Cerebral hemorrhage automatic identification method and system based on deep learning

Abstract

The invention discloses a cerebral hemorrhage automatic identification method and system based on deep learning, and the method comprises the steps: carrying out the data preprocessing of an original brain CT image, and obtaining the preprocessing data; the method comprises the following steps: constructing an improved UNet model with expansion convolution, performing down-sampling through an encoder, performing up-sampling through a decoder, separating the encoder and the decoder through a single convolution layer, and connecting each down-sampling step to a corresponding up-sampling step; introducing the GAN network structure into the improved UNet model, and inputting the preprocessed data into the improved UNet model to train the improved UNet model so as to obtain an optimal improved UNet model; and after data preprocessing is performed on a brain CT image to be recognized, the brain CT image to be recognized is input to the optimal improved UNet model, and a recognition result is output. By applying the technical scheme of the invention, the problems of low accuracy, efficiency and reliability of hemorrhagic stroke detection in the prior art can be solved.

Images