MEDICAL IMAGE DETECTION METHOD BASED ON DEEP LEARNING, AND RELATED DEVICE

摘要

Provided are a medical image detection method and apparatus based on deep learning, a computer-readable medium and an electronic device. The method comprises: acquiring a medical image to be detected, wherein the medical image to be detected comprises a plurality of slice maps; and for each slice map in the medical image to be detected, executing, by means of a deep neural network, the following operations: obtaining, through extraction, N basic feature maps of the slice map, and performing feature fusion on the N basic feature maps of the slice map to obtain M enhanced feature maps of the slice map; executing a hierarchical dilated convolution operation on each enhanced feature map to generate a superimposed feature map of each enhanced feature map of the slice map; and predicting, by means of the deep neural network and according to the superimposed feature map of each slice map in the medical image to be detected, position information of a region of interest in the medical image to be detected and a confidence level thereof, wherein N and M are both integers greater than one. By means of the technical solutions of the embodiments of the present application, the target detection accuracy for a medical image can be improved.