--- pipeline_tag: image-segmentation license: cc-by-4.0 tags: - medical - ct - body-composition - 3d-segmentation - nnunet - residual-encoder --- # BodyCompositionCT-ResEncM BodyCompositionCT-ResEncM is a 3D nnU-Net v2 model for segmenting native body-composition compartments and supporting anatomical structures in CT. This is a single-checkpoint ResEnc M model trained on the complete training set. For five-fold ResEnc L ensemble inference, see [BodyCompositionCT-ResEncL](https://huggingface.co/fhofmann/BodyCompositionCT-ResEncL). ## Model overview | Property | Value | | --- | --- | | Task | Mutually exclusive 3D semantic segmentation | | Input | One CT volume | | Architecture | nnU-Net v2, `3d_fullres`, ResEnc M | | Checkpoint | One `fold_all` model trained on all training cases | | Training set | 1,656 CT scans | | Native output | Background plus seven foreground labels | | License | CC BY 4.0 | ## Native output labels | ID | Label | Description | | ---: | --- | --- | | 0 | Background | | | 1 | Muscle | Muscle compartment | | 2 | Bone | Bone | | 3 | Subcutaneous | Subcutaneous compartment | | 4 | Abdominal | Abdominal compartment, with organs and larger vessels excluded | | 5 | Thoracic | Thoracic compartment, with organs and larger vessels excluded | | 6 | Heart | Heart | | 7 | Lungs | Lungs | Labels 1, 3, 4, and 5 denote anatomical compartments rather than final attenuation-defined tissue masks. The muscle compartment can contain inter- and intramuscular connective tissue, smaller vessels, and larger fat-attenuation regions. IMAT is not a separate model class; CT-visible IMAT can be derived downstream within label 1 using HU-thresholding. All downstream tissue measurements should state their HU range, cleanup rules, and source compartment. The machine-readable mapping is stored in [dataset.json](nnUNetTrainer__nnUNetResEncUNetMPlans__3d_fullres/dataset.json). ## Training data and target construction The training set contains 750 CT scans from [SAROS](https://doi.org/10.1038/s41597-024-03337-6) and 906 from the [TotalSegmentator v2 dataset](https://doi.org/10.5281/zenodo.10047292). Another 332 cases (150 SAROS and 182 TotalSegmentator) were reserved and were not used for training. Targets were constructed from dense [BOA](https://doi.org/10.1097/RLI.0000000000001040) Task542 body-region predictions, sparse expert-reviewed SAROS labels, and TotalSegmentator-derived anatomical masks. Reviewed SAROS labels replaced predictions on annotated slices. TotalSegmentator muscle, bone, lung, tracheal, body-trunk, organ, vessel, and neural masks supplied corrections and exclusions. HU-guided candidate selection, morphological cleanup, model-assisted completion, and manual review produced the final seven foreground labels. Only the open TotalSegmentator `total` and `body` tasks were used for target construction; the separately licensed `tissue_types` and `vertebrae_body` tasks were not used. Training logs, plans, a configuration snapshot, and the training progress plot are included with the model. ## Inference The model uses the standard nnU-Net v2 results layout. The commands below were tested with nnU-Net v2 2.5.2. Input files must be unwindowed CT NIfTI volumes containing Hounsfield-unit values and named `_0000.nii.gz`. Do not normalize or resample them manually; nnU-Net applies the preprocessing stored in the plans. For integration with preprocessing and downstream tissue derivation, see the [BodyComposition pipeline](https://github.com/fohofmann/BodyComposition). Set the nnU-Net results directory and download the model: ```bash export nnUNet_results="/path/to/nnUNet_results" hf download fhofmann/BodyCompositionCT-ResEncM \ --local-dir "${nnUNet_results}/Dataset611_Tissue" ``` Optionally verify the model artifacts: ```bash cd "${nnUNet_results}/Dataset611_Tissue" sha256sum -c MODEL_ARTIFACTS.sha256 ``` Run inference: ```bash nnUNetv2_predict \ -d Dataset611_Tissue \ -i INPUT_FOLDER \ -o OUTPUT_FOLDER \ -f all \ -tr nnUNetTrainer \ -c 3d_fullres \ -p nnUNetResEncUNetMPlans ``` No independent nnU-Net postprocessing configuration was selected for this `fold_all` model. HU-based tissue derivation remains a separate downstream step. The checkpoint is a serialized PyTorch artifact. Load it only from a trusted copy of this repository. ## Evaluation status The `fold_all` checkpoint was trained on all 1,656 training cases and therefore has no held-out training fold. Values in the training logs are optimization diagnostics, not independent performance estimates. ## Intended use and limitations The model is intended to provide compartment masks for research pipelines, including downstream body-composition measurements derived with CT attenuation thresholds. - It is not intended for diagnosis, treatment decisions, or stand-alone clinical measurement. - Training targets combine automated segmentations, deterministic corrections, and manual review; residual source-model and labeling errors can remain. - Performance may vary across populations, scanners, acquisition protocols, contrast phases, artifacts, implants, and uncommon anatomy. - The targets focus on the body trunk; extremity use is out of scope. - External validation is required for each intended population and measurement definition. ## License and attribution The trained weights, model documentation, metadata, and included training records are released under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/). Reuse requires appropriate credit, a link to the license, and an indication of changes. See [LICENSE](LICENSE) for the attribution format. Training source data, source annotations, upstream checkpoints, and third-party software are not redistributed and retain their original terms: | Upstream material | Role | Terms | | --- | --- | --- | | SAROS labels and split metadata | Sparse reviewed labels | CC BY 4.0 | | SAROS source CT scans | Training images | Collection-specific TCIA terms, including restricted, CC BY, and CC BY-NC collections | | BOA Task542 weights | Dense initial body-region predictions | MIT | | TotalSegmentator v2 dataset | Training CT scans and anatomical labels | CC BY 4.0 | | TotalSegmentator `total` and `body` tasks | Corrections and exclusions | Apache-2.0 | | nnU-Net v2 | Training framework and architecture | Apache-2.0 | See [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md) for source links and the complete provenance and license summary. ## References - Hofmann FO et al. *Validation of body composition parameters extracted via deep learning-based segmentation from routine computed tomographies.* Scientific Reports (2025). https://doi.org/10.1038/s41598-025-96238-6 - Haubold J et al. *SAROS: A dataset for whole-body region and organ segmentation in CT imaging.* Scientific Data (2024). https://doi.org/10.1038/s41597-024-03337-6 - Haubold J et al. *BOA: A CT-Based Body and Organ Analysis for Radiologists at the Point of Care.* Investigative Radiology (2023). https://doi.org/10.1097/RLI.0000000000001040 - Wasserthal J et al. *TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images.* Radiology: Artificial Intelligence (2023). https://doi.org/10.1148/ryai.230024 - Isensee F et al. *nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation.* Nature Methods (2021). https://doi.org/10.1038/s41592-020-01008-z - Isensee F et al. *nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation.* arXiv (2024). https://doi.org/10.48550/arXiv.2404.09556 Questions and feedback are welcome in the repository's [Community](https://huggingface.co/fhofmann/BodyCompositionCT-ResEncM/discussions) section.