Cerebral hemorrhage analysis method, computer equipment and storage medium

Abstract

The invention relates to a cerebral hemorrhage analysis method, computer equipment and a storage medium. The method comprises the following steps: acquiring a to-be-analyzed image comprising at leastone bleeding area; inputting the image into a convolutional neural network for feature extraction; obtaining a feature map of an image, inputting the feature map into a region-of-interest extraction network; obtaining a feature map of a detection box containing each bleeding area, inputting the feature map of the detection box containing each bleeding area into a classification network to obtain aclassification result of each bleeding area, and inputting the feature map of the detection box containing each bleeding area into a detection box regression network to obtain the position of each bleeding area. According to the cerebral hemorrhage analysis method, detection and classification of the images containing the multiple hemorrhage areas are achieved at the same time, and the applicability and classification accuracy of the cerebral hemorrhage analysis method are improved.

Description

technical field [0001] The present application relates to the technical field of neural network learning, in particular to an analysis method for cerebral hemorrhage, computer equipment and storage media. Background technique [0002] Cerebral hemorrhage refers to the hemorrhage caused by the rupture of intracranial blood vessels caused by trauma or non-trauma. It has the characteristics of acute onset, critical condition, high mortality and disability rate, and has become the second only to ischemic heart disease in the world. second leading cause of death. The early mortality of cerebral hemorrhage is very high. About half of the patients died within a few days of onset, and most of the survivors left sequelae of varying degrees. Therefore, how to accurately find the location of cerebral hemorrhage in the early stage is particularly important for the treatment of cerebral hemorrhage. [0003] At present, according to the bleeding location, cerebral hemorrhage can be divid...

AI Technical Summary

Problems solved by technology

[0004] However, the above method of directly classifying cerebral hemorrhage types through the classification network has the problem of low classification accuracy.

Images