9 papers
RadPRISM: Schema-stratified radiology-report supervision for concept-disentangled image representations and visual grounding
Fabian Drexel, Marlene Fritzsche, Era Stambollxhiu +15
Vision-language pretraining learns rich medical image representations from radiology reports, but previous model variants commonly operate within a single shared embedding space, s…
Self-supervision drives representational convergence in medical foundation models more than clinical supervision
Soroosh Tayebi Arasteh, Sebastian Ziegelmayer, Mahshad Lotfinia +4
Medical image encoders from different groups are increasingly treated as interchangeable, on the assumption that scale and clinical supervision concentrate their representations on…
Information-seeking failures of large language models in agentic clinical reasoning
Krischan Braitsch, Laura K. Schmalbrock, Theresa Weltermann +11
Large language models achieve high scores on medical knowledge assessments, yet clinical reasoning requires actively deciding what to investigate under uncertainty. We developed an…
Vision-language models for chest radiography do not always need the image
Mahshad Lotfinia, Sebastian Ziegelmayer, Lisa Adams +3
Medical vision-language models report strong chest radiograph accuracy, and this is increasingly read as evidence that they use the image. That inference is unsafe: a model exploit…
Routine laboratory trajectories encode the onset of organ-level complications in cancer
Jannik Lübberstedt, Krischan Braitsch, Jacqueline Lammert +21
Routine laboratory panels drawn during cancer treatment constitute longitudinal physiological recordings of organ function, yet their temporal structure is discarded by single-time…
Benchmarking Foundation Models for Renal Lesion Stratification in CT
Hartmut Häntze, Sarah de Boer, Myrthe Buser +7
The rapid proliferation of open-source medical foundation models (FMs) raises a practical question: how well do their pre-trained representations transfer to clinically relevant bu…