arXiv:2601. 08127v2 Announce Type: replace-cross Abstract: Expert-annotated training data remains the critical bottleneck for AI in histopathology, particularly for rare pathologies where even dozens of cases may be unavailable.
By Mohamad Koohi-Moghadam, Mohammad-Ali Nikouei Mahani, Rex K. H. Au-Yeung, Raymond Yu O, Monalyn Marabi, Piyapharom Intarawichian, Fabian Z. X. Lean, Andrew Ferguson, Kyongtae Tyler Bae
arXiv:2601.17228v2 Announce Type: replace
Abstract: Deep learning models in computational pathology often fail to generalize across cohorts and institutions due to domain shift. Existing approaches e...
By Tengyue Zhang, Ruiwen Ding, Luoting Zhuang, Yuxiao Wu, Erika F. Rodriguez, William Hsu
The paper introduces Interpretable Utility Similarity (IUS), a novel metric for quantifying how closely a synthetic image set matches a real image set in terms of usefulness for deep‑learning clinical decision support systems. IUS is interpretable, leveraging generalized neural additive models to explain why one synthetic dataset may outperform another based on clinically relevant image features. Experiments on color medical imaging modalities—endoscopic, dermoscopic, and fundus—show that selecting synthetic images with high IUS can boost classification performance by up to 54.6%, and the method also generalizes to grayscale X‑ray and ultrasound data.
By Panagiota Gatoula, George Dimas, Dimitris K. Iakovidis
The paper introduces "Destroy Me", a hybrid framework that generates realistic histopathology artifacts using Stable Diffusion and physics‑based modeling to create six common artifact types. Artifact realism is evaluated with KID and color Wasserstein metrics, and models trained on these augmented images outperform baselines on lung adenocarcinoma classification, achieving a 10.5% relative boost in macro F1‑score and a 15% increase in Cohen’s Kappa. The study highlights that selective, impact‑weighted augmentation is essential for enhancing robustness while preserving subtle diagnostic features.
By Zuzanna Krawczyk-Borysiak, Adam Krawczyk, Mateusz Miller, Gabriela Kaczmarek, S{\l}awomir Paku{\l}o, Ma{\l}gorzata Sok\'o{\l}, \.Zaneta Swiderska-Chadaj
The paper presents a systematic evaluation of six unsupervised image‑to‑image generative models for virtual Sirius Red staining of mouse liver tissue from routine H&E slides. It benchmarks these models across 54 scaling configurations on a newly released paired H&E‑to‑SR dataset, assessing perceptual, distributional, and task‑specific performance, and further trains the best models into deep ensembles to quantify epistemic uncertainty. The study finds that GAN‑based and diffusion‑based methods differ markedly across these metrics, indicating that reliable virtual staining requires reporting and selecting on all three axes simultaneously.
By Qasim Siddiqui, Adrian Friebel, Maiju Myllys, Zaynab Hobloss, Daniela Gonzalez, Ahmed Ghallab, Stefan Hoehme
The paper introduces an unsupervised approach to medical image segmentation by training a Denoising Diffusion Probabilistic Model (DDPM) on 21 unlabeled abdominal CT scans to learn anatomical features. The encoder weights from the DDPM are transferred to a U‑Net for downstream segmentation on the BTCV multi‑organ dataset, resulting in a significant Dice score improvement for liver segmentation from 0.75 to 0.93. In low‑data regimes, diffusion‑pretrained models retain robust performance, achieving high Dice scores even with only 10% of labeled data.
By Akshat G, Divyansh Gupta, Shaleen Bhatnagar, Shilpa Ankalaki, Tusar Kanti Mishra