novcor/CADS-dataset

---
license: other
license_name: cadsdataset
license_link: https://github.com/murong-xu/CADS
task_categories:
- image-segmentation
tags:
- medical
- ct
- segmentation
- image
- 3d
- whole-body
- anatomy
size_categories:
- 10K<n<100K
configs:
- config_name: 0001_visceral_gc
data_files:
- split: all
path: "0001_visceral_gc/0001_visceral_gc.csv"
- config_name: 0002_visceral_sc
data_files:
- split: all
path: "0002_visceral_sc/0002_visceral_sc.csv"
- config_name: 0003_kits21
data_files:
- split: all
path: "0003_kits21/0003_kits21.csv"
- config_name: 0004_lits
data_files:
- split: all
path: "0004_lits/0004_lits.csv"
- config_name: 0005_bcv_abdomen
data_files:
- split: all
path: "0005_bcv_abdomen/0005_bcv_abdomen.csv"
- config_name: 0006_bcv_cervix
data_files:
- split: all
path: "0006_bcv_cervix/0006_bcv_cervix.csv"
- config_name: 0007_chaos
data_files:
- split: all
path: "0007_chaos/0007_chaos.csv"
- config_name: 0008_ctorg
data_files:
- split: all
path: "0008_ctorg/0008_ctorg.csv"
- config_name: 0009_abdomenct1k
data_files:
- split: all
path: "0009_abdomenct1k/0009_abdomenct1k.csv"
- config_name: 0010_verse
data_files:
- split: all
path: "0010_verse/0010_verse.csv"
- config_name: 0011_exact
data_files:
- split: all
path: "0011_exact/0011_exact.csv"
- config_name: 0012_cad_pe
data_files:
- split: all
path: "0012_cad_pe/0012_cad_pe.csv"
- config_name: 0013_ribfrac
data_files:
- split: all
path: "0013_ribfrac/0013_ribfrac.csv"
- config_name: 0014_learn2reg
data_files:
- split: all
path: "0014_learn2reg/0014_learn2reg.csv"
- config_name: 0015_lndb
data_files:
- split: all
path: "0015_lndb/0015_lndb.csv"
- config_name: 0016_lidc
data_files:
- split: all
path: "0016_lidc/0016_lidc.csv"
- config_name: 0017_lola11
data_files:
- split: all
path: "0017_lola11/0017_lola11.csv"
- config_name: 0018_sliver07
data_files:
- split: all
path: "0018_sliver07/0018_sliver07.csv"
- config_name: 0019_tcia_ct_lymph_nodes
data_files:
- split: all
path: "0019_tcia_ct_lymph_nodes/0019_tcia_ct_lymph_nodes.csv"
- config_name: 0020_tcia_cptac_ccrcc
data_files:
- split: all
path: "0020_tcia_cptac_ccrcc/0020_tcia_cptac_ccrcc.csv"
- config_name: 0021_tcia_cptac_luad
data_files:
- split: all
path: "0021_tcia_cptac_luad/0021_tcia_cptac_luad.csv"
- config_name: 0022_tcia_ct_images_covid19
data_files:
- split: all
path: "0022_tcia_ct_images_covid19/0022_tcia_ct_images_covid19.csv"
- config_name: 0023_tcia_nsclc_radiomics
data_files:
- split: all
path: "0023_tcia_nsclc_radiomics/0023_tcia_nsclc_radiomics.csv"
- config_name: 0024_pancreas_ct
data_files:
- split: all
path: "0024_pancreas_ct/0024_pancreas_ct.csv"
- config_name: 0025_pancreatic_ct_cbct_seg
data_files:
- split: all
path: "0025_pancreatic_ct_cbct_seg/0025_pancreatic_ct_cbct_seg.csv"
- config_name: 0026_rider_lung_ct
data_files:
- split: all
path: "0026_rider_lung_ct/0026_rider_lung_ct.csv"
- config_name: 0027_tcia_tcga_kich
data_files:
- split: all
path: "0027_tcia_tcga_kich/0027_tcia_tcga_kich.csv"
- config_name: 0028_tcia_tcga_kirc
data_files:
- split: all
path: "0028_tcia_tcga_kirc/0028_tcia_tcga_kirc.csv"
- config_name: 0029_tcia_tcga_kirp
data_files:
- split: all
path: "0029_tcia_tcga_kirp/0029_tcia_tcga_kirp.csv"
- config_name: 0030_tcia_tcga_lihc
data_files:
- split: all
path: "0030_tcia_tcga_lihc/0030_tcia_tcga_lihc.csv"
- config_name: 0032_stoic2021
data_files:
- split: all
path: "0032_stoic2021/0032_stoic2021.csv"
- config_name: 0033_tcia_nlst
data_files:
- split: all
path: "0033_tcia_nlst/0033_tcia_nlst.csv"
- config_name: 0034_empire
data_files:
- split: all
path: "0034_empire/0034_empire.csv"
- config_name: 0037_totalsegmentator
data_files:
- split: all
path: "0037_totalsegmentator/0037_totalsegmentator.csv"
- config_name: 0038_amos
data_files:
- split: all
path: "0038_amos/0038_amos.csv"
- config_name: 0039_han_seg
data_files:
- split: all
path: "0039_han_seg/0039_han_seg.csv"
- config_name: 0040_saros
data_files:
- split: all
path: "0040_saros/0040_saros.csv"
- config_name: 0041_ctrate
data_files:
- split: all
path: "0041_ctrate/0041_ctrate.csv"
- config_name: 0042_new_brainct_1mm
data_files:
- split: all
path: "0042_new_brainct_1mm/0042_new_brainct_1mm.csv"
- config_name: 0043_new_ct_tri
data_files:
- split: all
path: "0043_new_ct_tri/0043_new_ct_tri.csv"
---

