5 papers
Metadata Supervised MRI Representations for Modelling and Controlling Acquisition Variability
Mehmet Yigit Avci, Pedro Borges, Virginia Fernandez +5
Magnetic resonance imaging exhibits substantial acquisition variability, where identical anatomy can appear markedly different across scanners and imaging protocols. Consequently,…
DIST-CLIP: Arbitrary Metadata and Image Guided MRI Harmonization via Disentangled Anatomy-Contrast Representations
Mehmet Yigit Avci, Pedro Borges, Virginia Fernandez +4
Deep learning holds immense promise for transforming medical image analysis, yet its clinical generalization remains profoundly limited. A major barrier is data heterogeneity. This…
Metadata-Aligned 3D MRI Representations for Contrast Understanding and Quality Control
Mehmet Yigit Avci, Pedro Borges, Virginia Fernandez +4
Magnetic Resonance Imaging suffers from substantial data heterogeneity and the absence of standardized contrast labels across scanners, protocols, and institutions, which severely…
MR-CLIP: Efficient Metadata-Guided Learning of MRI Contrast Representations
Mehmet Yigit Avci, Pedro Borges, Paul Wright +3
Accurate interpretation of Magnetic Resonance Imaging scans in clinical systems is based on a precise understanding of image contrast. This contrast is primarily governed by acquis…
Differentially Private Active Learning: Balancing Effective Data Selection and Privacy
Kristian Schwethelm, Johannes Kaiser, Jonas Kuntzer +3
Active learning (AL) is a widely used technique for optimizing data labeling in machine learning by iteratively selecting, labeling, and training on the most informative data. Howe…