Prostate needle biopsy method, equipment and program product
Through the computer-assisted prostate puncture biopsy method, nine puncture sites were located to cover the lesions and surrounding areas, solving the problem of excessive puncture needles in the existing technology, achieving efficient and safe diagnosis of prostate cancer, and reducing the risk of complications and medical costs.
Patent Information
- Application Number
- CN202411369934.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-29
- Publication Date
- 2024-11-26
AI Technical Summary
The existing prostate puncture biopsy method requires a larger number of puncture needles, which increases the risk of complications such as infection and bleeding, and may increase the difficulty of subsequent surgery, as well as increase medical costs and patient burden.
A computer-assisted prostate puncture biopsy method is used to identify and segment the areas of interest by obtaining images, and nine puncture sites are located for puncture, which is evenly distributed to cover the lesion and surrounding areas, reducing the number of puncture needles.
While ensuring the detection rate, the number of puncture needles is reduced, the diagnosis and treatment efficiency is improved, the medical cost is saved, the surgical time is shortened, the complication rate is reduced, the patient burden is reduced, and the operation safety is improved.
Smart Images

Figure CN119014954A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent medical care, and specifically to a method, device and program product for prostate puncture biopsy. Background Art
[0002] Prostate cancer is one of the most common malignant tumors in men worldwide and the leading cause of cancer-related death in men. In recent years, the incidence and mortality of prostate cancer in my country have shown an increasing trend year by year. For patients suspected of prostate cancer (PCa), the most ideal biopsy diagnostic method should be to detect clinically significant prostate cancer (csPCa) while minimizing the detection of clinically insignificant cancer, thereby reducing the burden on patients and the cost of the healthcare system. For the detection of csPCa, although increasing the number of needles for biopsy will increase its detection rate, the increased burden on patients and medical costs should also be weighed.
[0003] In addition, with the development of imaging technology and the continuous updating of puncture biopsy methods, the safety of puncture biopsy methods has gradually attracted the attention of the academic community. Although the current guidelines recommend that patients with suspicious lesions on the image undergoing the first puncture should undergo systematic puncture combined with targeted puncture (TB+SB), this requires a large number of puncture needles, which increases the risk of complications such as infection and bleeding, and may increase the difficulty of subsequent radical prostatectomy due to local inflammation, fibrosis, adhesion, infection, etc. Previous studies have pointed out that increasing the number of biopsy needles may be related to an increase in the incidence of complications such as rectal bleeding, hematuria, hematospermia, infection, and urinary retention. Therefore, appropriately reducing the number of puncture biopsy needles while ensuring the detection rate will not only improve the efficiency of diagnosis and treatment. Summary of the invention
[0004] In view of the above problems, the present invention provides a method for prostate puncture biopsy, comprising:
[0005] S1: Obtain the image of the subject;
[0006] S2: Identify and segment the region of interest based on the image to obtain an image of the region of interest;
[0007] S3: Based on the image of the region of interest, the biopsy puncture position is located to obtain a biopsy position, wherein the biopsy puncture position includes nine puncture sites.
[0008] The region of interest is a lesion region, the positions of the nine puncture sites are evenly distributed, and the distribution area of the nine puncture sites is larger than the region of interest;
[0009] Optionally, the locations of the nine-needle biopsy punctures include one or more of the following: lesion site, lesion and surrounding tissue, and surrounding tissue.
[0010] The region of interest includes the lesion and the area surrounding the lesion;
[0011] Optionally, the lesion peripheral area is an area extending N millimeters outward from the lesion area, where N is a natural number greater than 5;
[0012] Optionally, the lesion peripheral area is an area extending outward by 10 mm.
[0013] The nine puncture sites are evenly distributed in the region of interest;
[0014] Optionally, the uniform distribution is that the positions of the nine biopsy needles cover the region of interest at approximately equidistant intervals;
[0015] Optionally, the nine biopsy needle punctures are positioned at intervals of 5 mm to cover the region of interest.
[0016] The images include one or more of the following: multi-parameter magnetic resonance imaging, ultrasound;
[0017] Optionally, when the acquired image is a multi-parameter magnetic resonance image and an ultrasound image, the multi-parameter magnetic resonance image and the ultrasound image are registered and fused to obtain a fused image, and S2 is replaced by: identifying and segmenting a region of interest based on the fused image to obtain a region of interest image;
[0018] Optionally, when the acquired images are multi-parameter magnetic resonance images and ultrasound images, S2 is replaced by: identifying and segmenting the multi-parameter magnetic resonance image to obtain the image of the region of interest, and aligning and fusing the image of the region of interest with the ultrasound image to obtain the fused image of interest; and S3 is replaced by: locating the biopsy puncture position based on the fused image of interest to obtain the biopsy position.
