Hierarchical Optimal Transport for Comparing Histopathology Datasets
This work addresses the challenge of data scarcity in histopathology for cancer research, offering a principled method to assess dataset similarity, though it is incremental as it builds on existing optimal transport concepts.
The paper tackles the problem of measuring similarity between histopathology datasets to improve transfer learning, proposing a hierarchical optimal transport distance that outperforms a baseline in cancer-type prediction and predicts transferability difficulty in tumor vs. normal prediction.
Scarcity of labeled histopathology data limits the applicability of deep learning methods to under-profiled cancer types and labels. Transfer learning allows researchers to overcome the limitations of small datasets by pre-training machine learning models on larger datasets similar to the small target dataset. However, similarity between datasets is often determined heuristically. In this paper, we propose a principled notion of distance between histopathology datasets based on a hierarchical generalization of optimal transport distances. Our method does not require any training, is agnostic to model type, and preserves much of the hierarchical structure in histopathology datasets imposed by tiling. We apply our method to H&E stained slides from The Cancer Genome Atlas from six different cancer types. We show that our method outperforms a baseline distance in a cancer-type prediction task. Our results also show that our optimal transport distance predicts difficulty of transferability in a tumor vs.normal prediction setting.