Tumor malignancy risk stratification auxiliary diagnosis system based on artificial intelligence medical imaging

A technology of artificial intelligence and medical imaging, applied in medical images, medical automated diagnosis, image analysis, etc., can solve the problem of providing reference for clinical decision-making management of space-occupying lesions, questioning the reliability of data and the effective sample size of data, and the lack of data. Clarify issues such as pathological diagnosis information to achieve the effect of increasing diagnostic confidence, improving diagnosis rate, and improving accuracy and reliability

Active Publication Date: 2021-01-26
NANJING GENERAL HOSPITAL NANJING MILLITARY COMMAND P L A
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In general, most of the current systems use public datasets or single-center datasets for training, and the generalization and robustness of the models need to be tested; at the same time, the quality of the data is uneven, and some data even have no clear pathological diagnosis The information, data reliability and effective sample size of the data have been questioned; in addition, most of the current systems use binary classification thinking, pursuing high accuracy or high AUC (area under the ROC curve), but this classification method based on the possibility of malignancy does not Considering the actual situation of clinical application, it cannot effectively provide a reference for the clinical decision-making management of space-occupying lesions

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
  • Tumor malignancy risk stratification auxiliary diagnosis system based on artificial intelligence medical imaging
  • Tumor malignancy risk stratification auxiliary diagnosis system based on artificial intelligence medical imaging
  • Tumor malignancy risk stratification auxiliary diagnosis system based on artificial intelligence medical imaging

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be specifically introduced below in conjunction with specific embodiments.

[0040] The medical images in the present invention include but not limited to X-ray (X-ray) images, CT (Computed Tomography) images, MRI (Magnetic Resonance) images and ultrasonic detection, etc., and the auxiliary diagnosis of tumor malignancy risk stratification in the present invention The system can be integrated on these existing medical imaging devices, or it can be set up independently or on terminals such as servers.

[0041] see figure 1 , the tumor malignancy risk stratified auxiliary diagnosis system of the present invention is realized by artificial intelligence medical imaging, including:

[0042] (1) Data collection module: used to collect existing data, including imaging images, clinical information, gene information, and pathological benign and malignant labels, after verifying and evaluating data integrity and data quality, data desensitization is pe...

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 discloses an artificial intelligence medical imaging system for auxiliary diagnosis of tumor malignant risk stratification, comprising: a data acquisition module, a data preprocessing module, a model establishment module, a model verification and optimization module, a hierarchical diagnosis module and a database platform. The auxiliary diagnosis system for tumor malignant risk stratification of the present invention is based on artificial intelligence technology, which can realize successive stratification of malignant risk of tumors, simulate clinical diagnosis ideas, and detect benign lesions and malignant tumors with high precision using artificial intelligence models The ability to automatically diagnose space-occupying lesions with clear imaging features can substantially assist clinical management decision-making of space-occupying lesions, improve the existing workflow of clinical diagnosis, increase physicians' confidence in diagnosis, reduce work pressure, and reduce the risk of low malignancy The anxiety of patients with lesions has greatly improved the diagnosis rate of benign lesions and malignant tumors, and it is expected to realize the implementation of artificial intelligence clinical auxiliary diagnosis.

Description

technical field [0001] The invention relates to a system and method for auxiliary diagnosis of tumor malignancy risk stratification, in particular to a system and method for auxiliary diagnosis of tumor malignancy risk stratification of artificial intelligence medical imaging; it belongs to the technical field of artificial intelligence auxiliary diagnosis of medical imaging. Background technique [0002] Tumor refers to the new organism formed by the proliferation of local tissue cells under the action of various tumorigenic factors. Most benign lesions do not require surgical intervention without mass effect. The prognosis of early surgical intervention of malignant tumors is usually good, while the prognosis of advanced malignant tumors is generally poor whether it is surgical intervention or radiotherapy and chemotherapy. At present, medical institutions around the world are continuously investing huge sums of money in the study of the occurrence, development and treatm...

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): G06T7/00G06T7/10G16H30/20G16H50/20G16H50/30
CPCG06T7/0012G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30064G06T7/10G16H30/20G16H50/20G16H50/30
Inventor 卢光明吕文晖张其锐周长圣许强张龙江李新宇黄楚熙
Owner NANJING GENERAL HOSPITAL NANJING MILLITARY COMMAND P L A
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products