# CADS: A Comprehensive Anatomical Dataset and Segmentation for Whole-Body Anatomy in Computed Tomography

<img src="https://raw.githubusercontent.com/murong-xu/CADS/refs/heads/main/resources/images/whole-body-parts-visualization.png" width="90%">

## Overview
CADS is a robust, fully automated framework for segmenting 167 anatomical structures in Computed Tomography (CT), spanning from head to knee regions across diverse anatomical systems.

The framework consists of two main components:

1. **CADS-dataset**:
- 22,022 CT volumes with complete annotations for 167 anatomical structures.
- Most extensive whole-body CT dataset, exceeding current collections in both scale (18x more CT scans) and anatomical coverage (60% more distinct targets).
- Data collected from publicly available datasets and private hospital data, spanning 100+ imaging centers across 16 countries.
- Diverse coverage of clinical variability, protocols, and pathological conditions.
- Built through an automated pipeline with pseudo-labeling and unsupervised quality control.

2. **CADS-model**:
- An open-source model suite for automated whole-body segmentation.
- Performance validated on both public challenges and real-world hospital cohorts.
- Available as Python script run (this GitHub repo) for flexible command-line usage.
- Also available as a user-friendly 3D Slicer plugin with UI interface, simple installation and one-click inference.

<div style="background-color:#fffae6; padding:10px; border-radius:5px;">
This repository hosts the <strong>CADS-dataset</strong>, providing both original <strong>CT images</strong> and corresponding <strong>segmentation masks</strong> in their native spacing formats.
</div>

For more information on the dataset (data collection, labeling procedures, and model derivatives etc.), please refer to the [CADS paper preprint](https://arxiv.org/abs/2507.22953).

## Useful Links
- [📄 CADS Paper Preprint](https://arxiv.org/abs/2507.22953)
- [🤗 CADS-dataset](https://huggingface.co/datasets/mrmrx/CADS-dataset)
- [📦 CADS-model Weights](https://github.com/murong-xu/CADS/releases/tag/cads-model_v1.0.0)
- [🔧 CADS-model Codebase](https://github.com/murong-xu/CADS)
- [🛠 CADS-model 3D Slicer Plugin](https://github.com/murong-xu/SlicerCADSWholeBodyCTSeg)

<div style="background-color:#fffae6; padding:10px; border-radius:5px;">
<b>Update (2026-01-30):</b> Uploaded refinement of the CADS-dataset v1 segmentation for <code>spine</code> and <code>ribs</code>, available only for the <code>0037_totalsegmentator</code> dataset (see <a href="https://huggingface.co/datasets/mrmrx/CADS-dataset/tree/main/0037_totalsegmentator">details</a>). This refinement aims to: improve spine segmentation precision, correct vertebrae mislabeling in original TotalSegmentator dataset, and fix more missing costovertebral joint annotations. This update has partial coverage and does not apply to the full CADS-dataset. A dataset-wide update will be released at a later stage.
</div>

<div style="background-color:#fffae6; padding:10px; border-radius:5px;">
<b>Update (2025-10-04):</b> Fixed missing images and corrected affine/intensity errors in datasets <code>0010_verse</code>, <code>0041_ctrate</code>, and <code>0043_new_ct_tri</code>, see
<a href="https://huggingface.co/datasets/mrmrx/CADS-dataset/discussions/2">details for affected IDs</a>.
</div>

## Format

All images and segmentations are provided in NIfTI format, organized by data source.

The directory structure is as follows:
```plaintext
root/
├── dataset_name/
│ ├── images/ # Original CT volumes
│ ├── segmentations/ # Segmentation masks (indexing see [model labelmap](https://github.com/murong-xu/CADS/blob/main/resources/info/labelmap.md))
│ └── README.md # Dataset license, citation, and further details
```

## Important Notice
- We are **not the original owners of the CT images**, except for the [BrainCT-1mm](./0042_new_brainct_1mm/README_0042_new_brainct_1mm.md) and [CT-TRI](./0043_new_ct_tri/README_0043_new_ct_tri.md) datasets newly released in this project.
- Users should review the corresponding README.md file in each dataset subdirectory before using the data and decide whether to include or exclude that dataset based on their intended use.

