Default 117 anatomical structures across organs, vessels, bones, and muscles.
TotalSegmentator CT
TotalSegmentator CT does whole-body CT segmentation: one AI task outlines 117 structures, from organs, muscles and blood vessels to each vertebra and rib. Other tasks look closer at one region, such as the head and neck, the lungs, the liver or the spine.
Run this model →
Use TotalSegmentator CT in your browser: it runs in the cloud. No coding, no installation.
You upload
CT scan
You get
Outlined structures
Tasks
24
Cost per million voxels
€0.007–0.01
Is it right for your scan?
Intended use
Outlining anatomy on CT scans for research: measuring organs and other structures across groups of patients, or a first draft that you then correct by hand.
Known limitations
Less accurate on scans with severe disease, after surgery, with metal implants, of children, with an unusual field of view, or taken at low dose or with very thin slices. Small structures are the least reliable.
Available tasks (24)
Whole body
Body outline and extremity / skin segmentation.
Body cavity structures and pericardium.
Head & neck
Head glands, cavities, and eye structures.
Mastication and head muscles.
Head/neck bones, larynx, thyroid cartilage, and major vessels.
Neck and throat muscles.
Eye muscles and related orbital structures.
Skull, jaw, teeth, and sinus cavities.
Comprehensive dental structures including individual teeth with FDI numbering.
Cerebral ventricle subdivisions.
Intracerebral hemorrhage segmentation (research).
Chest
Pulmonary vasculature and airway structures.
Lung tissue and nodule segmentation.
Pleural and pericardial fluid segmentation.
Breast tissue segmentation.
Abdomen
Couinaud liver segment classification.
Hepatic vasculature and tumor structures.
Hepatic lesion segmentation.
Improved kidney cyst segmentation.
Trunk and abdominal wall muscles (T4–L4 range).
Spine & pelvis
Vertebral bodies C1–L5 with one label per vertebra.
Vertebral bodies C1–L5 with one label per vertebra, refined with the vertebrae_body model for sharper borders. More accurate contours than vertebrae_pp at a longer runtime (runs two models).
Hip implant segmentation.
After the AI task
Correct the result in your browser, then measure each structure and follow it across your study. See what is measured
Research details
Built by
Jakob Wasserthal and colleagues, University Hospital Basel, Switzerland. Nalvera.AI runs their published model and is independent of the authors.
Version
2.18.0 · Apache-2.0 · released 23 Aug 2026
Training data
Trained on 1,228 CT studies (TotalSegmentator v2 dataset, Wasserthal et al. 2023) spanning diverse scanners, contrast phases, and pathologies; annotations semi-automatically generated and expert-reviewed. Predominantly adult human anatomy.
Citations & references
- TotalSegmentator source code (GitHub)
- Wasserthal J, et al. TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images. Radiology: Artificial Intelligence, 2023
- Free preprint of the same paper (arXiv)
Questions about TotalSegmentator
Do I need to install TotalSegmentator or have a GPU?
No. Each AI task runs on GPU servers in the EU, and you upload scans in your browser. To run TotalSegmentator on your own computer instead, the authors' open-source code works on Windows, Mac and Ubuntu, with or without a GPU (slower without).
Can I upload DICOM, and what do I get back?
Upload a DICOM folder or a .nii.gz file. Each AI task returns one NIfTI label map (.nii.gz) in which every structure has its own number; the model reference gives the name for each number.
How do I get organ volumes from TotalSegmentator?
Run the AI task from a study. Nalvera.AI then measures each structure in your browser and lists its volume and Hounsfield values in one table you can copy as CSV.
How is this different from the authors' web app?
The authors' web app at totalsegmentator.com takes one scan at a time, and uploading there means accepting its terms: the data can be used to improve the model and shared with other parties or the public in anonymized form. Under Nalvera.AI's privacy policy, uploads are used only to deliver your results, unless you opt a task into research and model training. Nalvera.AI takes multiple scans per submission, lets you correct outlines in your browser and records each task's model version. Nalvera.AI's Study Design groups scans by patient, measures each structure's volume, intensity and functional PET and SPECT parameters, tracks them over time, compares patient groups and exports reports.
Does it work on MRI?
Yes, with its own version, TotalSegmentator MRI, which outlines 50 structures.
Other models
Nalvera iSegCT / MRI · Interactive segmentationNalvera’s in-house model for interactive CT and MRI segmentation. Define the structures you need and refine their outlines directly in your browser.MAISI-v2CT / MRI · GenerationGenerate synthetic CT or brain MRI images without an input scan. Choose the image size and anatomy for research dataset creation.MerlinCT · Report generation · AnalysisExplore abdominal CT scans through generated research reports and predicted findings. Includes tasks for estimating five-year disease risk.MOOSE CTCT · SegmentationFocused CT segmentation for heart chambers, lung lobes, muscles, and other anatomical regions.MRSegmentatorMRI / CT · SegmentationSegment 40 organs, vessels, bones, and muscles from the chest to the hips on MRI or CT, with a body composition task for fat and abdominal muscles on MRI.MuscleMap MRIMRI · SegmentationSegment muscles and bones on whole-body MRI scans across different MRI contrasts, with coverage from the neck through the trunk to the legs.NV-Reason-CTCT · Report generationWrite structured chest or abdominal CT reports, or a step-by-step reasoning walkthrough that states its observations and uncertainty.NV-Segment-CTCT · (Interactive) SegmentationNVIDIA’s CT segmentation model: 117 organs, bones, vessels, and muscles in one pass, plus tasks for the airway and the liver vessels.TotalSegmentator MRIMRI · SegmentationSegment organs, bones, vessels, and muscles on MRI scans. Choose whole-body segmentation or dedicated tasks for the body, spine, or liver.
Citing Nalvera.AI
Please cite the platform alongside the model's own paper.
@misc{nalvera,
title = {Nalvera.AI: a cloud platform for medical-imaging AI},
author = {{van der Heyden, Brent}},
year = {2026},
howpublished = {\url{https://nalvera.ai}},
note = {Model: TotalSegmentator CT v2.18.0. Accessed YYYY-MM-DD}
}Research use only — not a medical device. Outputs are not
validated for clinical diagnosis or treatment.