Medical image classification method and device, computer equipment and storage medium

Abstract

The invention relates to a medical image classification method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining a medical image, and taking the medical image as a training sample; constructing a channel information interaction perception network, wherein the network comprises an input network, a feature extraction network and an output network; training the channel information interaction perception network according to the training sample to obtain a medical image classification model; and acquiring a to-be-tested medical image, and inputting the to-be-tested medical image into the medical image classification model to obtain the category of the medical image. According to the method, the feature of ta previous module and the currently extracted feature are combined, so that it is guaranteed that information flows among the modules in a feed-forward mode, frequent change of the information among the modules is effectively avoided, the learning ability of the modules is improved, and the feature extraction ability of the network is enhanced; and after the pathological picture of a patient is transmitted to the trained network model, a diagnosis result can be directly given, so that the working efficiency of a doctor can be improved, the doctor is effectively helped to reduce the missed diagnosis rate, and the diagnosis accuracy is improved.

Description

technical field [0001] The present application relates to the technical field of image recognition, in particular to a medical image classification method, device, computer equipment and storage medium. Background technique [0002] Currently, the common clinical methods for the detection of colorectal cancer include fecal occult blood test, optical colonoscopy, and sigmoidoscopy. Among them, the biopsy of polyp tissue through optical colonoscopy to determine whether there is tumor, the nature of the tumor and the degree of differentiation is the gold standard for colon examination. However, if all the polyps found are removed and pathological biopsy is performed, a large amount of labor costs will be invested, which is not conducive to vigorously promoting the prevention and research of colorectal cancer. In order to improve the detection rate of precancerous polyps, in addition to improving the inspection level of endoscopists through systematic training and rich practica...

AI Technical Summary

Problems solved by technology

[0004] Existing medical image recognition algorithms cannot overcome problems such as information loss, gradient disappearance, and degradation when the network is transmitted as the number of network layers deepens. At the same time, the similarity between categories of colon polyp images is high and the variability within categories is low. , can lead to model bias and overfitting, leading to poor performance and generalization

Images