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

Esophageal-gastric junction tumor image classification method, system and device and storage medium

A gastric junction and junction technology are applied in the field of image classification methods, equipment and storage media, and systems for tumors in the esophagogastric junction, which can solve problems such as limited research in identification, reduce pain and economic burden, and stabilize evaluation effects. Easy-to-operate effects

Pending Publication Date: 2022-07-15
THE FIRST AFFILIATED HOSPITAL OF ZHENGZHOU UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are limited studies on the distinction between EGJ squamous cell carcinoma and adenocarcinoma at home and abroad.

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
  • Esophageal-gastric junction tumor image classification method, system and device and storage medium
  • Esophageal-gastric junction tumor image classification method, system and device and storage medium
  • Esophageal-gastric junction tumor image classification method, system and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0149] A method for classifying images of esophagogastric junction tumors, comprising the following steps:

[0150] S1. Process the enhanced CT image of the tumor at the esophagogastric junction of the subject to obtain a three-dimensional ROI area image of the tumor medical image lesion; the enhanced CT image is an arterial phase enhanced CT image, and the three-dimensional ROI area image is an arterial phase image 3D ROI area image;

[0151] S2, extracting the radiomics feature in the three-dimensional ROI area image;

[0152] S3, the value of the radiomics feature extracted in step S2 is input into the score prediction model, and the image score of the three-dimensional ROI region image is obtained by calculation;

[0153] S4. Perform qualitative analysis on the image scores obtained in step S3 to predict the image type of the tumor medical image.

[0154]In step S1, the tumor medical image of the esophagogastric junction of the subject is processed, and the specific oper...

Embodiment 2

[0198] A method for classifying images of esophagogastric junction tumors, comprising the following steps:

[0199] S1. Process the enhanced CT image of the tumor at the esophagogastric junction of the subject to obtain a three-dimensional ROI area image of the tumor medical image lesion; the enhanced CT image is a venous phase enhanced CT image, and the three-dimensional ROI area image is a venous phase image 3D ROI area image;

[0200] S2, extracting the radiomics feature in the three-dimensional ROI area image;

[0201] S3, the value of the radiomics feature extracted in step S2 is input into the score prediction model, and the image score of the three-dimensional ROI region image is obtained by calculation;

[0202] S4. Perform qualitative analysis on the image scores obtained in step S3 to predict the image type of the tumor medical image.

[0203] In step S1, the tumor medical image of the esophagogastric junction of the subject is processed, and the specific operation...

Embodiment 3

[0236] A method for classifying images of esophagogastric junction tumors, comprising the following steps:

[0237] S1. Process the enhanced CT image of the tumor at the esophagogastric junction of the subject to obtain a three-dimensional ROI image of the tumor medical image lesion; the enhanced CT image includes an arterial phase enhanced CT image and a venous phase enhanced CT image, and the three-dimensional The ROI area images include three-dimensional ROI area images in the arterial phase and three-dimensional ROI area images in the venous phase. The enhanced CT images in the arterial phase of the subjects' esophagogastric junction tumors are processed to obtain the three-dimensional ROI area images in the arterial phase. The venous phase enhanced CT images of the junction tumor were processed to obtain a three-dimensional ROI image in the venous phase;

[0238] S2, extracting the radiomic features in the three-dimensional ROI area image of the arterial phase and the thr...

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 relates to the technical field of computer vision and medical image analysis, and particularly discloses an esophageal-gastric junction tumor image classification method, system and device and a storage medium. The specific steps of the classification method are as follows: S1, processing a tumor medical image of an esophageal-gastric junction of a subject, and obtaining a three-dimensional ROI region image of a focus of the tumor medical image; s2, image omics characteristics in the three-dimensional ROI region image are extracted; s3, inputting the values of the radiomics characteristics extracted in the step S2 into a score prediction model, and calculating to obtain an image score of the three-dimensional ROI region image; and S4, performing qualitative analysis on the image score obtained in the step S3, and predicting the image type of the tumor medical image. The classification method provided by the invention can predict whether the tumor of the esophageal-gastric junction belongs to adenocarcinoma or squamous carcinoma before an operation, the predicted AUC can reach 0.8 or above, and the accuracy is relatively high; and moreover, the device has the advantage of non-invasiveness before operation.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence and medical image analysis, in particular to a method, system, equipment and storage medium for classifying images of tumors in the esophagus-gastric junction. Background technique [0002] In recent years, the incidence of gastric cancer has been gradually decreasing worldwide, and the incidence of esophagogastric junction (EGJ) cancer has been increasing year by year. EGJ refers to the virtual anatomical junction between the tubular esophagus and the cystic stomach. EGJ cancer is defined as a cancer whose tumor center is located within 5 cm above and below the esophagus-stomach anatomical junction and crosses or touches the EGJ. Its biological behavior is similar to that of gastric cancer or esophagus. Different from cancer, EGJ cancer, as a special type of tumor, is more prone to lymph node metastasis and hematogenous metastasis, and is mostly in the advanced stage at the time o...

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 Applications(China)
IPC IPC(8): G06V10/764G06K9/62G06V10/25G06V10/26G06V10/44G06T7/00G06T7/11G06T17/00
CPCG06T7/0012G06T7/11G06T17/00G06T2207/10081G06T2207/20081G06T2207/20104G06T2207/30096G06T2207/30092G06F18/241
Inventor 黄文鹏高剑波李莉明刘晨晨周宇涵
Owner THE FIRST AFFILIATED HOSPITAL OF ZHENGZHOU UNIV
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