## Dataset Sources Overview
The CADS-dataset comprises multiple publicly available and private-source datasets, each released under its own license.

The table below summarizes all included sources:

| Directory Name | Dataset Name | License | Number of CT Volumes | Details |
|---|---|---|---|---|
| 0001_visceral_gc | VISCERAL Gold Corpus | Customized license | 40 | [readme](./0001_visceral_gc/README_0001_visceral_gc.md) |
| 0002_visceral_sc | VISCERAL Silver Corpus | Customized license | 127 | [readme](./0002_visceral_sc/README_0002_visceral_sc.md) |
| 0003_kits21 | The Kidney and Kidney Tumor Segmentation Challenge （KiTS21） | CC BY-NC-SA 4.0 | 300 | [readme](./0003_kits21/README_0003_kits21.md) |
| 0004_lits | Liver Tumor Segmentation Benchmark (LiTS) | CC BY-NC-SA 4.0 | 201 | [readme](./0004_lits/README_0004_lits.md) |
| 0005_bcv_abdomen | MICCAI Multi-Atlas Labeling Beyond the Cranial Vault (Abdomen) | CC BY 4.0 | 50 | [readme](./0005_bcv_abdomen/README_0005_bcv_abdomen.md) |
| 0006_bcv_cervix | MICCAI Multi-Atlas Labeling Beyond the Cranial Vault (Cervix) | CC BY 4.0 | 50 | [readme](./0006_bcv_cervix/README_0006_bcv_cervix.md) |
| 0007_chaos | CHAOS – Combined (CT-MR) Healthy Abdominal Organ Segmentation Challenge (CT Subset) | CC BY-NC-SA 4.0 | 40 | [readme](./0007_chaos/README_0007_chaos.md) |
| 0008_ctorg | CT-ORG: Multiple Organ Segmentation in CT | CC BY 3.0 | 140 | [readme](./0008_ctorg/README_0008_ctorg.md) |
| 0009_abdomenct1k | AbdomenCT-1K | CC BY 4.0 | 1062 | [readme](./0009_abdomenct1k/README_0009_abdomenct1k.md) |
| 0010_verse | VerSe – Vertebrae Labelling and Segmentation Benchmark | CC BY-SA 4.0 | 374 | [readme](./0010_verse/README_0010_verse.md) |
| 0011_exact | EXACT'09 – Extraction of Airways from CT | Customized license | 40 | [readme](./0011_exact/README_0011_exact.md) |
| 0012_cad_pe | CAD-PE – Computer Aided Detection for Pulmonary Embolism Challenge | CC BY 4.0 | 40 | [readme](./0012_cad_pe/README_0012_cad_pe.md) |
| 0013_ribfrac | RibFrac Challenge Dataset | CC BY-NC 4.0 | 660 | [readme](./0013_ribfrac/README_0013_ribfrac.md) |
| 0014_learn2reg | Learn2Reg – Abdomen MR-CT (TCIA Subset) | CC BY 3.0 and TCIA Data Usage Policy | 16 | [readme](./0014_learn2reg/README_0014_learn2reg.md) |
| 0015_lndb | LNDb – Lung Nodule Database | CC BY-NC-ND 4.0 ⚠️| 294 | [readme](./0015_lndb/README_0015_lndb.md) <br> [](https://zenodo.org/records/7153205)|
| 0016_lidc | LIDC-IDRI – Lung Image Database Consortium and Image Database Resource Initiative | CC BY 3.0 | 997 | [readme](./0016_lidc/README_0016_lidc.md) |
| 0017_lola11 | LOLA11 (LObe and Lung Analysis 2011) | Customized license | 55 | [readme](./0017_lola11/README_0017_lola11.md) |
| 0018_sliver07 | SLIVER07 (Segmentation of the Liver 2007) | Customized license | 30 | [readme](./0018_sliver07/README_0018_sliver07.md) |
| 0019_tcia_ct_lymph_nodes | Lymph Node CT Dataset (NIH, TCIA) | CC BY 3.0 | 174 | [readme](./0019_tcia_ct_lymph_nodes/README_0019_tcia_ct_lymph_nodes.md) |
| 0020_tcia_cptac_ccrcc | CPTAC-CCRCC – Clear Cell Renal Cell Carcinoma | CC BY 3.0 | 258 | [readme](./0020_tcia_cptac_ccrcc/README_0020_tcia_cptac_ccrcc.md) |
| 0021_tcia_cptac_luad | CPTAC-LUAD – Clinical Proteomic Tumor Analysis Consortium Lung Adenocarcinoma Collection | CC BY 3.0 | 133 | [readme](./0021_tcia_cptac_luad/README_0021_tcia_cptac_luad.md) |