[0019] The recognition is performed by detecting the position and frame of the region of interest through a target detection model, and then the frame of the region of interest is segmented to obtain an image of the region of interest;
[0020] Optionally, the target detection model includes one or more of the following: Faster R-CNN, YOLO v5, SSD, MaskR-CNN, RetinaNet, EfficientDet, DETR, Cascade R-CNN, ATSS;
[0021] Optionally, the segmentation is performed by a segmentation model to obtain an image of a region of interest;
[0022] Optionally, the segmentation model includes one or more of the following: FCN, U-Net, PSPNet, Deeplab series, EncNet, Semantic FPN, HRNet.
[0023] The method further comprises preprocessing, scoring the lesions in the image to obtain a scored image, screening the scored image to obtain a screened image, and identifying and segmenting a region of interest based on the screened image to obtain a region of interest image;
[0024] Optionally, images that do not require a biopsy are removed through the screening.
[0025] The object of the present invention is to provide a computer program product having a computer program or instructions thereon, wherein the computer program or instructions are executed by a processor to implement the above-mentioned prostate puncture biopsy method.
[0026] The object of the present invention is to provide a computer device, comprising a processor, a memory and a computer program or instructions stored in the memory, wherein the computer program or instructions are executed by the processor to implement the above-mentioned prostate puncture biopsy method.
[0027] An object of the present invention is to provide a computer-readable storage medium having a computer program or instructions stored thereon, wherein the computer program or instructions are executed by a processor to implement the above-mentioned prostate puncture biopsy method.
[0028] Advantages of the present invention:
[0029] 1. A method of reduced-needle puncture biopsy is proposed. Nine needles are used to perform puncture biopsy on the lesion and surrounding areas. While ensuring the detection rate, the number of puncture biopsy needles is appropriately reduced. This will not only improve the efficiency of diagnosis and treatment, save medical costs, shorten the operation time, and reduce the workload of puncture biopsy doctors and pathologists, but also improve the safety of the operation, reduce the incidence of complications, and reduce the burden on patients.
[0030] 2. Local saturation puncture is performed through nine needles to cover the lesion and its surrounding area, which can achieve better detection results compared with traditional systematic puncture. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0032] Figure 1 A schematic flow chart of a prostate puncture biopsy method provided by an embodiment of the present invention;
[0033] Figure 2 A schematic diagram of a prostate puncture biopsy system provided by an embodiment of the present invention;
[0034] Figure 3 A schematic diagram of a prostate puncture biopsy device provided in an embodiment of the present invention;
[0035] Figure 4 Schematic diagram of 3TB+12SB and 9RSB provided in an embodiment of the present invention, Targeted biopsy: targeted biopsy puncture, Systematic biopsy: systematic puncture, Regional saturation biopsy: local saturation puncture. DETAILED DESCRIPTION
[0036] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.
[0037] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The sequence numbers of the operations, such as S101, S102, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.
[0038] Figure 1 A schematic diagram of a prostate puncture biopsy method provided by an embodiment of the present invention specifically includes:
[0039] S1: Obtain the image of the subject;
[0040] In one embodiment, the image includes one or more of the following: multi-parameter magnetic resonance imaging, ultrasound.
[0041] In one embodiment, the ultrasound image is a TRUS ultrasound image.
[0042] In one embodiment, the method further includes preprocessing, scoring the lesions in the image to obtain a scored image, screening the scored image to obtain a screened image, and identifying and segmenting the region of interest based on the screened image to obtain a region of interest image.
[0043] In one embodiment, the screening removes images that do not require a biopsy.
[0044] In a specific embodiment, the detection rate of prostate targeted puncture (TB) based on multi-parameter magnetic resonance imaging (mpMRI) is not inferior to that of traditional 12-needle transrectal ultrasound-guided prostate systematic puncture (SB). It can not only accurately locate suspicious lesions and effectively improve the accuracy of puncture, but also reduce unnecessary punctures and reduce the detection of clinically insignificant cancers.
