Classification methods, computer equipment and storage media

Abstract

This application relates to a classification method, computer equipment and storage medium. The computer equipment inputs the input slice set corresponding to the current layer slice of the image to be detected into the pre-trained multi-channel classification network model to obtain the feature classification of the current layer slice. As a result, the feature classification result of the current layer slice will be input into the first classifier to obtain the slice-level classification result of the current layer slice, because in this method, the input slice set corresponding to the current layer slice includes the current layer slice and the current layer slice The associated layer slices, so that the slices related to the current layer slice are used as input to classify at the same time, and the complete structure information of the data of the current layer slice is preserved, and the first classifier is trained according to the slices of multiple samples and the actual classification label, so that The classification results are more specific and more in line with the actual scene, which greatly guarantees the reliability and accuracy of the classification results.

Description

technical field [0001] The application relates to the field of medical technology, in particular to a classification method, computer equipment and storage media. Background technique [0002] In the diagnosis process of cerebral hemorrhage, it is very important to determine the location of cerebral hemorrhage. According to the location of cerebral hemorrhage, cerebral hemorrhage can be divided into various types. At present, the diagnosis of cerebral hemorrhage type needs to be judged by CT images of head scan. [0003] In order to improve the accuracy of the classification of cerebral hemorrhage types, the classification of cerebral hemorrhage types based on deep learning algorithms is usually used in the prior art. The methods based on deep learning mainly include 3D convolutional neural network classification methods and 2D convolutional neural network classification methods, wherein, The classification method of the 3D convolutional neural network is as follows: first, ...

AI Technical Summary

Problems solved by technology

[0004] However, the classification method based on 2D convolutional neural network ignores the structural information of the sample, which affects the reliability and accuracy of the classification results of cerebral hemorrhage types

Images