FEATMAP: Targeted Correction of Acquisition Signatures Harmonizes Medical Foundation Model Embeddings and Enables Robust Task Generalization
Leonhard Donle, Michael Phillips, Farieda Gaber, Siddhi Ramesh, Matteo Sacco, Sampsa Hautaniemi, Anni Virtanen, Keno K. Bressem, Lisa C. Adams, Kelsey Goon, Elena Nevins, Ryan A. Robinett, Sara E. Kochanny, Sasha Hassan, James M. Dolezal, , Ernst Lengyel
FEATMAP corrects acquisition signatures in medical foundation model embeddings to improve cross-condition similarity and task generalization without retraining.
bioRxiv · Jul 8, 2026 · PreprintBioinformatics