The paper evaluates how well generalist and dermatology-specific machine learning models perform on diverse skin lesion datasets, including dermoscopic images and smartphone photographs. It benchmarks a range of architectures—general-purpose vision-language models, foundation models, and task-specific dermatology classifiers—under conditions of distribution shift, modality change, and demographic variability. The study quantifies the performance gap between current state‑of‑the‑art models and the robustness needed for safe, equitable clinical deployment.
By Emanoel dos Santos, Kelvin Cunha, Rodrigo Mota, Fabio Papais, Thales Bezerra, Natalia Lopes, Erico Medeiros, Shirley Cruz, Jessica Araujo, Paulo Borba, Tsang Ing Ren
The paper introduces the Semantic Tri-view Pipeline, an interpretable system that automatically screens teledermatology photographs for gradability by analyzing epidermal micro-relief across up to three smartphone views. It uses a lightweight DeepLabV3+ model to segment micro-relief fidelity and aggregates the resulting spatial masks with logistic regression, leveraging viewpoint redundancy to improve robustness. Evaluated on the SCIN dataset, the approach raises the AUC from 0.81 to 0.96 on optically clear cases, offering real‑time, privacy‑by‑design feedback to filter ungradable photo sets before clinician review.
By Robert Engel
arXiv:2606. 06224v1 Announce Type: cross Abstract: Explanations of multiple instance learning (MIL) models are widely used for validation and discovery in digital histopathology.
By Yanqing Luo (Berlin Institute for the Foundations of Learning and Data, Berlin, Germany, Machine Learning Group, Technische Universit\"at Berlin, Berlin, Germany), Julius Hense (Berlin Institute for the Foundations of Learning and Data, Berlin, Germany, Machine Learning Group, Technische Universit\"at Berlin, Berlin, Germany), Niklas Preni{\ss}l (Institute of Pathology, Charit\'e Universit\"atsmedizin, Berlin, Germany, Berlin Institute of Health at Charit\'e -- Universit\"atsmedizin Berlin, BIH Biomedical Innovation Academy, BIH Charit\'e Digital Clinician Scientist Program, Berlin, Germany), Andreas Mock (Institute of Pathology, Ludwig Maximilian University of Munich, Munich, Germany, Division of Translational Medical Oncology, DKFZ, Heidelberg, Germany, NCT Heidelberg, Heidelberg, Germany, German Cancer Consortium), Klaus-Robert M\"uller (Berlin Institute for the Foundations of Learning and Data, Berlin, Germany, Machine Learning Group, Technische Universit\"at Berlin, Berlin, Germany, Department of Artificial Intelligence, Korea University, Seoul, Korea, Max-Planck Institute for Informatics, Saarbr\"ucken, Germany), Thomas Schnake (Department of Chemistry, Chemical Physics Theory Group, University of Toronto, Canada, Vector Institute for Artificial Intelligence, Toronto, Canada, Acceleration Consortium, University of Toronto, Canada), Mina Jamshidi Idaji (Berlin Institute for the Foundations of Learning and Data, Berlin, Germany, Machine Learning Group, Technische Universit\"at Berlin, Berlin, Germany)
arXiv:2608. 14657v1 Announce Type: new Abstract: Early identification of lung cancer risk is critical for timely intervention, yet existing prediction models are limited by their reliance on single data modalities and their inability to leverage structured clinical knowledge.
By Chunlei Yang, Shuyan Li, Zhong Cao
The paper presents an optimal‑transport based generative model that learns the distributional differences between healthy and diseased patients, producing per‑patient counterfactuals and label‑free attribution heatmaps. On tabular breast cancer data the model achieves high malignancy scoring (AUROC ≈ 0.91) and its attributions correlate moderately with a supervised classifier, yet it does not surpass logistic regression. In chest X‑ray experiments the transport heatmaps capture population‑level signals but fail to localize real lesions, revealing a synthetic‑to‑real gap that challenges the reliability of label‑free explanations.
By Lalit Kumar
The study examines why dermatology AI models, largely trained on light‑skinned, cancer‑focused images, perform poorly when applied to diverse patient populations. By comparing a cancer‑trained baseline, two dermatology foundation models, and a general‑purpose vision model on tone‑stratified and disease‑shifted datasets, the authors find that disease‑distribution shift, rather than skin‑tone underrepresentation, is the primary cause of generalization failure. Representation analysis shows that cancer‑specialized features lack transferable structure, while dermatology‑pretrained features maintain stronger clustering, and lightweight adaptation with about ten labeled examples per category can recover most performance.
By Nirajan Kunwor, Sanjaya Poudel, Quoc-Huy Trinh, Jahidul Arafat, Sunil Kumar Gaire
arXiv:2610.08086v1 Announce Type: new
Abstract: The clinical integration of AI systems in digital dermatology relies heavily on human trust. Clinically interpretable visual concepts can act as interm...
By Linda Wermelinger, Simone Lionetti, Fabian Gr\"oger, Nipun Ranasekara, Philippe Gottfrois, Ludovic Amruthalingam, Labelling Consortium, Marc Pouly, Alexander A. Navarini
OpenMTB‑Audit is an open‑source benchmark that tests large language models on 500 synthetic non‑small cell lung cancer cases, covering five adversarial error categories and four safety labels: Supported, Partially Supported, Unsupported, and Insufficient Information. The study found that all eight tested LLMs over‑refused Partially Supported recommendations, collapsing labels to achieve high safety scores. A deterministic seven‑module framework, MTB‑AuditAgent, was introduced to reduce over‑refusal to 6.7% and reach 91.2% accuracy, while an oncologist annotation study highlighted disagreement around the boundary between information sufficiency and treatment optimization.
By Negin Ashrafi, Jia Luo, Stacey M. Frumm, Roxana Daneshjou
Background/Objectives: Dermoscopic skin lesion classifiers often lose accuracy under domain shift across imaging devices, illumination, and capture artifacts. We study how data augmentation improves the robustness of a binary malignant-versus-non-malignant classifier, with emphasis on out-of-domain (OOD) generalization.
RACR-MIL is a weakly‑supervised method for grading squamous cell carcinoma (SCC) from whole‑slide images, using an attention‑based multiple‑instance learning framework. It introduces a hybrid WSI graph to capture local tissue context and non‑local phenotypic dependencies, and applies rank‑ordering constraints on attention to prioritize higher‑grade tumor regions, mirroring pathologists’ diagnostic reasoning. The approach achieves state‑of‑the‑art performance, improving SCC grading accuracy by 3–9% over existing methods and up to 10% in tumor localization, and a pilot study showed pathologists reported increased grading efficiency in 60% of cases.
By Anirudh Choudhary, Mosbah Aouad, Krishnakant Saboo, Angelina Hwang, Jacob Kechter, Blake Bordeaux, Puneet Bhullar, David DiCaudo, Steven Nelson, Nneka Comfere, Emma Johnson, Olayemi Sokumbi, Jason Sluzevich, Leah Swanson, Dennis Murphree, Aaron Mangold, Ravishankar Iyer
arXiv:2607. 26765v1 Announce Type: cross Abstract: Background/Objectives: Dermoscopic skin lesion classifiers often lose accuracy under domain shift across imaging devices, illumination, and capture artifacts.
By Alexander Kozachok, Ilya Latyshev, Evgeny Karpulevich, Elena Kozachok, Egor Ushakov, Oleg Samovarov
arXiv:2609.38705v1 Announce Type: new
Abstract: Foundation models for computational pathology are usually evaluated using AUC and accuracy, while calibration is often left untested. This matters beca...
By Wenjun Liu, Saeed Hassanpour