a second determining module and a third determining module, wherein the first determining module is used for determining a first screw endpoint region and a second screw endpoint region in a three-dimensional image; generating a plurality of initial screw channels from endpoints in the first screw endpoint region and endpoints in the second screw endpoint region; a plurality of feasible screw channels meeting the safety condition are determined from the initial screw channels.
In one embodiment, the safety conditions include: the screw channel is located entirely inside the region of interest.
In a third aspect, the present application further provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the steps of the method according to any one of the first aspect when executing the computer program.
In a fourth aspect, the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method of any of the first aspects described above.
In a fifth aspect, the present application also provides a computer program product comprising a computer program that, when executed by a processor, performs the steps of the method of any of the first aspects described above.
According to the screw channel generation method, the device, the equipment, the medium and the program product, the three-dimensional image of the interested part is obtained by segmenting the target medical image, then the feasible screw channels meeting the safety condition are determined in the three-dimensional image, the optimized screw channel is determined near the position of the feasible screw channel for each feasible screw channel, and then the target screw channel is determined from the optimized screw channels, so that the automatic generation of the screw channel is realized, the risk of errors caused by manual screw channel selection is avoided, and the accuracy of screw channel selection is further improved.
Drawings
FIG. 1 is a schematic flow chart of a screw channel generation method in one embodiment;
FIG. 2 is a block diagram of one possible screw channel in one embodiment;
FIG. 3 is a block diagram of one embodiment of determining an optimized screw channel;
FIG. 4 is a flow chart illustrating another method for screw channel generation in one embodiment;
FIG. 5 is a screw channel creating device in one embodiment;
FIG. 6 is a diagram of the internal structure of a computer device, in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In an embodiment, as shown in fig. 1, a flow chart of a screw channel generation method is provided, and this embodiment is illustrated by applying the method to a terminal, it is to be understood that the method may also be applied to a server, and may also be applied to a system including a terminal and a server, and implemented by interaction between the terminal and the server, where the terminal may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and the like. The server may be implemented as a stand-alone server or as a server cluster consisting of a plurality of servers. In the embodiment of the application, the method comprises the following steps:
The target medical image is an initial three-dimensional image with a region of interest, the region of interest may be other bone structures such as a pelvis, and the three-dimensional image is a three-dimensional CT (Computed Tomography) image composed of a plurality of points.
Optionally, performing image semantic segmentation on the target medical image by using a semantic segmentation network of a Transformer to obtain a three-dimensional image of the interested part. The target medical image is divided into blocks based on ViT (Vision Transformer), the blocks are mapped into a linear embedded sequence, the linear embedded sequence is encoded by an encoder, the output of the encoder and class embedding is decoded by a Mask Transformer, argmax is applied to each pixel after upsampling, and the final three-dimensional image of the interested part is output.
The screw channel can be represented by the central points of two ends of the cylinder, and the connecting line of two points on the three-dimensional image can represent one screw channel. Safety conditions can be set as desired, as screw channels are required inside the bones of the pelvis. The feasible screw channel is the screw channel meeting the safety condition.
Optionally, as shown in fig. 2, a structural diagram of a feasible screw channel is provided, and a professional marks the entry surface 201 and the exit surface 202 of the screw channel in a three-dimensional image of the pelvis, and then inputs the three-dimensional image marked with the entry surface 201 and the exit surface 202 into a trained training model to obtain a plurality of feasible screw channels meeting safety conditions. The training model is based on Boolean operation, iterative optimization is carried out by using a double-current DFS (Depth First Search) algorithm, whether the screw channel is safe or not is judged according to whether the point set forming the screw channel belongs to a subset of the point set forming the three-dimensional image, and if the point set forming the screw channel is safe, an in point and an out point of the screw channel are output.
In addition, the entry face 201 and the exit face 202 are much larger than the two end points of the screw channel, and therefore the practitioner chooses the exit face and the entry face much simpler than conventional techniques.
For each feasible screw channel, an optimized screw channel is determined in the vicinity of where the feasible screw channel is located, step 103.
