{"architecture":{"family":"nnU-Net (3D U-Net)","input":"CT (NIfTI/DICOM), any field of view","output":"multi-label segmentation volume","params":"multiple 3D U-Nets","pretraining":"supervised on curated CT segmentations"},"article":null,"cancer_slugs":["pan-cancer"],"category":"radiology","confidence":"high","datasets":[],"developer":"University Hospital Basel","evaluation":[{"benchmark":"internal test set (v1 paper)","external":false,"metric":"Dice","source":"https://pubs.rsna.org/doi/10.1148/ryai.230024","value":"0.943 mean over 104 structures"}],"hf":null,"kind":"tool","license":"apache-2.0","limitations":"- Anatomy, not tumours: it does not segment lesions.\n- Reduced accuracy on very low-dose or heavily artefacted scans.","links":{"demo":null,"docs":null,"doi":"10.1148/ryai.230024","github":"https://github.com/wasserth/TotalSegmentator","huggingface":null,"paper":"https://pubs.rsna.org/doi/10.1148/ryai.230024","pmid":null},"modalities":["radiology-ct","radiology-mri"],"name":"TotalSegmentator","notable_uses":"","openness":"open-weights","regulatory":{"intended_use_en":"Research tool; not a medical device.","intended_use_pl":"Narz\u0119dzie badawcze; nie jest wyrobem medycznym.","source_url":"https://github.com/wasserth/TotalSegmentator","status":"research-only"},"regulatory_status":"research-only","release_date":"2023-07-05","run_snippet":"pip install TotalSegmentator\nTotalSegmentator -i ct.nii.gz -o segmentations/           # 117 structures (v2)\nTotalSegmentator -i ct.nii.gz -o seg/ --task body          # extra task models: body, lung_vessels, ...","settings":["treatment-planning","basic-research"],"slug":"totalsegmentator","sources":[{"label":"Wasserthal J et al. TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images. Radiology: AI 2023","url":"https://pubs.rsna.org/doi/10.1148/ryai.230024"},{"label":"GitHub \u2014 wasserth/TotalSegmentator","url":"https://github.com/wasserth/TotalSegmentator"}],"summary":"Command-line tool that segments 117 anatomical structures (v2) in any CT scan with nnU-Net models trained on more than 1,200 clinical CTs \u2014 the standard way to get organ masks for radiomics, dose planning and tumour-context features.","tasks":["segmentation"],"training":{"institutions":"University Hospital Basel (CH)","size":"1,204 CTs (v1)","summary_en":"1,204 CT examinations (v1) from routine clinical practice at University Hospital Basel, covering a wide range of pathologies, scanners and protocols; v2 extends the classes and data.","summary_pl":"1204 badania TK (v1) z rutynowej praktyki klinicznej Szpitala Uniwersyteckiego w Bazylei, obejmuj\u0105ce wiele patologii, skaner\u00f3w i protoko\u0142\u00f3w; v2 rozszerza klasy i dane."},"updated_at":"2026-09-05T22:26:01.552536","url":"/ai-oncology/models/totalsegmentator","usage":{"hardware":"GPU for full resolution; --fast mode runs on CPU","library":"pip package TotalSegmentator (nnU-Net)","snippet":"pip install TotalSegmentator\nTotalSegmentator -i ct.nii.gz -o segmentations/           # 117 structures (v2)\nTotalSegmentator -i ct.nii.gz -o seg/ --task body          # extra task models: body, lung_vessels, ..."},"verified_at":"2026-09-05T22:26:01.552100","verified_by":"editorial","version":"v2","what_it_does":"pip install and one command: organs, bones, vessels and muscles labelled voxel-wise; separate task models add vertebrae, lung lobes, body composition and more."}