Semi-Supervised Domain Adaptation with Latent Diffusion for Pathology Image Classification
This work addresses domain generalization issues in computational pathology, which is crucial for deploying models across different medical institutions, though it appears incremental as it builds on existing diffusion and domain adaptation methods.
The paper tackled the problem of domain shift in computational pathology by proposing a semi-supervised domain adaptation framework using latent diffusion models to generate synthetic images that preserve tissue structure while adapting to target-domain appearance, resulting in improved F1 scores from 0.611 to 0.706 on a target cohort for lung adenocarcinoma prognostication.
Deep learning models in computational pathology often fail to generalize across cohorts and institutions due to domain shift. Existing approaches either fail to leverage unlabeled data from the target domain or rely on image-to-image translation, which can distort tissue structures and compromise model accuracy. In this work, we propose a semi-supervised domain adaptation (SSDA) framework that utilizes a latent diffusion model trained on unlabeled data from both the source and target domains to generate morphology-preserving and target-aware synthetic images. By conditioning the diffusion model on foundation model features, cohort identity, and tissue preparation method, we preserve tissue structure in the source domain while introducing target-domain appearance characteristics. The target-aware synthetic images, combined with real, labeled images from the source cohort, are subsequently used to train a downstream classifier, which is then tested on the target cohort. The effectiveness of the proposed SSDA framework is demonstrated on the task of lung adenocarcinoma prognostication. The proposed augmentation yielded substantially better performance on the held-out test set from the target cohort, without degrading source-cohort performance. The approach improved the weighted F1 score on the target-cohort held-out test set from 0.611 to 0.706 and the macro F1 score from 0.641 to 0.716. Our results demonstrate that target-aware diffusion-based synthetic data augmentation provides a promising and effective approach for improving domain generalization in computational pathology.