Interpretable learning for rare disease classification in computational hematology
This research line addresses automated analysis of hematological disorders from microscopic blood images, where rare diseases, limited annotations, and cross-site variability challenge conventional deep learning approaches.
Abstract
This research line addresses automated analysis of hematological disorders from microscopic blood images, where rare diseases, limited annotations, and cross-site variability challenge conventional deep learning approaches. Using multi-center microscopy datasets covering several rare anemia subtypes, we developed interpretable and data-efficient learning methods, including anomaly-aware multiple instance learning and unsupervised cross-domain feature extraction. The proposed approaches achieved improved generalization and instance-level interpretability compared to supervised and attention-based baselines.
Perspective
Initiated during my appointment at Helmholtz Munich and continued after transitioning to the University of Bonn, this collaboration established a durable national research partnership and contributed to doctoral training. The methodological insights continue to inform ongoing work on robust and weakly supervised learning for rare diseases.
