Imaging omics analysis method fusing traditional features and depth features

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...

Images