Alternatively, as shown in fig. 3, a structural diagram for determining an optimized screw channel is provided, and each feasible screw channel is composed of two endpoints, namely an in-point a and an out-point B. And then in the three-dimensional structure, selecting a plurality of nearest neighbors of the exit point B as candidate exit points B1 according to a first preset value, and selecting a plurality of nearest neighbors of the entry point A as candidate entry points A1 according to a second preset value, wherein the first preset value and the second preset value can be the same or different. And then respectively judging whether the screw channel formed by the exit point A and each candidate exit point B1, the screw channel formed by each candidate entry point A1 and exit point B, and the screw channel formed by each candidate entry point A1 and each candidate exit point B1 meet the safety condition, and if the screw channel which does not meet the safety condition is rejected, at least one screw channel which is left is a safety screw channel. And then calculating the minimum distance between the feasible screw channel and each safety screw channel and the outline of the three-dimensional image, and selecting the screw channel with the maximum minimum distance as an optimized screw channel. In addition, if the entry point and/or the exit point of the optimized screw channel are/is in the bone, the connecting line of the entry point and/or the exit point is extended to intersect with the outline of the three-dimensional image, and the intersection point is the entry point and/or the exit point of the optimized screw channel. Wherein B1' shown in FIG. 3 is the point of intersection of the extended exit point B1 of the optimized screw channel A1-B1 with the contour of the three-dimensional image.
For example, in the three-dimensional structure, 6 candidate input points, A1, A2, A3, A4, A5 and A6, 6 candidate output points, B1, B2, B3, B4, B5 and B6, are arranged near the input point A, 6 candidate output points are arranged near the output point B, the minimum distance between the screw channel formed by the A-B, A-B1, the A-B4, the A6-B, A-B2 and the A3-B5 and the pelvis contour is calculated according to the judgment of safety conditions, the minimum distance between the screw channel formed by the A-B, A-B1, the A-B4, the A6-B, A-B2 and the A3-B5 is obtained, the minimum distance between the A6-B and the pelvis contour is the maximum, therefore, the optimized screw channel is the screw channel formed by the candidate input point A6 and the output point B, wherein the candidate A6 is inside the pelvis contour, the intersection line of the candidate A6 and the output point B is the optimized screw channel, and the output point A6 'is the output point B, and the optimized screw channel is the output point A' is the output point B.
The optimized screw channel is determined near the position of the feasible screw channel, a point inside a bone can be selected as at least one endpoint of the screw channel, the endpoint is prolonged to be intersected with the outline of the three-dimensional image, the intersection point is used as one end of the screw channel, and the position of the intersection point can be between the entry points or the exit points of the two feasible screw channels, so that the screw channel outside the feasible screw channel can be expanded by the method to select the optimized screw channel, the option of selecting the optimized screw channel is increased, and the accuracy of selecting the screw channel is improved.
A target screw channel is determined from the plurality of optimized screw channels, step 104.
Optionally, for each optimized screw channel, a central point of the optimized screw channel is obtained according to an entry point and an exit point of the optimized screw channel, a decision line segment of the optimized screw channel is determined according to the preset length and the central point, and the minimum distance from the decision line segment to the contour of the three-dimensional image is calculated to obtain the minimum distance from the optimized screw channel to the contour of the three-dimensional image. And then comparing the minimum distance between each optimized screw channel and the outline of the three-dimensional image, wherein the optimized screw channel corresponding to the maximum minimum distance is the target screw channel. Wherein, the decision line segment for determining and optimizing the screw channel according to the preset length and the central point comprises: and intercepting preset lengths from the central point of the optimized screw channel to two ends along the direction of the optimized screw channel to obtain a decision line segment of the optimized screw channel. In addition, a connecting line of an in point and an out point of the target screw channel is used as a central line, and the target screw channel in the shape of a cylinder is obtained based on a preset radius.
Because the optimized screw channel is intersected with the outline of the three-dimensional image, the minimum distance from the optimized screw channel to the outline of the three-dimensional image is directly calculated, and the obtained results are all 0, so that the minimum distance from the calculated optimized screw channel to the outline of the three-dimensional image is not all 0 by determining a decision line segment of the optimized screw channel according to the preset length and a central point and then calculating the minimum distance from the decision line segment to the outline of the three-dimensional image, and the method has strong performability.
