Data-efficient and weakly supervised computational pathology on whole-slide images

Abstract

Deep-learning methods for computational pathology typically suffer from poor domain adaptation, interpretability or visualization, and require either manual annotation of gigapixel whole slide images (WSIs) or large datasets of WSIs with slide-level labels. Here, we report an interpretable weakly supervised deep-learning method for data-efficient WSI processing that only requires slide-level labels. The method, which we named clustering-constrained-attention multiple-instance learning (CLAM), uses attention-based learning to identify subregions of high diagnostic value to accurately classify whole slides, and instance-level clustering over the identified representative regions to constrain and refine the feature space. By applying CLAM to the subtyping of renal cell carcinoma and of non-small-cell lung cancer and to the detection of lymph-node metastasis, we show that it can be used to localize well-known morphological features on WSIs without the need for spatial labels, that it overperforms standard weakly supervised classification methods, and that it is adaptable to independent test cohorts, to smartphone microscopy and to varying tissue content.