Self-Rule to Adapt: Generalized Multi-source Feature Learning Using Unsupervised Domain Adaptation for Colorectal Cancer Tissue Detection

by   Christian Abbet, et al.

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 variations in tissue stainings, types, and textures. Additionally, current domain adaptation methods mainly rely on fully-labeled source datasets. In this work, we propose SRA, which takes advantage of self-supervised learning to perform domain adaptation and removes the necessity of a fully-labeled source dataset. SRA 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 architecture to learn from multi-source domains. We show that our proposed method outperforms baselines for domain adaptation of colorectal tissue type classification and further validate our approach on our in-house clinical cohort. The code and models are available open-source:


page 6

page 8

page 11

page 12

page 13

page 20

page 21


Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels

Existing unsupervised domain adaptation methods aim to transfer knowledg...

IMPaSh: A Novel Domain-shift Resistant Representation for Colorectal Cancer Tissue Classification

The appearance of histopathology images depends on tissue type, staining...

Adversarial Domain Adaptation for Classification of Prostate Histopathology Whole-Slide Images

Automatic and accurate Gleason grading of histopathology tissue slides i...

Source-Free Open-Set Domain Adaptation for Histopathological Images via Distilling Self-Supervised Vision Transformer

There is a strong incentive to develop computational pathology models to...

An Empirical Study on Measuring the Similarity of Sentential Arguments with Language Model Domain Adaptation

Measuring the similarity between two different sentential arguments is a...

Multi-scale Feature Alignment for Continual Learning of Unlabeled Domains

Methods for unsupervised domain adaptation (UDA) help to improve the per...

Abductive Reasoning as Self-Supervision for Common Sense Question Answering

Question answering has seen significant advances in recent times, especi...

Please sign up or login with your details

Forgot password? Click here to reset