In summary, a three-dimensional image of a part of interest is obtained by segmenting a target medical image, then a plurality of feasible screw channels meeting safety conditions are determined in the three-dimensional image, for each feasible screw channel, an optimized screw channel is determined near the position where the feasible screw channel is located, and then a target screw channel is determined from the plurality of optimized screw channels, so that automatic generation of the screw channel is realized, the risk of errors in manual screw channel selection is avoided, and the accuracy of screw channel selection is improved.
In one embodiment, the method further comprises: carrying out contour recognition processing on the three-dimensional image to obtain a contour of the interested part; correspondingly, an optimized screw channel is determined near the position where the feasible screw channel is located, comprising: based on the contour of the region of interest, an optimized screw channel is determined near the location where the feasible screw channel is located.
Optionally, the three-dimensional image is subjected to contour extraction by any one of a raster scanning method, a region growing method and a region splitting and merging method to obtain the contour of the interested part. The method can also be used for extracting the contour of the three-dimensional image by adopting a contour extraction method, and comprises the following specific processes: inputting a three-dimensional image into a contour extraction model, wherein the contour extraction model divides the three-dimensional image into a plurality of two-dimensional images, then identifying Boolean values of a plurality of adjacent points corresponding to each two-dimensional image, and if the Boolean values of the plurality of adjacent points corresponding to the points are consistent, namely all the Boolean values are 0 or all the Boolean values are 1, judging that the points are not contour points; if the boolean values of a plurality of neighboring points corresponding to the point do not match, i.e., both 0 and 1, the point is determined to be a contour point.
It should be noted that after the semantic segmentation network of the Transformer performs image semantic segmentation on the target medical image, the boolean value of the background is 0, the boolean value of the three-dimensional image of the interested region is 1, and in addition, the selection of the neighboring points may be performed according to a preset threshold.
In one embodiment, as shown in fig. 4, another method for generating a screw channel is provided, which determines an optimized screw channel near a position where a feasible screw channel is located based on a contour of a region of interest, including:
a plurality of first candidate end points are determined near the first end points of the feasibility screw channels, and a plurality of first candidate screw channels are generated based on the second end points of the feasibility screw channels and the plurality of first candidate end points, step 401.
A first target candidate screw channel is determined from the feasible screw channel and a plurality of first candidate screw channels based on the contour of the region of interest, wherein the first target candidate endpoint may be a first endpoint or a first candidate endpoint, step 402.
Wherein determining a plurality of first candidate end points near a first end point of the feasibility screw channel and determining a plurality of second candidate end points near a second end point of the feasibility screw channel comprises: a plurality of first candidate end points are determined near a first end point of the feasibility screw channel and a plurality of second candidate end points are determined near a second end point of the feasibility screw channel according to a preset range. In the three-dimensional structure, according to the preset range, the nearest neighbors of the first endpoint and the second endpoint of the feasible screw channel are 6 points, the 6 points of the nearest neighbors of the first endpoint are first candidate endpoints, and the 6 points of the nearest neighbors of the second endpoint are second candidate endpoints. Determining a first target candidate screw channel from the first plurality of candidate screw channels and a second target candidate screw channel from the second plurality of candidate screw channels based on the contour of the site of interest comprises: and determining a first target candidate screw channel from the plurality of first candidate screw channels and a second target candidate screw channel from the plurality of second candidate screw channels according to the safety degree, wherein the safety degree refers to the minimum distance between the screw channel and the outline of the interested part, and the greater the minimum distance is, the higher the safety of the screw channel is.
