215 citations · 1k across the 75 of their papers we have counts for
78 papers
Single-Pass Decision Scores Enable Rapid Classification with Adjustable Thresholds in Medical Multimodal Large Language Models
Patrick Wienholt, Frederik Hauke, Christiane Kuhl +3
Multimodal large language models (MLLMs) answer binary clinical questions with a yes or no token, leaving the decision threshold implicit and fixed. We derive a continuous score fr…
Listening for Airway Stenosis: A Foundation Model-Based Method for Rapid and Accessible Detection
Jean Groeninger, Zihao Zhao, Juliana de Castilhos +2
Airway stenosis can cause severe respiratory complications, yet its detection often relies on specialized examinations and medical imaging. This study explores the potential of aco…
FRAME: Separating sampling variation from performance disparities in medical image analysis
Mahshad Lotfinia, Daniel Truhn, Andreas Maier +1
Fairness audits of medical imaging models commonly report the largest performance difference between demographic subgroups and treat any positive value as evidence of bias. Yet a p…
Auditable CT Phenotyping Through Report-derived Radiological Observations
Riga Wu, Walter Witschey, Yicheng Li +9
Medical image foundation models can predict clinical phenotypes from computed tomography (CT), but strong performance leaves open whether they read disease-specific findings or sho…
CANDOR: Chance-Calibrated Neighborhood Discordance in Frozen Encoders for Medical Imaging
Soroosh Tayebi Arasteh, Sven Nebelung, Daniel Truhn
A foundation encoder is pretrained once on a large image corpus and then reused with its weights frozen. Each new task is solved by training a small head on the features it produce…
Foundation-model-guided radiogenomic discovery linking cancer genomes to cancer scans
Frederik Hauke, Jeremias Krause, Patrick Wienholt +6
The function of many genes is still unknown, and conventional driver-discovery methods, which rely on how frequently a gene is mutated, cannot assess genes that are only rarely aff…
Bayesian uncertainty estimation improves clinical decision making in medical AI agents
Frederik Hauke, Patrick Wienholt, Christiane Kuhl +4
Machine learning models for medical image analysis typically lack a reliable measure of confidence, limiting their use in ambiguous or atypical cases. Here we show that Monte Carlo…
Medical foundation models converge less under label supervision
Soroosh Tayebi Arasteh, Sebastian Ziegelmayer, Mahshad Lotfinia +4
Diagnostic classifiers and imaging biomarkers are fitted on the embeddings of medical foundation models. These models are replaced as new versions appear. This practice assumes tha…
Vision-language models for chest radiography do not always need the image
Mahshad Lotfinia, Sebastian Ziegelmayer, Lisa Adams +4
Vision-language models that answer questions about chest radiographs are evaluated by their accuracy on labels derived from radiology reports. High benchmark accuracy is often inte…
Cross-modal linkage risk in clinical vision-language models
Soroosh Tayebi Arasteh, Mahshad Lotfinia, Sven Nebelung +1
Vision-language models (VLMs) trained on paired chest radiographs and radiology reports learn a shared embedding space that can preserve instance-level image-report correspondence.…
From Clinical Intent to Clinical Model: Autonomous Coding-Agents for Clinician-driven AI Development
Zihao Zhao, Frederik Hauke, Juliana De Castilhos +4
Developing AI models that are useful in clinical practice, requires efficient collaboration between clinicians and AI developers. This poses a practical challenge: clinicians must…
Safety and accuracy follow different scaling laws in clinical large language models
Sebastian Wind, Tri-Thien Nguyen, Jeta Sopa +9
Clinical LLMs are often scaled by increasing model size, context length, retrieval complexity, or inference-time compute, with the implicit expectation that higher accuracy implies…
Differential privacy representation geometry for medical image analysis
Soroosh Tayebi Arasteh, Marziyeh Mohammadi, Sven Nebelung +1
Differential privacy (DP)'s effect in medical imaging is typically evaluated only through end-to-end performance, leaving the mechanism of privacy-induced utility loss unclear. We…
Case-Grounded Evidence Verification: A Framework for Constructing Evidence-Sensitive Supervision
Soroosh Tayebi Arasteh, Mehdi Joodaki, Mahshad Lotfinia +2
Evidence-grounded reasoning requires more than attaching retrieved text to a prediction: a model should make decisions that depend on whether the provided evidence supports the tar…
Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering
Mina Farajiamiri, Jeta Sopa, Saba Afza +9
Agentic retrieval-augmented reasoning pipelines are increasingly used to structure how large language models (LLMs) incorporate external evidence in clinical decision support. Thes…
Can Agents Distinguish Visually Hard-to-Separate Diseases in a Zero-Shot Setting? A Pilot Study
Zihao Zhao, Frederik Hauke, Juliana De Castilhos +2
The rapid progress of multimodal large language models (MLLMs) has led to increasing interest in agent-based systems. While most prior work in medical imaging concentrates on autom…
The pretraining domain outweighs the training objective in setting the privacy-utility trade-off of differentially private medical image analysis
Soroosh Tayebi Arasteh, Mina Farajiamiri, Mahshad Lotfinia +7
Differential privacy limits how much each training image can influence a medical imaging model but lowers its diagnostic accuracy. Pretrained weights reduce this loss. It is unknow…
Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbations
Johannes Moll, Markus Graf, Tristan Lemke +7
Vision-language models (VLMs) often produce chain-of-thought (CoT) explanations that sound plausible yet fail to reflect the underlying decision process, undermining trust in high-…
Effect of Reporting Mode and Clinical Experience on Radiologists' Gaze and Image Analysis Behavior in Chest Radiography
Mahta Khoobi, Marc Sebastian von der Stueck, Felix Barajas Ordonez +11
Structured reporting (SR) and artificial intelligence (AI) may transform how radiologists interact with imaging studies. This prospective study (July to December 2024) evaluated th…
Agentic Systems in Radiology: Design, Applications, Evaluation, and Challenges
Christian Bluethgen, Dave Van Veen, Daniel Truhn +8
Building agents, systems that perceive and act upon their environment with a degree of autonomy, has long been a focus of AI research. This pursuit has recently become vastly more…
Large Language Model-Based Uncertainty-Adjusted Label Extraction for Artificial Intelligence Model Development in Upper Extremity Radiography
Hanna Kreutzer, Anne-Sophie Caselitz, Thomas Dratsch +4
Objectives: To evaluate GPT-4o's ability to extract diagnostic labels (with uncertainty) from free-text radiology reports and to test how these labels affect multi-label image clas…
Hallucination Filtering in Radiology Vision-Language Models Using Discrete Semantic Entropy
Patrick Wienholt, Sophie Caselitz, Robert Siepmann +6
To determine whether using discrete semantic entropy (DSE) to reject questions likely to generate hallucinations can improve the accuracy of black-box vision-language models (VLMs)…
Resolution scaling governs DINOv3 transfer performance in chest radiograph classification
Soroosh Tayebi Arasteh, Mina Shaigan, Christiane Kuhl +3
Self-supervised learning (SSL) has improved visual representation learning, but its value in chest radiography remains uncertain. DINOv3 extends earlier SSL models through Gram-anc…
MedicalPatchNet: A Patch-Based Self-Explainable AI Architecture for Chest X-ray Classification
Patrick Wienholt, Christiane Kuhl, Jakob Nikolas Kather +2
Deep neural networks excel in radiological image classification but frequently suffer from poor interpretability, limiting clinical acceptance. We present MedicalPatchNet, an inher…