Photoacoustic device fingerprints induce bias in deep learning models

Abstract Deep learning (DL) models developed for established medical imaging modalities have shown increasing performance and reliability as a result of scaling efforts. In contrast, model development for emerging modalities such as photoacoustic imaging (PAI) remains challenged by data sparsity, wh...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Christoph J. Bender, Marcel Knopp, Niklas Holzwarth, Tom Rix, Jan-Hinrich Nölke, Kris K. Dreher, Yi Li, Julius Kempf, Milenko Caranovic, Fabian Schneider, Melanie Schellenberg, Leonie Boland, Briain Haney, Ferdinand Knieling, Ulrich Rother, Alexander Seitel, Lena Maier-Hein
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	Nature Portfolio 2026-06-01
Цуврал:	Scientific Reports
Нөхцлүүд:	Deep learning Photoacoustic Shortcut learning Bias Hardware confounder
Онлайн хандалт:	https://doi.org/10.1038/s41598-026-53468-6
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!