Overview

Schema Version

https://atlas.rsna.org/schemas/2025-11/dataset.json

Name

TotalSegmentator training dataset

Link

https://pubs.rsna.org/doi/full/10.1148/ryai.230024

Indexing

Keywords: TotalSegmentator, segmentation, CT, nn-UNet, 104 structures, organs, bones, muscles, vessels

Content: CH, CT, GI, GU, HN, MK, NR, OI, VA

RadLex: RID15779, RID40190, RID34861, RID10782, RID4, RID12362, RID49469, RID13205

Author(s)

Wasserthal J

Breit HC

Meyer MT

Comments

Publicly released fully segmented CT training dataset used to develop TotalSegmentator, which segments 104 anatomic structures.

Date

Published: 2023-01-01

References

[1] Wasserthal J, Breit HC, Meyer MT, et al.. "TotalSegmentator: robust segmentation of 104 anatomic structures in CT images". Radiol Artif Intell. 2023-01-01. doi:10.1148/ryai.230024.

Dataset

Motivation

Create a large dataset of CT scans with full segmentation of 104 structures to enable accurate automated segmentation and support AI/radiomics research; released publicly with the model and code.

Missing information

Counts of sites, patients, exams, and file formats are not stated in the source article.