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

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.

Saved in:

Bibliographic Details
Main Authors:	Misera, Leo (Author) , Nebelung, Sven (Author) , Carrero, Zunamys I. (Author) , Bressem, Keno (Author) , Ligero, Marta (Author) , Kühn, Jens-Peter (Author) , Hoffmann, Ralf-Thorsten (Author) , Truhn, Daniel (Author) , Kather, Jakob Nikolas (Author)
Format:	Article (Journal)
Language:	English
Published:	2026
In:	BMC medical imaging Year: 2026, Volume: 26, Pages: 1-12
ISSN:	1471-2342
DOI:	10.1186/s12880-025-02075-4
Online Access:	Verlag, kostenfrei, Volltext: https://doi.org/10.1186/s12880-025-02075-4
Author Notes:	Leo Misera, Sven Nebelung, Zunamys I. Carrero, Keno Bressem, Marta Ligero, Jens-Peter Kühn, Ralf-Thorsten Hoffmann, Daniel Truhn and Jakob Nikolas Kather

Description
Summary:	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.
Item Description:	Online veröffentlicht: 8. Januar 2026 Gesehen am 27.05.2026
Physical Description:	Online Resource
ISSN:	1471-2342
DOI:	10.1186/s12880-025-02075-4