[0045] In a specific embodiment, the present invention is a single-center, prospective, randomized controlled study. The subjects included in the study were randomly divided into two groups at a ratio of 1:1 using a computer-generated random number sequence to ensure that the allocation of experimental conditions was unbiased. The first group of subjects received a conventional 3TB+12SB puncture biopsy; the second group of subjects received a 9RSB puncture biopsy, that is, 9 needle punctures were performed at intervals of 5 mm for the lesions found by mpMRI and the range of 10 mm in radius around them, according to the shape and location of the suspicious lesions. By analyzing and comparing indicators such as csPCa detection rate and surgical operation time between the two groups of subjects, the effectiveness of different puncture schemes was evaluated, etc., to provide clinical evidence for further optimizing the clinical diagnosis and treatment plan of prostate puncture biopsy and promoting the accurate diagnosis and treatment of prostate cancer.
[0046] In a specific embodiment, the present invention prospectively collects subjects who have mpMRI suspicious prostate cancer lesions (PIRADS V2.1 4-5 points) from January 2024 to June 2024, have indications for prostate puncture and plan to undergo initial prostate puncture biopsy at Peking University First Hospital.
[0047] Inclusion criteria:
[0048] (1) Aged 45-85 years;
[0049] (2) The hospital's prostate mpMRI imaging data were complete, the image quality control was qualified, a single suspicious lesion was found, and the PI-RADS V2.1 score was 4 or 5;
[0050] (3) Meet the indications for prostate biopsy in the clinical guidelines and undergo the first biopsy (suspicious prostate nodules found by rectal examination; suspicious lesions found by transrectal ultrasound or MRI; tPSA>10 ng / mL; tPSA 4-10 ng / mL, f / t<0.16 or PSAD>0.15);
[0051] (4) The aforementioned lesions have pathological results of puncture biopsy, and the interval between them and prostate mpMRI examination is no more than 1 month;
[0052] (5) Complete clinical data.
[0053] Exclusion criteria:
[0054] (1) The quality of prostate mpMRI imaging data is unsatisfactory or some sequences are missing;
[0055] (2) receiving radiotherapy, chemotherapy, endocrine therapy, and surgical treatment before prostate mpMRI examination or prostate puncture;
[0056] (3) PI-RADS V2.1≤3 points;
[0057] (4) Those who do not meet the indications for prostate puncture in the clinical guidelines, are not undergoing prostate puncture for the first time, or have not completed systematic prostate puncture + targeted puncture;
[0058] (5) Unable to cooperate in completing the prostate systematic puncture + targeted puncture, or the individual or family members refuse to participate;
[0059] (6) The clinical data are incomplete.
[0060] S2: Identify and segment the region of interest based on the image to obtain an image of the region of interest;
[0061] In one embodiment, when the acquired images are multi-parameter magnetic resonance images and ultrasound images, the multi-parameter magnetic resonance images and ultrasound images are registered and fused to obtain a fused image, and S2 is replaced by: identifying and segmenting the region of interest based on the fused image to obtain a region of interest image.
[0062] In one embodiment, when the acquired images are multi-parameter magnetic resonance images and ultrasound images, S2 is replaced by: identifying and segmenting the multi-parameter magnetic resonance image to obtain the region of interest image, registering and fusing the region of interest image with the ultrasound image to obtain the fused image of interest, and S3 is replaced by: locating the biopsy puncture position based on the fused image of interest to obtain the biopsy position.
[0063] In one embodiment, the recognition is performed by detecting the position and frame of the region of interest through a target detection model, and then the frame of the region of interest is segmented to obtain an image of the region of interest;
[0064] Optionally, the target detection model includes one or more of the following: Faster R-CNN, YOLO v5, SSD, MaskR-CNN, RetinaNet, EfficientDet, DETR, Cascade R-CNN, ATSS.
[0065] In one embodiment, the segmentation is performed by segmenting a segmentation model to obtain an image of a region of interest;
[0066] Optionally, the segmentation model includes one or more of the following: FCN, U-Net, PSPNet, Deeplab series, EncNet, Semantic FPN, HRNet.
[0067] In one embodiment, through MRI / TRUS software fusion image, MRI / TRUS software fusion targeted puncture refers to the fusion of MRI and TRUS images through a fusion platform before performing targeted puncture to clearly display the target, and then track the probe and perform puncture under its guidance.
[0068] In one embodiment, a multi-parameter magnetic resonance image is acquired, the magnetic resonance image is analyzed and lesions are identified and risk is assessed according to PI-RADS guidelines, the prostate and lesions in the magnetic resonance image are then segmented, and image reconstruction is performed based on the segmented image to generate a 3D region of interest image;
[0069] Acquire an ultrasound image, segment the prostate, and then reconstruct the image based on the segmented ultrasound image to obtain a 3D image or directly obtain a 3D region of interest image through 3D software;
[0070] The 3D region of interest image of the magnetic resonance image and the 3D region of interest image of the ultrasound are registered and fused to obtain a 3D fused image, and the location of the biopsy puncture is determined based on the 3D fused image.
