Imaging omics analysis method fusing traditional features and depth features

A deep feature and radiomics technology, applied in the processing of brain magnetic resonance images, combined with traditional features and deep features in the field of radiomics analysis, to achieve good classification results

Active Publication Date: 2019-12-03
SOUTHEAST UNIV
View PDF8 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At this stage, how to effectively extract and select radiomics features and how to combine them with deep learning models is still a challenging problem, and there is no relevant feasible solution in the existing technology

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
  • Imaging omics analysis method fusing traditional features and depth features
  • Imaging omics analysis method fusing traditional features and depth features
  • Imaging omics analysis method fusing traditional features and depth features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The technical solutions provided by the present invention will be described in detail below in conjunction with specific examples. It should be understood that the following specific embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention.

[0048] The present invention provides a radiomics analysis method that integrates traditional features and deep features, which combines traditional low-level features extracted with high-level deep features extracted using convolutional neural networks. The specific process of the present invention is as figure 1 shown, including the following steps:

[0049] Step 1, traditional feature extraction

[0050] Step 1-1, preprocessing the multimodal image. The multimodal images involved in this example include four sequences, namely T2-weighted fluid attenuated inversion recovery (Flair), T1-weighted (T1), T1-weighted contrast-enhanced (T1c), T2-weighted (T2) . B...

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 image omics analysis method fusing traditional features and depth featuresThe method comprises the following steps: firstly, extracting the traditional features of a regionof interest, such as first-order features, shape features and texture features; secondly, performing feature selection on the extracted original feature set to remove redundant features; secondly, extracting depth features through a convolutional neural network model; and finally, the traditional features and the depth features are fused to realize classification of different groups. Compared withsingle use of traditional features or depth features, the method has the advantage that a better classification effect is obtained.

Description

technical field [0001] The present invention relates to the technical field of digital image processing, and relates to a processing method of brain magnetic resonance images, and more specifically, relates to a radiomics analysis method integrating traditional features and depth features. Background technique [0002] Radiomics technology converts medical images into usable information by extracting high-throughput features from quantitative features. The main steps include region of interest (ROI) segmentation, feature extraction and feature selection, and classifier modeling. Good results have been achieved in the problem. ROI segmentation is still a key and challenging step in the radiomics model. At present, all features are calculated based on the segmented area, and the automatic tumor segmentation technology still has problems such as blurred boundaries, and the progress is not obvious. , so manual segmentation by multiple experienced physicians is still the main me...

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): G06T7/136G06K9/62
CPCG06T7/136G06T2207/20081G06T2207/20084G06T2207/10088G06T2207/30096G06T2207/20221G06F18/241
Inventor 舒华忠袁歆雨杨冠羽孔佑勇
Owner SOUTHEAST UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap