RWTH Aachen University

Medical imaging foundation model unifying pathology and radiology, serving classification and segmentation on 2D, 3D and gigapixel inputs.

Nanobody CDR design framework that alternates structure prediction, docking, and CDR generation in an expectation-maximization refinement loop.

Radiology CT framework pairing lesion-driven contrastive slice embeddings with attention pooling to predict clinical endpoints without fine-tuning.

Missense pathogenicity prediction that folds wild-type and mutant sequences with ESMFold and encodes each structure as a graph autoencoder embedding.

Patient-level single-cell foundation model that condenses a donor's scRNA-seq profile into one 288-dimensional embedding for disease cohort search.

Histopathology tile encoder trained by supervised multi-task learning over 16 annotated tasks, matching self-supervised encoders on 6% of patches.

Multi-task pretrained biomedical imaging model whose frozen features match ImageNet fine-tuning on CT, X-ray and histology tasks from 1% of labels.