A histopathological image classification method for cholangiocarcinoma based on spatial-channel feature fusion convolution neural network

Histopathological image analysis plays an important role in the diagnosis and treatment of cholangiocarcinoma. This time-consuming complex process is currently performed manually by pathologists. To reduce burden on pathologists, this paper proposes a histopathological classification method for cholangiocarcinoma based spatial-channel feature fusion convolutional neural networks. Specifically, proposed model consists spatial branch channel branch. In branch, residual structural blocks are used to extract deep features. multi-scale extraction module some multi-level modules designed features order increase representational ability model. The experimental results Multidimensional Choledoch Database show that performs better than other classical CNN methods.