Optionally, the second end point of the feasible screw channel is first fixed, 6 first candidate end points are determined near the first end point according to a preset range, then each first candidate end point is connected with the second end point to obtain 6 first candidate screw channels, and a first target candidate screw channel is determined from the multiple first candidate screw channels and the feasible screw channel according to the safety degree, at this time, two end points of the first target candidate screw channel are the first target candidate end point and the second end point respectively, and the first target candidate end point may be the first end point or the first candidate end point. And then fixing a first target candidate endpoint of the first target candidate screw channel, determining 6 second candidate endpoints near the second endpoint according to a preset range, connecting each second candidate endpoint with the first target candidate endpoint to obtain 6 second candidate screw channels, and determining a second target candidate screw channel from the plurality of second candidate screw channels and the first target candidate screw channel according to the safety degree, wherein the two endpoints of the second target candidate screw channel are the first target candidate endpoint and the second target candidate endpoint respectively, and the second target candidate endpoint may be the second endpoint or the second candidate endpoint. Finally, the determined second target candidate screw channel is the optimized screw channel. In addition, when the first target candidate endpoint and/or the second target candidate endpoint is/are located inside the bone of the interested part, the first target candidate endpoint and/or the second target candidate endpoint is/are extended to intersect with the outline of the interested part along the second target candidate screw channel, so as to obtain a first target intersection point and/or a second target intersection point, and the screw channel formed by the first target intersection point or the first target candidate endpoint and the second target intersection point or the second target candidate endpoint is an optimized screw channel.
The method comprises the steps of determining a first candidate endpoint near a first endpoint of a feasible screw channel, obtaining a first target candidate screw channel based on the outline of a part of interest, determining a second candidate endpoint near a second endpoint of the feasible screw channel, obtaining a second target candidate screw channel based on the outline of the part of interest, and obtaining an optimized screw channel, wherein a point inside a bone can be selected as at least one endpoint of the screw channel, and an intersection point of the endpoint and the outline of the part of interest along the direction of the screw channel is used as one endpoint of the screw channel, and the intersection point can be between the first endpoints or the second endpoints of the two feasible screw channels.
In one embodiment, the safety conditions include: the screw channel is located entirely inside the region of interest.
In one embodiment, determining a first target candidate screw channel from the feasible screw channel and a plurality of first candidate screw channels based on the contour of the site of interest comprises: determining a plurality of first safety screw channels satisfying a safety condition from the plurality of first candidate screw channels; a first target candidate screw channel is determined from the feasibility screw channel and the plurality of first safety screw channels based on a minimum distance between the centerlines of the feasibility screw channel and each of the first safety screw channels to the contour surface of the site of interest.
In one embodiment, determining a second target candidate screw channel from the first target candidate screw channel and a plurality of second candidate screw channels based on the contour of the region of interest comprises: determining a plurality of second safety screw channels satisfying a safety condition from the plurality of second candidate screw channels; a second target candidate screw channel is determined from the first target candidate screw channel and the plurality of second safety screw channels based on a minimum distance between the centerlines of the first target candidate screw channel and each of the second safety screw channels to the contour plane of the site of interest.
Wherein the screw channel is located entirely within the site of interest means that all points constituting the screw channel belong to a subset of the set of points constituting the site of interest, and the screw channel needs to satisfy a safety condition in order to ensure that the screw channel does not penetrate the cortex. Determining a plurality of first safety screw channels from the plurality of first candidate screw channels that satisfy a safety condition includes: and for each first candidate screw channel, judging whether the point set forming the first candidate screw channel belongs to the subset of the point set forming the interested part, and eliminating the first candidate screw channels of the non-subset, wherein the rest first candidate screw channels are first safety screw channels. Determining a plurality of second safety screw channels from the plurality of second candidate screw channels that satisfy a safety condition includes: and for each second candidate screw channel, judging whether the point set forming the second candidate screw channel belongs to the subset of the point set forming the interested part, and rejecting the second candidate screw channels of the non-subset, wherein the rest second candidate screw channels are second safety screw channels.
Optionally, for each first safety screw channel, a central point of the first safety screw channel is obtained according to a first candidate end point and a second end point of the first safety screw channel, then a preset length is cut from the central point of the first safety screw channel to the two ends along the direction of the first safety screw channel to obtain a decision line segment of the first safety screw channel, then a central point of the feasible screw channel is obtained according to the first end point and the second end point of the feasible screw channel, then a preset length is cut from the central point of the feasible screw channel to the two ends along the direction of the feasible screw channel to obtain a decision line segment of the feasible screw channel, then the minimum distance between the decision line segment of the feasible screw channel and the profile surface of the interested part of each first safety screw channel is compared, and the screw channel corresponding to the maximum minimum distance is the first target candidate screw channel.
