NV-Segment-CT
CT segmentation built from MONAI VISTA3D: 117 structures automatically, or 132 promptable by point or class. Research use only, not for clinical care. Needs a CUDA GPU; weights are about 872 MB
- What it is
- Segmentation (Segmentation & frameworks)
- Modality
- Radiology: CT
- Maintainer
- NVIDIA
- License
- Apache-2.0 (code); NVIDIA Open Model License (weights)
- Commercial use
- Verify
- Access
- Free, public source repository (see links below)
- Last update
- 2026-10-05 (last repository push, UTC; Maintained)
- Last checked
- 2026-11-16
- Limitations
- Listed for research and development reference. Hounsfield Lab has not tested its clinical performance; check the project’s own documentation for intended use and regulatory status.
Links
License review: Hugging Face LICENSE applies Apache-2.0 to every file except the weights. Weights (model.pt is 872 MB) are under the NVIDIA Open Model License, which says the models are commercially usable; it is a custom license, not an OSI license (https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/, last modified October 24, 2025). The model card limits use to research and says it is not for clinical use. Inference expects a CUDA GPU (Ampere or Hopper). NV-Segment-CTMR is a different, non-commercial model and is not this listing.
Commercial use: read the project’s license (and any model-weight terms) yourself before relying on it. This isn’t legal advice.
Related tools in Segmentation & frameworks
- MONAI: PyTorch-based AI toolkit for healthcare imaging
- MONAI Label: AI-assisted image labeling and active learning; integrates with 3D Slicer and OHIF
- nnU-Net: Self-configuring segmentation framework
- TotalSegmentator: Segments more than 100 anatomical structures in CT and MR
- TotalSpineSeg: Two-stage nnU-Net tool that segments and individually labels every vertebra and intervertebral disc plus the spinal cord and canal, using an odd/even vertebra scheme and landmark discs (C2-C3, C7-T1, T12-L1, L5-S) to avoid fused or split vertebrae; works on localizers and short-FOV scans; peer-reviewed in European Radiology (Nov 7, 2026)
- CXAS: Chest X-ray anatomy segmentation (Mask2Former models: 187 frontal and 177 lateral classes) plus 132 named landmarks and landmark-based measurements such as cardiothoracic ratio, costophrenic angle, Cobb angle and the Haller index, in mm for DICOM input; cxas_idc writes one multi-segment DICOM SEG and a TID 1500 SR per radiograph; trained on PAXRay++ CT-projected radiographs
Related public imaging datasets
- AMOS (abdominal multi-organ segmentation): CT, MR, Body · CC BY 4.0
- C4KC-KiTS: CT, Body · CC BY 3.0
- Colorectal-Liver-Metastases: CT, Body · CC BY 4.0
- CT Colonography: CT, Body · CC BY 3.0 and CC BY 4.0 (see the file table)
- CT-ORG: CT, Body · CC BY 3.0
- FDG-PET-CT-Lesions (autoPET): PT, CT, Nuclear medicine · CC BY 4.0 (defaced images and clinical CSV); NIH Controlled Data Access Policy (original images)
Browse all DICOM datasets with license and access details.