[0071] In a specific embodiment, all subjects who are clinically suspected of prostate cancer and are scheduled to undergo prostate puncture biopsy are subjected to mpMRI examination using a 3.0T superconducting magnetic resonance scanner (Discovery 750, GE Healthcare; Achieva, Philips Healthcare). All MRI images are evaluated by at least two experienced radiologists, and suspicious lesions found on mpMRI are scored according to the PI-RADS V2.1 version guidelines. For subjects who meet the inclusion criteria, baseline information such as age, gender, BMI, comorbidities, anticoagulant medication, rectal examination results, PSA levels, mpMRI image features, PI-RADS V2.1 scores, etc. are collected before puncture. All subjects underwent transrectal puncture biopsy (TRBx) under ultrasound guidance. The ultrasound was performed using a color Doppler ultrasound diagnostic instrument (Esaote Mylab 9eHD) and a transrectal end-scanning probe (4-10MHz). MRI / TRUS image recognition fusion targeted puncture was performed; it was equipped with a sterile puncture guide frame; BARD automatic biopsy gun and 18G biopsy needle. The puncture operation time was recorded for each subject. After the puncture operation was completed, the subject was observed in the observation room for at least 30 minutes to observe whether there was more severe bleeding, vasovagal reaction, allergic reaction, etc.
[0072] S3: Based on the image of the region of interest, the biopsy puncture position is located to obtain a biopsy position, wherein the biopsy puncture position includes nine puncture sites.
[0073] In one embodiment, the region of interest is a lesion region, the positions of the nine puncture sites are evenly distributed, and the distribution area of the nine puncture sites is larger than the region of interest;
[0074] The locations of the nine-needle biopsy punctures include one or more of the following: lesion site, lesion and surrounding tissue, and surrounding tissue.
[0075] In another embodiment, the region of interest includes a lesion and an area surrounding the lesion;
[0076] Optionally, the lesion peripheral area is an area extending N millimeters outward from the lesion area, where N is a natural number greater than 5;
[0077] Optionally, the lesion peripheral area is an area extending outward by 10 mm.
[0078] The nine puncture sites are evenly distributed in the region of interest;
[0079] Optionally, the uniform distribution is that the positions of the nine biopsy needles cover the region of interest at approximately equidistant intervals;
[0080] Optionally, the nine biopsy needle punctures are positioned at intervals of 5 mm to cover the region of interest.
[0081] In one embodiment, the distribution of nine needle biopsy punctures and traditional punctures is as follows Figure 4 As shown in the figure, the nine-needle biopsy punctures are evenly spaced in the lesion area and the surrounding area of the lesion. Traditional punctures include 12-needle systematic punctures and 3-needle targeted punctures. The 12-needle systematic punctures are distributed in the entire prostate area, and the puncture positions do not include the lesion area. The lesion area is biopsied by 3-needle targeted punctures. By comparing the number of positive puncture needles, the proportion of positive needles, the maximum positive proportion, and the single-needle puncture pathological Gleason score of the nine-needle biopsy (nine-needle local saturation biopsy 9RSB) and traditional puncture (3TB+12SB), the PCa and csPCa detection rates of the 9RSB scheme are not inferior to those of 3TB+12SB.
[0082] In a specific embodiment, the visual analogue scale (VAS) scale is used to assess the pain and degree of the subject immediately after the puncture. The biopsy specimens are evaluated by two experienced pathologists, and the pathological characteristics such as the number of positive puncture needles, the proportion of positive needles, the maximum positive proportion, and the single-needle puncture pathological Gleason score are reported. For subjects who subsequently undergo radical prostatectomy in this hospital, the surgical resection specimens are evaluated by two experienced pathologists and the pathological characteristics such as tumor size, location, T stage, Gleason score, capsule and nerve invasion are reported. By analyzing and comparing the csPCa detection rate, complication rate, surgical operation time and other indicators between the two groups of subjects, the effectiveness and safety of different puncture schemes are evaluated, so as to provide clinical evidence for further optimizing the clinical diagnosis and treatment of prostate puncture biopsy and promoting the precise diagnosis and treatment of prostate cancer.
[0083] In a specific embodiment, the primary study endpoint is the detection rate of clinically significant prostate cancer (csPCa, prostate cancer with Gleason score = 3+4 or higher).