Optionally, for each second safety screw channel, according to the first candidate endpoint and the second candidate endpoint of the second safety screw channel, the central point of the second safety screw channel is obtained, then, along the direction of the second safety screw channel, the preset length is cut from the central point to the two ends of the second safety screw channel to obtain the decision line segment of the second safety screw channel, then, the minimum distance between the decision line segment of each second safety screw channel of the decision line segment of the first target candidate screw channel and the contour surface of the interested part is compared, and the screw channel corresponding to the maximum minimum distance is the second target candidate screw channel.
In addition, the calculation formula of the minimum distance d between the decision line segment and the contour surface of the interested part is as follows:
where A, B denotes both end points of the screw channel, O denotes a vector constituted by points on the contour plane constituting the region of interest, and S is an Element Spacing (Element Spacing) denotes a dot Spacing constituting the region of interest.
In one embodiment, determining a target screw channel from a plurality of optimized screw channels comprises: and determining a target screw channel from the plurality of optimized screw channels according to the minimum distance between the central line of each optimized screw channel and the profile surface of the interested part.
Optionally, for each optimized screw channel, a central point of the optimized screw channel is obtained according to a first candidate end point and a second candidate end point of the optimized screw channel, a preset length is cut from the central point to two ends of the optimized screw channel along the direction of the optimized screw channel to obtain a decision line segment of the optimized screw channel, then the minimum distance between the decision line segment of each optimized screw channel and the contour surface of the interested part is compared, and the optimized screw channel corresponding to the maximum minimum distance is the target screw channel.
In one embodiment, determining a plurality of feasible safety-compliant screw channels in a three-dimensional image includes: determining a first screw endpoint region and a second screw endpoint region in the three-dimensional image; generating a plurality of initial screw channels from endpoints in the first screw endpoint region and endpoints in the second screw endpoint region; a plurality of feasible screw channels meeting the safety condition are determined from the initial screw channels.
Optionally, the first screw endpoint region and the second screw endpoint region may be two regions calibrated in a three-dimensional image by a professional, and the three-dimensional image calibrated with the first screw endpoint region and the second screw endpoint region is input into a trained training model, the training model takes a point in the first screw endpoint region as a first initial endpoint, takes a point in the second screw endpoint region as a second initial endpoint, connects the first initial endpoint and the second initial endpoint to form an initial screw channel, and determines whether a point set forming the initial screw channel belongs to a subset of a point set forming the three-dimensional image, and outputs the initial screw channel belonging to the subset of the point set forming the three-dimensional image, where the initial screw channel is a feasible screw channel.
In conclusion, the target medical image is segmented to obtain a three-dimensional image of the interested part. Determining a first screw endpoint region and a second screw endpoint region in the three-dimensional image, generating a plurality of initial screw channels according to the endpoints in the first screw endpoint region and the endpoints in the second screw endpoint region, and determining a plurality of feasible screw channels meeting safety conditions from the initial screw channels, wherein the safety conditions comprise that the screw channels are all positioned in the interior of the interested part. And carrying out contour recognition processing on the three-dimensional image to obtain the contour of the interested part. Determining a plurality of first candidate end points in the vicinity of the first end points of the feasibility screw channels, generating a plurality of first candidate screw channels based on the second end points of the feasibility screw channels and the plurality of first candidate end points; determining a plurality of first safety screw channels satisfying a safety condition from the plurality of first candidate screw channels; a first target candidate screw channel is determined from the feasibility screw channel and the plurality of first safety screw channels based on a minimum distance between the centerlines of the feasibility screw channel and each first safety screw channel to the contour plane of the site of interest, wherein the first target candidate endpoint may be either a first endpoint or a first candidate endpoint. Determining a plurality of second candidate end points near the second end points of the feasible screw channels, and generating a plurality of second candidate screw channels based on the first target candidate end points corresponding to the first target candidate screw channels and the second candidate end points; determining a plurality of second safety screw channels satisfying a safety condition from the plurality of second candidate screw channels; and determining a second target candidate screw channel from the first target candidate screw channel and the plurality of second safety screw channels according to the minimum distance between the central line of the first target candidate screw channel and the central line of each second safety screw channel to the profile surface of the interested part, wherein the second target candidate end point corresponding to the second target candidate screw channel may be a second end point and may also be a second candidate end point. And determining an optimized screw channel based on a first target candidate endpoint corresponding to the first target candidate screw channel and a second target candidate endpoint corresponding to the second target candidate screw channel. According to the minimum distance between the central line of each optimized screw channel and the profile surface of the interested part, the target screw channel is determined from the optimized screw channels, so that the screw channel can be automatically generated, the risk of errors in manual screw channel selection is avoided, and the accuracy of screw channel selection is improved.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides a screw channel generation device for implementing the above-mentioned screw channel generation method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so specific limitations in one or more embodiments of the screw channel generation device provided below can be referred to the limitations on the screw channel generation method in the above, and details are not described herein again.
