Leveraging Unlabeled Whole-Slide-Images for Mitosis Detection
This work addresses the time-consuming and subjective manual counting of mitoses for cancer prognosis, though it is incremental as it builds on existing semi-supervised techniques for a specific medical imaging task.
The paper tackles the problem of expensive expert annotations for automated mitosis detection in breast cancer whole-slide-images by proposing a semi-supervised method that leverages unlabeled data to mine additional samples, improving the F1-score by ~5% compared to fully-supervised models and achieving an F1-score of 0.64 on the TUPAC challenge.
Mitosis count is an important biomarker for prognosis of various cancers. At present, pathologists typically perform manual counting on a few selected regions of interest in breast whole-slide-images (WSIs) of patient biopsies. This task is very time-consuming, tedious and subjective. Automated mitosis detection methods have made great advances in recent years. However, these methods require exhaustive labeling of a large number of selected regions of interest. This task is very expensive because expert pathologists are needed for reliable and accurate annotations. In this paper, we present a semi-supervised mitosis detection method which is designed to leverage a large number of unlabeled breast cancer WSIs. As a result, our method capitalizes on the growing number of digitized histology images, without relying on exhaustive annotations, subsequently improving mitosis detection. Our method first learns a mitosis detector from labeled data, uses this detector to mine additional mitosis samples from unlabeled WSIs, and then trains the final model using this larger and diverse set of mitosis samples. The use of unlabeled data improves F1-score by $\sim$5\% compared to our best performing fully-supervised model on the TUPAC validation set. Our submission (single model) to TUPAC challenge ranks highly on the leaderboard with an F1-score of 0.64.