CN-121998975-A - Evaluation method, device, equipment, medium and product based on prostate image

CN121998975ACN 121998975 ACN121998975 ACN 121998975ACN-121998975-A

Abstract

The invention relates to an evaluation method, device, equipment, medium and product based on a prostate image, wherein the method comprises the steps of obtaining first image data of a prostate target area matched with a structural evaluation model, wherein the structural evaluation model comprises a structural morphological network and a structural evaluation network, extracting features of the first image data through the structural morphological network to obtain morphological feature data, wherein the morphological feature data represent quantitative information of structural morphology of the prostate target area, and carrying out structural evaluation through the structural evaluation network according to the morphological feature data to determine the structural evaluation data of the prostate target area.

Inventors

LIU MING
HOU RONGRONG
WANG JINFU
CHEN WENBO
ZHAO JING
CHEN YONGMING
HOU HUIMIN
ZHANG GUANSHU

Assignees

北京智愈医疗科技有限公司
北京医院

Dates

Publication Date: 20260508
Application Date: 20260408

Claims (18)

1. A prostate image-based assessment method, comprising: Acquiring first image data of a target region of a prostate matched with a structural assessment model, the structural assessment model comprising a structural morphology network and a structural assessment network; feature extraction is carried out on the first image data through the structural morphology network, so as to obtain morphology feature data, wherein the morphology feature data represents quantization information of structural morphology of the prostate target area; And carrying out structural evaluation according to the morphological feature data through the structural evaluation network, and determining structural evaluation data of the prostate target area.
2. The method according to claim 1, wherein the structural assessment model comprises a first assessment model for assessing structural properties of the target region of the prostate in a two-dimensional imaging mode and/or a three-dimensional imaging mode and/or a second assessment model for assessing structural properties of the prostatic urethra in one or more patency characteristic dimensions within the target region of the prostate.
3. The method of claim 2, wherein the second evaluation model comprises at least one of a first patency model, a second patency model, and a third patency model; when the structural assessment model comprises a first unobstructed model, the structural morphology network comprises a geometric feature layer corresponding to a first anatomical region, when the structural assessment model comprises a second unobstructed model, the structural morphology network comprises a symmetric feature layer and/or a coherent feature layer, and when the structural assessment model comprises a third unobstructed model, the structural morphology network comprises an elimination feature layer; When the structural assessment model comprises a first assessment model, the structural morphology network comprises symmetrical feature layers and/or geometric feature layers corresponding to a first anatomical region, and when the first assessment model comprises a three-dimensional assessment model, the structural morphology network further comprises coherent feature layers and/or elimination feature layers; Wherein the first anatomical region comprises bladder neck and/or prostate tip in the prostate target region, and the geometric features of the urethra output by the geometric feature layer characterize quantitative information of the opening morphology of the prostatic urethra at the first anatomical region.
4. The method of claim 1, wherein the determining structural assessment data of the target prostate region from the structural assessment by the structural assessment network based on the morphological feature data comprises: acquiring a reliable evaluation model and evaluation object data matched with the structure evaluation model, wherein the reliable evaluation model comprises a reliable feature network and a reliable evaluation network; Performing feature extraction on the evaluation object data through the reliable feature network to obtain reliable feature data corresponding to the morphological feature data, and screening the morphological feature data according to the reliable evaluation network and the reliable feature data to obtain an invalid feature set; Updating network parameters of the structure evaluation network according to the invalid feature set under the condition that the invalid feature set is a non-empty set; And carrying out structural evaluation according to the morphological characteristic data through the updated structural evaluation network, and determining structural evaluation data of the prostate target area.
5. The method of claim 4, wherein the evaluation object data comprises first image data, the reliable feature network comprises a first feature layer comprising an image matching module and a feature extraction module; the step of extracting the characteristics of the evaluation object data through the reliable characteristic network to obtain the reliable characteristic data corresponding to the morphological characteristic data, includes: Acquiring at least one second anatomical region corresponding to the structural morphology network through the image matching module, and acquiring second image data matched with each second anatomical region from the first image data; respectively carrying out feature extraction on each second image data through the feature extraction module to obtain a first feature sequence corresponding to the second image data one by one; according to each first characteristic sequence, determining reliable characteristic data corresponding to the morphological characteristic data; wherein the second anatomical region is a bladder neck, a middle portion of a prostate, a tip portion of a prostate, or an entire target region of a prostate in the target region of a prostate.
6. The method of claim 3, wherein the structural morphology network further comprises an image input layer, the feature extracting the first image data by the structural morphology network to obtain morphology feature data, comprising: determining third image data corresponding to each morphological feature layer according to the first image data through the image input layer; carrying out feature extraction according to the input third image data through each morphological feature layer to obtain the structural morphological features of the prostatic urethra; determining morphological feature data according to the morphological features of each structure; Wherein the morphological feature layer is the geometric feature layer, the symmetric feature layer, the coherent feature layer, or the elimination feature layer.
7. The method according to claim 6, wherein the morphological feature layer is a geometrical feature layer, the geometrical feature layer comprises an angle extraction module and/or an area extraction module, and the third image data is image data corresponding to a bladder neck or a prostate tip; The feature extraction is performed by each morphological feature layer according to the input third image data to obtain the structural morphological feature of the prostatic urethra, which comprises the following steps: determining at least one first urethral profile pair corresponding to the prostatic urethra according to the third image data by the angle extraction module, determining an opening angle corresponding to the first anatomical region according to each first urethral profile pair, wherein two first urethral profiles in the first urethral profile pair are distributed along opposite sides of the urethral axis, and/or, And determining at least one urethral occlusive profile corresponding to the prostatic urethra according to the third image data by the area extraction module, and determining the opening area corresponding to the first anatomical region according to each urethral occlusive profile.
