SAM2CT

Zenodo (CERN European Organization for Nuclear Research) 2026 Dataset Open access

Read full text
Authors: Samuel Church
DOI: 10.5281/zenodo.18394859
Cited by: 0

Abstract

SAM2CT is a fine-tuned version of SAM2 used for segmenting 3D structures in CT. SAM2CT can interpret standard SAM2 prompt types (i.e., point, bounding box, mask) as well as lines and arrows. During CT reporting, radiologists often create line or arrow annotations. These are stored in PACS systems as GSPS objects. SAM2CT is designed to convert those annotations into 3D masks.

Fields of Study & Subjects

Medical Image Segmentation Techniques Artificial Intelligence in Healthcare and Education Medical Imaging and Analysis

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
27 January 2026
Document type
Dataset