Self-Rule to Multi-Adapt: Generalized Multi-source Feature Learning Using Unsupervised Domain Adaptation for Colorectal Cancer Tissue Detection
This work addresses the challenge of domain shift in medical imaging for colorectal cancer detection, offering a solution that reduces reliance on fully-labeled datasets, though it is incremental in adapting existing self-supervised techniques to this domain.
The paper tackled the problem of limited labeled data in digital pathology by proposing Self-Rule to Multi-Adapt (SRMA), a method that uses self-supervised learning for unsupervised domain adaptation to transfer knowledge from few labeled source domains to a target domain without additional annotations, outperforming baselines in colorectal tissue type classification.
Supervised learning is constrained by the availability of labeled data, which are especially expensive to acquire in the field of digital pathology. Making use of open-source data for pre-training or using domain adaptation can be a way to overcome this issue. However, pre-trained networks often fail to generalize to new test domains that are not distributed identically due to tissue stainings, types, and textures variations. Additionally, current domain adaptation methods mainly rely on fully-labeled source datasets. In this work, we propose Self-Rule to Multi-Adapt (SRMA), which takes advantage of self-supervised learning to perform domain adaptation, and removes the necessity of fully-labeled source datasets. SRMA can effectively transfer the discriminative knowledge obtained from a few labeled source domain's data to a new target domain without requiring additional tissue annotations. Our method harnesses both domains' structures by capturing visual similarity with intra-domain and cross-domain self-supervision. Moreover, we present a generalized formulation of our approach that allows the framework to learn from multiple source domains. We show that our proposed method outperforms baselines for domain adaptation of colorectal tissue type classification \new{in single and multi-source settings}, and further validate our approach on an in-house clinical cohort. The code and trained models are available open-source: https://github.com/christianabbet/SRA.