Multiple instance learning-based two-stage metric learning network for whole slide image classification

Cancer is one of the most common diseases around the world. For cancer diagnosis, pathological examination is the most effective method. But the heavy and time-consuming workflow has increased the workload of the pathologists. With the appearance of whole slide image (WSI) scanners, tissues on a glass slide can be saved as a high-definition digital image, which makes it possible to diagnose diseases with computer aid. However, the extreme size and the lack of pixel-level annotations of WSIs make machine learning face a great challenge in pathology image diagnosis. To solve this problem, we propose a metric learning-based two-stage MIL framework (TSMIL) for WSI classification, which combines two stages of supervised clustering and metric-based classification. The training samples (WSIs) are first clustered into different clusters based on their labels in supervised clustering. Then, based on the previous step, we propose four different strategies to measure the distance of the test samples to each class cluster to achieve the test samples classification: MaxS, AvgS, DenS and HybS. Our model is evaluated on three pathology datasets: TCGA-NSCLC, TCGA-RCC and HER2. The average AUC scores can be up to 0.9895 and 0.9988 over TCGA-NSCLC and TCGA-RCC, and 0.9265 on HER2, respectively. The results showed that compared with the state-of-the-art methods, our method outperformed. The excellent performance on different kinds of cancer datasets verifies the feasibility of our method as a general architecture.