[0084] Secondary study outcomes were (1) prostate cancer detection rate; (2) clinically insignificant prostate cancer detection rate; (3) prostate biopsy pathological Gleason score; (4) maximum proportion of cancerous tissue in prostate biopsy pathology; (5) subject-reported pain and discomfort; (6) biopsy operation time; and (7) pathological upgrade rate after radical prostatectomy.
[0085] In a specific embodiment, the present invention includes a total of 120 patients (9RSB: n=60, 3TB+12SB: n=120). The median age is 67 years old. The median PSA is 9.45ng / ml. The baseline data of the two groups are balanced and comparable. The overall csPCa and PCa detection rates of the included patients were 54.2% and 63.3%, respectively. The csPCa detection rate of 9RSB (51.7% vs. 60.0%, p=0.855) is not inferior to that of 3TB+12SB, and the PCa detection rate of 9RSB (60.0% vs. 63.3%, p=0.851) is not inferior to that of 3TB+12SB. 9RSB significantly reduced the number of puncture needles (9 needles vs. 15 needles) and significantly shortened the surgical operation time (164s vs. 223s, p<0.001). The pain and discomfort levels of patients after 9RSB surgery were lower than those of 3TB+12SB.
[0086] Compared with the conventional 3TB+12SB regimen, the PCa and csPCa detection rates of the 9RSB regimen are not inferior to those of 3TB+12SB, and it can significantly reduce the number of puncture needles, significantly shorten the surgical operation time, and reduce the patient's postoperative pain and discomfort.
[0087] In one embodiment, with the development of imaging technology and the continuous updating of puncture biopsy methods, the safety of puncture biopsy methods has gradually attracted the attention of the academic community. Although the current guidelines recommend that patients with suspicious lesions on mpMRI who undergo initial puncture should undergo TB+SB, this requires a large number of puncture needles, which increases the risk of complications such as infection and bleeding, and may increase the difficulty of subsequent radical prostatectomy due to local inflammation, fibrosis, adhesions, and infection. Previous studies have pointed out that increasing the number of biopsy needles may be associated with an increase in the incidence of complications such as rectal bleeding, hematuria, hematospermia, infection, and urinary retention. Therefore, while ensuring the detection rate, appropriately reducing the number of puncture biopsy needles will not only improve the efficiency of diagnosis and treatment, save medical costs, shorten the operation time, and reduce the workload of puncture biopsy doctors and pathologists, but also improve the safety of the operation, reduce the incidence of complications, and reduce the burden on patients. Although many studies have confirmed the effectiveness and feasibility of reduced-needle puncture schemes such as RSB, its safety still needs to be further demonstrated by prospective studies. The latest EAU guidelines in 2024 have recommended TB+RSB for patients with suspicious lesions (PI-RADS ≥ 4) on MRI, but the level of evidence is still low, and high-quality, prospective clinical studies are urgently needed to evaluate the effectiveness and safety of TB combined with RSB to provide higher-level evidence for evidence-based medicine. This study will prospectively recruit subjects to compare RSB and other puncture schemes with traditional TB+SB puncture schemes to evaluate safety and effectiveness, thereby providing high-quality clinical evidence for further optimizing the clinical diagnosis and treatment of prostate puncture biopsy and promoting the precise diagnosis and treatment of prostate cancer.
[0088] The present invention executes all steps through a computer to assist doctors in diagnosis and treatment.
[0089] The disclosed embodiments of the present invention further provide a computer program product or system, including a computer program, which implements the steps of the above-mentioned prostate puncture biopsy method when executed by a processor.
[0090] Figure 2 A schematic diagram of a prostate puncture biopsy system provided by an embodiment of the present invention specifically includes:
[0091] Acquisition unit: acquires the image of the subject;
[0092] Area unit: identifying and segmenting the region of interest based on the image to obtain an image of the region of interest;
[0093] Puncture unit: locates the biopsy puncture position based on the image of the region of interest to obtain the biopsy position, and the biopsy puncture includes nine needles.
[0094] Figure 3 A schematic diagram of a prostate puncture biopsy device provided by an embodiment of the present invention specifically includes:
[0095] A memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, any one of the above-mentioned prostate puncture biopsy methods is performed.
[0096] The disclosed embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it is any one of the above-mentioned methods for prostate puncture biopsy.
[0097] The verification results of this verification example show that assigning inherent weights to indications can improve the performance of the method relative to the default settings. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. In several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways.
