Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

System and method for automatic segmentation and localization of prostate cancer on mpMRI

A prostate cancer and automatic segmentation technology, applied in the field of medical information, can solve the problems of lack of cancer focus location information, unfavorable, and reduced doctor's work efficiency, and achieve the effect of more humanized process, improved work efficiency, and complete report content

Active Publication Date: 2022-07-15
北京赛迈特锐医疗科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the main purpose of the present invention is to provide a system and method for automatically segmenting and locating prostate cancer on mpMRI, which can solve the problems in the prior art that are not conducive to guiding biopsy and reduce the cost of doctors. work efficiency problem

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • System and method for automatic segmentation and localization of prostate cancer on mpMRI
  • System and method for automatic segmentation and localization of prostate cancer on mpMRI
  • System and method for automatic segmentation and localization of prostate cancer on mpMRI

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] figure 1 A schematic diagram of the system structure for automatic segmentation and localization of prostate cancer on mpMRI according to Embodiment 1 of the present invention is shown; as figure 1 As shown, the system includes: an AI scheduling module 10, a prostate segmentation module 20, a prostate cancer intelligent detection module 30 and a structured reporting module 40, wherein,

[0034] The AI ​​scheduling module 10 is respectively connected with the prostate segmentation module 20, the prostate cancer intelligent detection module 30 and the structured reporting module 40, and is used when the patient has completed the scan and the examination item is a multiparametric MRI (mpMRI) examination of the prostate. , extract the header file information of the DICOM image, find the ADC sequence image based on the header file information, and send the ADC sequence image to the prostate segmentation module 20 and the prostate cancer intelligent detection module 30;

[0...

Embodiment 2

[0061] image 3 A schematic structural diagram of a system for automatically segmenting and locating prostate cancer on mpMRI according to Embodiment 2 of the present invention is shown, as shown in FIG. image 3 As shown, the prostate cancer intelligent detection module 30 also includes a judgment unit 302, which is connected to the AI ​​scheduling module 10 and is used to calculate the sum of the percentage values ​​of all the partitions. When the sum of the percentage values ​​is equal to 1, it is judged that the cancer focus is in the prostate. Internally, when the sum of the percentage values ​​is less than 1 and greater than 0, it is judged that the cancer foci has extraprostatic invasion; when the sum of the percentage values ​​is equal to 0, it is judged that the cancer foci is not in the prostate; and the judgment data is sent to the AI ​​scheduling module 10.

[0062] The embodiment of the present invention is provided with a judging unit, which can judge whether ea...

Embodiment 3

[0064] Figure 4 A schematic structural diagram of a system for automatically segmenting and locating prostate cancer on mpMRI according to Embodiment 3 of the present invention is shown; such as Figure 4 As shown, the prostate cancer intelligent detection module 30 further includes a marker lesion identification unit 304, which is respectively connected with the judgment unit 302 and the AI ​​scheduling module 10, and is used for identifying the extra-prostatic invasion data based on the extra-prostatic invasion data when receiving the extra-prostatic invasion data. Corresponding cancer foci data, determine that the cancer foci is a marker cancer foci; when no extraprostatic invasion data is received, based on the three-dimensional diameter of each cancer foci and the volume of each cancer foci, identify the cancer foci with the largest cancer foci, Then the cancer focus is judged as a marker lesion, and the key image, three-dimensional diameter and volume of the tumor focus...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a system for automatically segmenting and locating prostate cancer on mpMRI, comprising an AI scheduling module that searches for an ADC sequence image when a patient has finished scanning the examination item for prostate mpMRI; the prostate segmentation module divides the prostate gland into The prostate gland is divided into a plurality of different partitions; the intelligent prostate cancer detection module identifies all the cancer foci of the prostate in the ADC sequence image, and measures the three-dimensional diameter and volume of each cancer foci; based on the image data after the partition, calculates The percentage value of the volume of the overlapped part of the cancer focus and each partition in the volume of the cancer focus, and the partition with the largest percentage value is determined as the location of the cancer focus; the structured report module outputs the partition where the cancer focus is located based on the returned results and outputs the PI‑RADS score (4 or 5). The invention also discloses a method for automatically segmenting and locating prostate cancer on mpMRI. The invention can accurately locate the position of the cancer foci, judge whether the cancer foci has invaded outside the prostate, and improve the work efficiency.

Description

technical field [0001] The present invention relates to the field of medical information, and more particularly, to a system and method for automatically segmenting and locating prostate cancer on mpMRI. Background technique [0002] The main task of prostate mpMRI examination is to detect and locate cancer to guide needle biopsy. The clinical requirements for the mpMRI report are: clearly write the size and location of each cancer foci. According to clinical routine or international guidelines, each tumor foci should provide localization information annotated according to the template. Lack of positioning information, or the positioning information is unclear, the positioning information is not given according to the template, etc., which are all irregular, and the value of the image report is limited at this time. [0003] In addition, because prostate cancer is basically multiple, the most important cancer foci should be paid attention to during puncture. This cancer fo...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): A61B5/055
CPCA61B5/055A61B5/4381
Inventor 张晓东王霄英岳新贺长征张虽虽
Owner 北京赛迈特锐医疗科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com