8. The method of claim 6, wherein the morphological feature layer is a symmetrical feature layer and the third image data includes image data corresponding to at least one second anatomical region, respectively, of bladder neck, middle of prostate, tip of prostate, or whole target prostate region of the target prostate region; The feature extraction is performed by each morphological feature layer according to the input third image data to obtain the structural morphological feature of the prostatic urethra, which comprises the following steps: acquiring second image data matched with the second anatomical region in the third image data according to each second anatomical region through the symmetrical characteristic layer; Determining a longitudinal central axis of the prostatic urethra in the second anatomical region from the second image data; And executing mirror image comparison operation according to the longitudinal central axis and the second image data to obtain urethra symmetrical characteristics corresponding to the second anatomical region.
9. The method according to claim 6, wherein the morphological feature layer is a coherent feature layer, the third image data is a three-dimensional reconstruction model of the target region of the prostate, and the feature extraction is performed by each morphological feature layer according to the input third image data to obtain structural morphological features of the prostatic urethra, including: determining a continuous transverse image sequence according to the third image data through the continuous feature layer, and determining axial offset data according to every two adjacent transverse images in the transverse image sequence; and determining the urethra coherence characteristics corresponding to the prostate target region according to the axial offset data.
10. The method according to claim 6, wherein the morphological feature layer is an elimination feature layer, the third image data is a three-dimensional reconstruction model of the target region of the prostate, and the feature extraction is performed by each morphological feature layer according to the input third image data to obtain structural morphological features of the prostatic urethra, including: Acquiring a first intracavity volume of a prostatic urethra in the target region of the prostate through the elimination feature layer, determining a second intracavity volume according to the third image data, and determining tissue elimination features corresponding to the target region of the prostate according to the first intracavity volume and the second intracavity volume; wherein the first intra-luminal volume is determined from historical image data of the target region of the prostate, the historical image data being acquired prior to performing an interventional procedure on the target region of the prostate.
11. The method of claim 4, wherein a structural spatial feature in the morphological feature data represents actual measurement information in a physical environment, the structural spatial feature being determined by the structural morphological network according to a first scale factor corresponding to the structural spatial feature, the structural spatial feature being a structural morphological feature having a spatial feature attribute.
12. The method of claim 11, wherein the method further comprises: Determining environmental parameter data according to a second anatomical region corresponding to the structural spatial feature, wherein the environmental parameter data comprises perfusion pressure data, pump flow data and spatial distance data; Determining a first scale factor corresponding to the structural space feature according to the environmental parameter data; Wherein the spatial distance data characterizes minimum distance information of the cystoscope and the urethral cavity wall in a transverse plane.
13. The method according to claim 12, wherein the method further comprises: In a cystoscope imaging scene, before image acquisition is started, adjusting the pump flow of a pumping system according to a preset pressure range until the real-time perfusion pressure meets the preset pressure range, and closing the pumping system; In the image acquisition process, acquiring an environment parameter sequence in real time according to a parameter acquisition frequency by a parameter sensor, and storing an original image frame acquired by a cystoscope in a correlated manner with the environment parameter sequence, wherein the parameter acquisition frequency is the same as the imaging frame rate of the cystoscope; In response to detecting the image blur caused by the interfering medium, the pumping system is started to synchronously perform a perfusion operation and a suction operation with the same flow rate.
14. The method according to claim 12, wherein the evaluation object data includes environmental parameter data corresponding to each structural spatial feature, the reliable feature network includes a second feature layer, and the performing feature extraction on the evaluation object data through the reliable feature network to obtain reliable feature data corresponding to the morphological feature data includes: Respectively determining a second feature sequence according to each environmental parameter data through the second feature layer, and determining reliable feature data of the morphological feature data according to each second feature sequence; Wherein the second feature sequence comprises scale fluctuation features and/or scale offset features.
15. An evaluation device based on a prostate image, comprising: A first image data acquisition module for acquiring first image data of a target region of a prostate that is matched with a structural assessment model, the structural assessment model comprising a structural morphology network and a structural assessment network; the morphological feature data determining module is used for carrying out feature extraction on the first image data through the structural morphological network to obtain morphological feature data, and the morphological feature data represent quantitative information of the structural morphology of the prostate target area; And the structure evaluation data determining module is used for performing structure evaluation according to the morphological characteristic data through the structure evaluation network and determining the structure evaluation data of the prostate target area.
16. An electronic device, the electronic device comprising: At least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the prostate image-based assessment method of any one of claims 1-14.
17. A computer readable storage medium, characterized in that the computer readable storage medium stores computer instructions for causing a processor to implement the prostate image based assessment method according to any one of claims 1 to 14 when executed.
18. A computer program product comprising a computer program which, when executed by a processor, implements the method of assessing a prostate-image based according to any one of claims 1-14.

