Reducing manual workload in CT and MRI annotation with the Segment Anything Model 2

Download PDF
Open Webpage

Leo Misera, Sven Nebelung, Zunamys I. Carrero, Keno K. Bressem, Marta Ligero, Jens-Peter Kühn, Ralf-Thorsten Hoffmann, Daniel Truhn, Jakob Nikolas Kather

Published: 2026, Last Modified: 15 Apr 2026BMC Medical Imaging 2026EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Volumetric segmentation in CT and MRI is valuable for artificial intelligence workflows in radiology, yet creating the large, precisely annotated datasets required for training segmentation models remains laborious.