[0098] For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, each functional unit in each embodiment of the present invention may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.
[0099] A person of ordinary skill in the art can understand that all or part of the steps in the above-mentioned embodiment method can be implemented by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. The above-mentioned medium storage can be a read-only memory, a disk or an optical disk, etc.
[0100] The above is a detailed introduction to a computer device provided by the present invention. For a person skilled in the art, according to the concept of the embodiments of the present invention, there may be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.
Claims
1. A method for prostate puncture biopsy, It is characterized in that include: S1: Obtain the image of the subject; S2: Identify and segment the region of interest based on the image to obtain an image of the region of interest; S3: Based on the image of the region of interest, the biopsy puncture position is located to obtain a biopsy position, wherein the biopsy puncture position includes nine puncture sites.
2. The method for prostate biopsy according to claim 1, It is characterized in that The region of interest is a lesion region, the positions of the nine puncture sites are evenly distributed, and the distribution area of the nine puncture sites is larger than the region of interest; Optionally, the location of the biopsy puncture includes one or more of the following: lesion site, lesion and surrounding tissue, and surrounding tissue.
3. The method for prostate puncture biopsy according to claim 1, It is characterized in that The region of interest includes the lesion and the area surrounding the lesion; Optionally, the lesion peripheral area is an area extending N millimeters outward from the lesion area, where N is a natural number greater than 5; Optionally, the lesion peripheral area is an area extending outward by 10 mm.
4. The method for prostate puncture biopsy according to claim 3, It is characterized in that The nine puncture sites are evenly distributed in the region of interest; Optionally, the uniform distribution is that the positions of the nine biopsy needles cover the region of interest at approximately equidistant intervals; Optionally, the nine biopsy needle punctures are positioned at intervals of 5 mm to cover the region of interest.
5. The method for prostate biopsy according to claim 1, It is characterized in that The images include one or more of the following: multi-parameter magnetic resonance imaging, ultrasound; Optionally, when the acquired image is a multi-parameter magnetic resonance image and an ultrasound image, the multi-parameter magnetic resonance image and the ultrasound image are registered and fused to obtain a fused image, and S2 is replaced by: identifying and segmenting a region of interest based on the fused image to obtain a region of interest image; Optionally, when the acquired images are multi-parameter magnetic resonance images and ultrasound images, S2 is replaced by: identifying and segmenting the multi-parameter magnetic resonance image to obtain the image of the region of interest, and aligning and fusing the image of the region of interest with the ultrasound image to obtain the fused image of interest; and S3 is replaced by: locating the biopsy puncture position based on the fused image of interest to obtain the biopsy position.
6. The method for prostate puncture biopsy according to claim 1, It is characterized in that The recognition is performed by detecting the position and frame of the region of interest through a target detection model, and then the frame of the region of interest is segmented to obtain an image of the region of interest; Optionally, the target detection model includes one or more of the following: Faster R-CNN, YOLO v5, SSD, Mask R-CNN, RetinaNet, EfficientDet, DETR, Cascade R-CNN, ATSS; Optionally, the segmentation is performed by a segmentation model to obtain an image of a region of interest; Optionally, the segmentation model includes one or more of the following: FCN, U-Net, PSPNet, Deeplab series, EncNet, Semantic FPN, HRNet.
7. The method for prostate biopsy according to claim 1, It is characterized in that The method further comprises preprocessing, scoring the lesions in the image to obtain a scored image, screening the scored image to obtain a screened image, and identifying and segmenting a region of interest based on the screened image to obtain a region of interest image; Optionally, images that do not require a biopsy are removed through the screening.
8. A computer program product having a computer program or instructions thereon, It is characterized in that The computer program or instructions are executed by a processor to implement the prostate puncture biopsy method described in claims 1-7.
9. A computer device comprising a processor, a memory and a computer program or instructions stored in the memory, It is characterized in that The computer program or instructions are executed by a processor to implement the prostate puncture biopsy method described in claims 1-7.
10. A computer-readable storage medium having a computer program or instructions stored thereon, It is characterized in that The computer program or instructions are executed by a processor to implement the prostate puncture biopsy method described in claims 1-7.
Citation Information
Patent Citations
Prostate cancer automatic detection and classification system based on deep learning
CN111028206A
Prostate puncture guiding method, device, equipment and system based on multimode fusion
CN118021410A
Cited By
Biopsy range positioning method and device for gastric ulcer image
CN120852526A
A biopsy range positioning method and device for a gastric ulcer image
CN120852526B