Description

Evaluation method, device, equipment, medium and product based on prostate image Technical Field The disclosure relates to the technical field of medical image processing, in particular to an evaluation method, device, equipment, medium and product based on a prostate image. Background The accurate evaluation of the prostate function is a core decision basis for promoting the optimization of an intervention scheme and realizing personalized intervention, and has key effects on improving the intervention effect and reducing the bad risk. The existing evaluation mode mainly relies on manually observing anatomical features such as the size, surface texture, hardness degree, envelope integrity and the like of key glands in the prostate, and makes subjective judgment by combining clinical experience. The evaluation mode is greatly influenced by subjective factors, and due to the lack of a unified quantitative anchoring standard, a universality and standardization evaluation flow cannot be constructed, objectivity and repeatability of an evaluation task are difficult to ensure, and standardized iteration of a prostate intervention technology is further restricted. Disclosure of Invention The embodiment of the disclosure provides an evaluation method, device, equipment, medium and product based on a prostate image, which are used for solving the problem of insufficient accuracy of an evaluation mode depending on manpower, realizing objectivity and repeatability of a prostate evaluation task and providing assistance for promoting standardized iteration of a prostate intervention technology. One aspect of the present disclosure provides a method of evaluating based on a prostate image, the method comprising: Acquiring first image data of a target region of a prostate matched with a structural assessment model, the structural assessment model comprising a structural morphology network and a structural assessment network; feature extraction is carried out on the first image data through the structural morphology network, so as to obtain morphology feature data, wherein the morphology feature data represents quantization information of structural morphology of the prostate target area; And carrying out structural evaluation according to the morphological feature data through the structural evaluation network, and determining structural evaluation data of the prostate target area. Another aspect of the present disclosure provides an evaluation apparatus based on a prostate image, the apparatus comprising: A first image data acquisition module for acquiring first image data of a target region of a prostate that is matched with a structural assessment model, the structural assessment model comprising a structural morphology network and a structural assessment network; the morphological feature data determining module is used for carrying out feature extraction on the first image data through the structural morphological network to obtain morphological feature data, and the morphological feature data represent quantitative information of the structural morphology of the prostate target area; And the structure evaluation data determining module is used for performing structure evaluation according to the morphological characteristic data through the structure evaluation network and determining the structure evaluation data of the prostate target area. Another aspect of the present disclosure provides an electronic device, comprising: At least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the prostate image-based assessment method of any of the embodiments of the present disclosure. Another aspect of the present disclosure provides a computer-readable storage medium storing computer instructions for causing a processor to implement a prostate image-based assessment method according to any one of the embodiments of the present disclosure when executed. Another aspect of the present disclosure provides a computer program product comprising a computer program which, when executed by a processor, implements a method of assessing based on a prostate image according to any of the embodiments of the present disclosure. According to the technical scheme, the structural evaluation model is built through the structural morphological dimension planning quantitative feature of the prostate, the structural morphological network in the structural evaluation model is used for carrying out feature extraction on the first image data of the prostate target area to obtain morphological feature data, the structural evaluation network in the structural evaluation model is used for evaluating according to the morphological feature data to determine the structural evaluation data of the prostate target area, the standardized quantitative characterization of the structural morpho