Unsupervised Domain Adaptation with Contrastive Learning for OCT Segmentation
This addresses the challenge of adapting segmentation models to new medical imaging domains without labeled data, which is crucial for reliable diagnosis and treatment of eye diseases, representing a strong specific gain but not a broad paradigm shift.
The paper tackles the problem of domain adaptation for retinal fluid segmentation in 3D OCT images, where supervised models fail on images from different devices, and proposes a semi-supervised framework with contrastive learning that achieves a 13.8% higher Dice coefficient in the target domain compared to SimCLR and improves results by 5.4% Dice in the source domain.
Accurate segmentation of retinal fluids in 3D Optical Coherence Tomography images is key for diagnosis and personalized treatment of eye diseases. While deep learning has been successful at this task, trained supervised models often fail for images that do not resemble labeled examples, e.g. for images acquired using different devices. We hereby propose a novel semi-supervised learning framework for segmentation of volumetric images from new unlabeled domains. We jointly use supervised and contrastive learning, also introducing a contrastive pairing scheme that leverages similarity between nearby slices in 3D. In addition, we propose channel-wise aggregation as an alternative to conventional spatial-pooling aggregation for contrastive feature map projection. We evaluate our methods for domain adaptation from a (labeled) source domain to an (unlabeled) target domain, each containing images acquired with different acquisition devices. In the target domain, our method achieves a Dice coefficient 13.8% higher than SimCLR (a state-of-the-art contrastive framework), and leads to results comparable to an upper bound with supervised training in that domain. In the source domain, our model also improves the results by 5.4% Dice, by successfully leveraging information from many unlabeled images.