In one embodiment, as shown in fig. 5, there is provided a screw channel generating device, the screw channel generating 500 comprising: a segmentation module 501, a first determination module 502, a second determination module 503, and a third determination module 504, wherein:
the segmentation module 501 is configured to perform segmentation processing on the target medical image to obtain a three-dimensional image of the region of interest.
A first determination module 502 is configured to determine a plurality of feasible screw channels in a three-dimensional image that meet a safety condition.
A second determination module 503 for determining, for each feasible screw channel, an optimized screw channel in the vicinity of where the feasible screw channel is located.
A third determining module 504 for determining a target screw channel from the plurality of optimized screw channels.
In one embodiment, the apparatus further comprises a processing module, configured to perform contour recognition processing on the three-dimensional image to obtain a contour of the region of interest; a second determination module 503 for determining an optimized screw channel around where the feasible screw channel is located, based on the contour of the region of interest.
In one embodiment, the second determining module 503 is configured to determine a plurality of first candidate end points near the first end point of the feasible screw channel, and generate a plurality of first candidate screw channels based on the second end point of the feasible screw channel and the plurality of first candidate end points; determining a first target candidate screw channel from the feasible screw channel and a plurality of first candidate screw channels based on the contour of the interested part, wherein the first target candidate endpoint may be a first endpoint and may also be a first candidate endpoint; determining a plurality of second candidate end points near the second end points of the feasible screw channels, and generating a plurality of second candidate screw channels based on the first target candidate end points corresponding to the first target candidate screw channels and the second candidate end points; determining a second target candidate screw channel from the first target candidate screw channel and a plurality of second candidate screw channels based on the outline of the interested part, wherein the second target candidate endpoint corresponding to the second target candidate screw channel may be a second endpoint and may also be a second candidate endpoint; and determining an optimized screw channel based on a first target candidate endpoint corresponding to the first target candidate screw channel and a second target candidate endpoint corresponding to the second target candidate screw channel.
In one embodiment, the second determining module 503 is further configured to determine a plurality of first safety screw channels satisfying a safety condition from the plurality of first candidate screw channels; a first target candidate screw channel is determined from the feasibility screw channel and the plurality of first safety screw channels based on a minimum distance between the centerlines of the feasibility screw channel and each of the first safety screw channels to the contour surface of the site of interest.
In one embodiment, the second determining module 503 is further configured to determine a plurality of second safety screw channels satisfying the safety condition from the plurality of second candidate screw channels; a second target candidate screw channel is determined from the first target candidate screw channel and the plurality of second safety screw channels based on a minimum distance between the centerlines of the first target candidate screw channel and each of the second safety screw channels to the contour plane of the site of interest.
In one embodiment, the third determining module 504 is configured to determine a target screw channel from the plurality of optimized screw channels according to a minimum distance between a centerline of each optimized screw channel and a contour of the region of interest.
In one embodiment, the first determining module 502 is configured to determine a first screw endpoint region and a second screw endpoint region in the three-dimensional image; generating a plurality of initial screw channels from endpoints in the first screw endpoint region and endpoints in the second screw endpoint region; a plurality of feasible screw channels meeting the safety condition are determined from the initial screw channels.
