Classification method, computer equipment and storage medium

Abstract

The invention relates to a classification method, computer equipment and a storage medium. The computer equipment inputs an input slice set corresponding to a current layer slice of a to-be-detected image into a pre-trained multi-channel classification network model to obtain a feature classification result of the current layer of slices, and inputs the feature classification result of the current-layer slice into a first classifier to obtain a slice level classification result of the current slice. As in the classification method, the input slice set corresponding to the current layer slice comprises the current layer slice and an associated layer slice of the current layer slice, the slices related to the current-layer slice are classified as input at the same time, and the data completestructure information of the current layer of slices is reserved, and the first classifier is obtained by training according to the slices of the plurality of samples and the actual classification labels, so that the classification result is more specific and more conforms to the actual scene, and the reliability and accuracy of the classification result are greatly ensured.

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