Jan 2026· IEEE journal of biomedical and health informatics· pp. 1-13· 0 citations· 52 references
MedicineComputer ScienceBiology
TL;DR
This work proposes 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.
Abstract
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.
This work presents MORSE (Morphological Observation with Reweighted Spectral Encoding), a minimal architecture that incorporates specific inductive biases by performing multi-scale morphological operations, adaptive gating of the spectrally decomposed signals, and memory-efficient hierarchical fusion, suggesting that d...
A. Darem, Sami F. Karali, Mohammed I. Thanoon et al.· Journal of Computers, Mechan...· 0 citations
Background Artificial intelligence (AI) models for mammography can achieve high diagnostic performance when training and test data originate from similar populations and imaging environments, but performance often deteriorates under cross-cohort domain shift. Differences in acquisition systems, image characteristics, p...
Automated melanoma detection from dermoscopic images remains a critical yet unresolved challenge due to substantial dataset heterogeneity, artifact contamination, and limited model generalization across clinical sources. Existing deep learning methods commonly rely on single-dataset training, single-backbone architectu...
Faysal Ahmmed, Resadus Salehin Rafsan, Muhtadi Mansib et al.· Photodiagnosis and Photodyna...· 0 citations
Prognostic assessment via whole-slide images (WSIs) is a key task in computational pathology. However, the development of robust predictive models is often bottlenecked by the scarcity of survival-annotated data, given the longitudinal nature of clinical follow-up. Despite its potential, semi-supervised learning (SSL)...
Yi Huang, Ling-Han Cai, Zi-Liang Feng et al.· Medical Image Analysis· 0 citations
Transfer learning from natural images is standard in supervised and increasingly adopted in self-supervised medical image analysis, but its role in generative modelling, and in particular diffusion denoisers, remains underexplored. Medical diffusion models typically train the denoiser from scratch, with no systematic e...
Efthymios Georgiou, Ioannis Kakogeorgiou, S. Brüningk· 0 citations
This paper addresses the domain shift problem commonly encountered in cross-center and cross-device deployment for binary dementia imaging classification, and proposes an unsupervised domain adaptation framework that jointly improves target-domain generalization and prediction reliability through uncertainty disturbanc...