In one embodiment, the safety conditions include: the screw channel is located entirely inside the region of interest.
The various modules in the screw channel generating device described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 6. The computer apparatus includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input device. The processor, the memory and the input/output interface are connected by a system bus, and the communication interface, the display unit and the input device are connected by the input/output interface to the system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The input/output interface of the computer device is used for exchanging information between the processor and an external device. The communication interface of the computer device is used for communicating with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a screw channel generation method. The display unit of the computer device is used for forming a visual picture and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, carries out the steps in the method embodiments described above.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), magnetic Random Access Memory (MRAM), ferroelectric Random Access Memory (FRAM), phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (12)
1. A screw channel generation method, the method comprising:
performing segmentation processing on the target medical image to obtain a three-dimensional image of the interested part;
determining a plurality of feasible screw channels meeting safety conditions in the three-dimensional image;
for each of the feasible screw channels, determining an optimized screw channel in the vicinity of the location where the feasible screw channel is located;
a target screw channel is determined from a plurality of the optimized screw channels.
2. The method of claim 1, further comprising:
carrying out contour recognition processing on the three-dimensional image to obtain a contour of the interested part;
correspondingly, the determining an optimized screw channel near the position where the feasible screw channel is located includes:
determining the optimized screw channel in the vicinity of the location where the feasible screw channel is located, based on the contour of the site of interest.
3. The method of claim 2, wherein said determining the optimized screw channel around where the feasible screw channel is located based on the contour of the region of interest comprises:
determining a plurality of first candidate end points in the vicinity of the first end point of the feasibility screw channel, generating a plurality of first candidate screw channels based on the second end point of the feasibility screw channel and the plurality of first candidate end points;
determining a first target candidate screw channel from the feasible screw channel and the plurality of first candidate screw channels based on the contour of the region of interest, wherein a first target candidate endpoint corresponding to the first target candidate screw channel may be the first endpoint and may also be the first candidate endpoint;
determining a plurality of second candidate end points near the second end points of the feasible screw channels, and generating a plurality of second candidate screw channels based on the first target candidate end points corresponding to the first target candidate screw channels and the second candidate end points;
determining a second target candidate screw channel from the first target candidate screw channel and the plurality of second candidate screw channels based on the contour of the region of interest, wherein a second target candidate endpoint corresponding to the second target candidate screw channel may be the second endpoint and may also be the second candidate endpoint;
determining the optimized screw channel based on a first target candidate endpoint corresponding to the first target candidate screw channel and a second target candidate endpoint corresponding to the second target candidate screw channel.
4. The method of claim 3, wherein determining a first target candidate screw channel from the feasible screw channel and the plurality of first candidate screw channels based on the contour of the site of interest comprises:
determining a plurality of first safety screw channels satisfying the safety condition from the plurality of first candidate screw channels;
determining the first target candidate screw channel from the feasibility screw channel and the plurality of first safety screw channels according to a minimum distance between a centerline of the feasibility screw channel and each of the first safety screw channels to a contour surface of the region of interest.
5. The method of claim 3, wherein determining a second target candidate screw channel from the first target candidate screw channel and the plurality of second candidate screw channels based on the contour of the site of interest comprises:
determining a plurality of second safety screw channels satisfying the safety condition from the plurality of second candidate screw channels;
determining the second target candidate screw channel from the first target candidate screw channel and the plurality of second safety screw channels according to a minimum distance between the center line of the first target candidate screw channel and each of the second safety screw channels to the contour surface of the region of interest.
6. The method of any of claims 2 to 5, wherein said determining a target screw channel from a plurality of said optimized screw channels comprises:
and determining the target screw channel from the plurality of optimized screw channels according to the minimum distance between the central line of each optimized screw channel and the profile surface of the interested part.
7. The method of claim 1, wherein said determining a plurality of feasible safety-compliant screw channels in said three-dimensional image comprises:
determining a first screw endpoint region and a second screw endpoint region in the three-dimensional image;
generating a plurality of initial screw channels from endpoints in the first screw endpoint region and endpoints in the second screw endpoint region;
and determining a plurality of feasible screw channels meeting the safety condition from the initial screw channels.
