Classifying Pathological Images Based on Multi-Instance Learning and End-to-End Attention Pooling

In order to address the issue that previous deep learning methods for classifying pathological images cannot adaptively learn features, we proposed an end-to-end attention pooling method based on a multi-instance learning patch scoring model. This method integrates feature extraction and classification into a unified framework that is conducive to extracting the most valuable features. In this model, a patch scoring method is constructed by a multi-instance learning method firstly and then the partial patches selected by the patches scoring model are classified using an end-to-end classification model that incorporates an attention pooled mechanism. To make the pathological image classification mechanism more compatible with the pathologist diagnosis method, we used the squared average normalization function instead of the softmax function to optimize the feature extraction and fusion process, so that the high score patches in positive pathological images receive more attention weights, thus giving better interpretability to the classification results. Experiments on publicly available datasets TCGA_BRCA show a significant improvement in the performance of this approach over other work.