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

Multi-center effect compensation method based on PET/CT intelligent diagnosis system

An intelligent diagnosis and multi-center technology, applied in the field of medical imaging and deep learning, can solve the data volume requirements, the number of cases cannot meet the sample size requirements for fine-tuning, and unrealistic problems, so as to improve the generalization ability and reduce multiple The center effect, the effect of eliminating the multi-center effect

Active Publication Date: 2020-06-26
ZHEJIANG LAB +1
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This problem can be solved by adding the data from the training center to the model for fine tuning, but this solution has certain requirements for the amount of data
However, the number of cases in primary hospitals is often far below the sample size requirements for fine-tuning, so this method is not realistic for these primary hospitals

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
  • Multi-center effect compensation method based on PET/CT intelligent diagnosis system
  • Multi-center effect compensation method based on PET/CT intelligent diagnosis system
  • Multi-center effect compensation method based on PET/CT intelligent diagnosis system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] The following takes the deep convolutional neural network ResNet-152 as an example to explain how to apply this multi-center effect compensation method to the deep convolutional neural network.

[0050] The ResNet-152 network structure is shown in Table 1:

[0051] Table 1: ResNet-152 network structure

[0052]

[0053] In the actual implementation process, training center A used the center's PET / CT image data to train an intelligent auxiliary diagnosis model for benign and malignant tumors based on ResNet-152. used in . However, due to the statistical differences between the imaging protocols used by training center A and test center B, if the model is directly used in test center B, the diagnostic efficiency will decrease to a certain extent. Therefore, the above problems are solved by the polycentric effect compensation method of the present invention. The specific implementation steps are as follows:

[0054] (1) Input all the image data used for training in ...

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 a multi-center effect compensation method based on a PET / CT intelligent diagnosis system, and belongs to the field of medical images. The method comprises the following steps:based on a position scale model about additive and multiplicative multi-center effect parameters, estimating multi-center effect parameters of the test center B relative to the training center A by using a non-parameterized mathematical method for the data of the training center A and the test center B, and compensating the data of the test center B by using the parameters so as to eliminate the multi-center effect between the test center B and the training center A. According to the invention, the multi-center effect between the training center A and the test center B can be compensated, so that the data of the test center B can be used in the model trained by the training center A after compensation, and the generalization ability of the model is indirectly improved.

Description

technical field [0001] The present invention relates to the fields of medical imaging and deep learning, and in particular to a multi-center effect compensation method based on a PET / CT intelligent diagnosis system. Background technique [0002] Positron emission tomography (PET) is a functional imaging device at the molecular level. The radioactive tracer needs to be injected into the patient before scanning, and the tracer decays and annihilates in the patient's body, producing a pair of 511keV gamma photons with emission directions about 180° opposite, and the detector will collect these gamma photons to reach the position of the crystal and time information. By using image reconstruction algorithms to reconstruct and post-process the acquired information, the metabolism and uptake of the reaction tracer in the patient can be obtained. According to the imaging results of PET / CT, doctors comprehensively analyze the patient's condition in combination with various clinical...

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): G06T7/00G06K9/62G16H50/20A61B6/00A61B6/03
CPCG06T7/0012G16H50/20A61B6/032A61B6/037A61B6/5235G06F18/213G16H30/40G06V10/82G06V10/7715G06V10/84G06V2201/03G06V10/774G06V10/766
Inventor 陈凌朱闻韬李辉杨宝饶璠叶宏伟王瑶法
Owner ZHEJIANG LAB
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