Learning from Thresholds: Fully Automated Classification of Tumor Infiltrating Lymphocytes for Multiple Cancer Types
This work addresses the need for efficient and scalable digital pathology analysis for cancer diagnosis, though it is incremental as it builds on existing thresholding methods.
The paper tackles the problem of automating Tumor Infiltrating Lymphocyte (TIL) classification in H&E images across multiple cancer types by proposing a semi-automated annotation method that uses thresholded results as large-scale training data, resulting in better TIL prediction in 12 cancer types compared to prior human-in-the-loop approaches.
Deep learning classifiers for characterization of whole slide tissue morphology require large volumes of annotated data to learn variations across different tissue and cancer types. As is well known, manual generation of digital pathology training data is time consuming and expensive. In this paper, we propose a semi-automated method for annotating a group of similar instances at once, instead of collecting only per-instance manual annotations. This allows for a much larger training set, that reflects visual variability across multiple cancer types and thus training of a single network which can be automatically applied to each cancer type without human adjustment. We apply our method to the important task of classifying Tumor Infiltrating Lymphocytes (TILs) in H&E images. Prior approaches were trained for individual cancer types, with smaller training sets and human-in-the-loop threshold adjustment. We utilize these thresholded results as large scale "semi-automatic" annotations. Combined with existing manual annotations, our trained deep networks are able to automatically produce better TIL prediction results in 12 cancer types, compared to the human-in-the-loop approach.