Dataset with segmentations of 117 important anatomical structures in 1939 CT images

Info: This is version 3 of the TotalSegmentator dataset.

In 1939 CT images we segmented 117 anatomical structures covering a majority of relevant classes for most use cases. The CT images were randomly sampled from clinical routine, thus representing a real world dataset which generalizes to clinical application. The dataset contains a wide range of different pathologies, scanners, sequences and institutions.

Link to a copy of this dataset on Dropbox for much quicker download: Dropbox Link

A small subset of this dataset with only 102 subjects for quick download+exploration can be found here: here

You can find a segmentation model trained on this dataset here.

More details about the dataset can be found in the corresponding paper (the paper describes v1 of the dataset). Please cite this paper if you use the dataset.

This dataset was created by the department of Research and Analysis at University Hospital Basel.

UPDATE: On 2023-10-27 we uploaded version 2.0.1 which fixes broken files.

UPDATE: On 2026-09-10 we uploaded version 3.0.0 which increases the number of images from 1228 to 1939.  We added 291 pediatric CT images to improve the segmentation performance on children. Moreover, we greatly improved the label quality: We fixed many small errors in the segmentations, we refined the labels especially for bones structures (e.g. femur segmentations a lot more precise now), and we fixed the vertebrae label mixups.