8. The method of claim 1, 4, 5 or 7, wherein the safety condition comprises: the screw channel is located entirely inside the region of interest.
9. A screw channel generating device, the device comprising:
the segmentation module is used for carrying out segmentation processing on the target medical image to obtain a three-dimensional image of the interested part;
the first determination module is used for determining a plurality of feasible screw channels meeting the safety condition in the three-dimensional image;
a second determination module for determining, for each of the feasible screw channels, an optimized screw channel in the vicinity of where the feasible screw channel is located;
a third determination module for determining a target screw channel from the plurality of optimized screw channels.
10. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 8.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 8.
12. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 8 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211487676.9A CN115760813A (en) | 2022-11-25 | 2022-11-25 | Screw channel generation method, device, equipment, medium and program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211487676.9A CN115760813A (en) | 2022-11-25 | 2022-11-25 | Screw channel generation method, device, equipment, medium and program product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115760813A true CN115760813A (en) | 2023-03-07 |
Family
ID=85337694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211487676.9A Pending CN115760813A (en) | 2022-11-25 | 2022-11-25 | Screw channel generation method, device, equipment, medium and program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115760813A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116650112A (en) * | 2023-07-24 | 2023-08-29 | 杭州键嘉医疗科技股份有限公司 | Automatic planning method, device, equipment and storage medium for pedicle screw path |
-
2022
- 2022-11-25 CN CN202211487676.9A patent/CN115760813A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116650112A (en) * | 2023-07-24 | 2023-08-29 | 杭州键嘉医疗科技股份有限公司 | Automatic planning method, device, equipment and storage medium for pedicle screw path |
| CN116650112B (en) * | 2023-07-24 | 2023-11-14 | 杭州键嘉医疗科技股份有限公司 | Automatic planning method, device, equipment and storage medium for pedicle screw path |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11657509B2 (en) | Method for precisely and automatically positioning reference line for integrated images | |
| US11100647B2 (en) | 3-D convolutional neural networks for organ segmentation in medical images for radiotherapy planning | |
| CN110321920A (en) | Image classification method, device, computer readable storage medium and computer equipment | |
| WO2022001623A1 (en) | Image processing method and apparatus based on artificial intelligence, and device and storage medium | |
| CN109934812A (en) | Image processing method, device, server and storage medium | |
| CN110276408B (en) | 3D image classification method, device, equipment and storage medium | |
| CN109903269B (en) | Method and computing device for determining abnormal type of spine cross-sectional image | |
| CN110751187B (en) | Training method of abnormal area image generation network and related product | |
| CN112465819A (en) | Image abnormal area detection method and device, electronic equipment and storage medium | |
| CN116228787A (en) | Image sketching method, device, computer equipment and storage medium | |
| CN114998247A (en) | Abnormality prediction method, abnormality prediction device, computer apparatus, and storage medium | |
| CN114341872A (en) | Facilitating interpretability of classification models | |
| CN114998374A (en) | Image segmentation method, device and equipment based on position prior and storage medium | |
| CN115760813A (en) | Screw channel generation method, device, equipment, medium and program product | |
| CN114332132A (en) | Image segmentation method and device and computer equipment | |
| CN110533120B (en) | Image classification method, device, terminal and storage medium for organ nodule | |
| CN110992310A (en) | Method and device for determining partition where mediastinal lymph node is located | |
| Dou et al. | Tooth instance segmentation based on capturing dependencies and receptive field adjustment in cone beam computed tomography | |
| CN115546011A (en) | Image processing method, image processing device, computer equipment and storage medium | |
| Penarrubia et al. | Improving motion‐mask segmentation in thoracic CT with multiplanar U‐nets | |
| CN115115772A (en) | Key structure reconstruction method and device based on three-dimensional image and computer equipment | |
| CN114494144A (en) | Image segmentation method and device, computer equipment and storage medium | |
| CN115731240A (en) | Segmentation method, segmentation device, electronic equipment and storage medium | |
| WO2020137092A1 (en) | Region identification device, method, and program | |
| CN112785562A (en) | System for evaluating based on neural network model and related products |
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 |