7 papers
Look What the Probes Dragged In! Real-World Chest X-ray Shortcuts in MedCLIP
Nikolette Pedersen, Regitze Sydendal, Veronika Cheplygina +1
Vision-language models, such as contrastive language-image pre-training (CLIP)-based approaches, have reached state-of-the-art (SOTA) results in medical artificial intelligence. Ho…
Robustness of transferability estimation metrics for medical imaging
Niclas Claßen, Théo Sourget, Dovile Juodelyte +2
In transfer learning, the choice of source model largely influences the performance on a target dataset. Still, selecting a fitting source remains a challenging task, especially in…
Dataset Diversity Metrics and Impact on Classification Models
Théo Sourget, Niclas ClaÃen, Jack Junchi Xu +2
The diversity of training datasets is usually perceived as an important aspect to obtain a robust model. However, the definition of diversity is often not defined or differs across…
Fairness and Robustness of CLIP-Based Models for Chest X-rays
Théo Sourget, David Restrepo, Céline Hudelot +3
Motivated by the strong performance of CLIP-based models in natural image-text domains, recent efforts have adapted these architectures to medical tasks, particularly in radiology,…
In the Picture: Medical Imaging Datasets, Artifacts, and their Living Review
Amelia Jiménez-Sánchez, Natalia-Rozalia Avlona, Sarah de Boer +26
Datasets play a critical role in medical imaging research, yet issues such as label quality, shortcuts, and metadata are often overlooked. This lack of attention may harm the gener…
Mask of truth: model sensitivity to unexpected regions of medical images
Théo Sourget, Michelle Hestbek-Møller, Amelia Jiménez-Sánchez +2
The development of larger models for medical image analysis has led to increased performance. However, it also affected our ability to explain and validate model decisions. Models…