Transfer Learning from Nucleus Detection to Classification in Histopathology Images

Despite significant recent success, modern computer vision techniques such as Convolutional Neural Networks (CNNs) are expensive to apply to cell-level prediction problems in histopathology images due to difficulties in providing celllevel supervision. This work explores the transferability of features learned by an object detection CNN (Faster R-CNN) to nucleus classification in histopathology images. We detect nuclei in these images using class-agnostic models trained on small annotated patches, and use the CNN representations of detected nuclei to cluster and classify them. We show that with a small training dataset, the proposed pipeline can achieve superior nucleus classification performance, and generalizes well to unseen stain types.