Corrected hip bone segmentation for the TotalSegmentator small subset
Abstract
This dataset provides revised ground truth hip bone segmentation masks for eligible hips (N = 104) in the TotalSegmentator small subset. Masks were manually corrected by the authors based on original ground truth within the TotalSegmentator dataset. Revisions were made across the full hip bone volume, with the most substantial changes in the acetabulum and sacroiliac joint regions. Details about this dataset can be found in this validation study (link to come), where these corrected segmentations serve as the ground truth for evaluating a post-processing workflow for TotalSegmentator-generated acetabular segmentations.
Fields of Study & Subjects
Medical Imaging and Analysis
Medical Image Segmentation Techniques
Artificial Intelligence in Healthcare and Education
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 3 March 2026
- Language
- EN
- Document type
- Dataset