| 0022_tcia_ct_images_covid19 | CT Images in COVID-19 | CC BY 4.0 | 121 | [readme](./0022_tcia_ct_images_covid19/README_0022_tcia_ct_images_covid19.md) |
| 0023_tcia_nsclc_radiomics | NSCLC Radiogenomics | CC BY 3.0 | 131 | [readme](./0023_tcia_nsclc_radiomics/README_0023_tcia_nsclc_radiomics.md) |
| 0024_pancreas_ct | Pancreas-CT | CC BY 3.0 | 80 | [readme](./0024_pancreas_ct/README_0024_pancreas_ct.md) |
| 0025_pancreatic_ct_cbct_seg | Pancreatic CT-CBCT Segmentation | CC BY 4.0 | 93 | [readme](./0025_pancreatic_ct_cbct_seg/README_0025_pancreatic_ct_cbct_seg.md) |
| 0026_rider_lung_ct | RIDER Lung CT | CC BY 4.0 | 59 | [readme](./0026_rider_lung_ct/README_0026_rider_lung_ct.md) |
| 0027_tcia_tcga_kich | TCGA-KICH (Kidney Chromophobe) | CC BY 3.0 | 17 | [readme](./0027_tcia_tcga_kich/README_0027_tcia_tcga_kich.md) |
| 0028_tcia_tcga_kirc | TCGA-KIRC (Kidney Renal Clear Cell Carcinoma) | CC BY 3.0 | 398 | [readme](./0028_tcia_tcga_kirc/README_0028_tcia_tcga_kirc.md) |
| 0029_tcia_tcga_kirp | TCGA-KIRP (Kidney Renal Papillary Cell Carcinoma) | CC BY 3.0 | 19 | [readme](./0029_tcia_tcga_kirp/README_0029_tcia_tcga_kirp.md) |
| 0030_tcia_tcga_lihc | TCGA-LIHC (Liver Hepatocellular Carcinoma) | CC BY 3.0 | 242 | [readme](./0030_tcia_tcga_lihc/README_0030_tcia_tcga_lihc.md) |
| 0032_stoic2021 | STOIC (Study of Thoracic CT in COVID-19) | CC BY-NC 4.0 | 2000 | [readme](./0032_stoic2021/README_0032_stoic2021.md) |
| 0033_tcia_nlst | National Lung Screening Trial (NLST) | CC BY 4.0 | 7172 | [readme](./0033_tcia_nlst/README_0033_tcia_nlst.md) |
| 0034_empire | EMPIRE10 Challenge | Customized license | 60 | [readme](./0034_empire/README_0034_empire.md) |
| 0037_totalsegmentator | TotalSegmentator | CC BY 4.0 | 1203 | [readme](./0037_totalsegmentator/README_0037_totalsegmentator.md) |
| 0038_amos | AMOS (Multi-Modality Abdominal Multi-Organ Segmentation Challenge) | CC BY 4.0 | 200 | [readme](./0038_amos/README_0038_amos.md) |
| 0039_han_seg | HaN-Seg: The head and neck organ-at-risk CT & MR segmentation dataset | CC BY-NC-ND 4.0 ⚠️| 42 | [readme](./0039_han_seg/README_0039_han_seg.md) <br> [](https://zenodo.org/records/7442914)|
| 0040_saros | SAROS: A dataset for whole-body region and organ segmentation in CT imaging | Mix of CC BY 3.0, CC BY 4.0, and CC BY-NC 3.0 | 900 | [readme](./0040_saros/README_0040_saros.md) |
| 0041_ctrate | CT-RATE | CC BY-NC-SA 4.0 | 3134 | [readme](./0041_ctrate/README_0041_ctrate.md) |
| 0042_new_brainct_1mm | (Newly Released) BrainCT-1mm | CC BY 4.0 | 484 | [readme](./0042_new_brainct_1mm/README_0042_new_brainct_1mm.md) |
| 0043_new_ct_tri | (Newly Released) CT-TRI (Triphasic Contrast-Enhanced Abdominal CTs) | CC BY-NC-SA 4.0 | 586 | [readme](./0043_new_ct_tri/README_0043_new_ct_tri.md) |

## Citation
<img src="https://raw.githubusercontent.com/murong-xu/CADS/refs/heads/main/resources/images/logo.png" width="25%">

If you use any component of CADS (CADS-dataset, its curated segmentation masks, pretrained CADS-model, or the 3D Slicer extension), please cite:

```bibtex
@article{xu2025cads,
title={CADS: A Comprehensive Anatomical Dataset and Segmentation for Whole-Body Anatomy in Computed Tomography},
author={Xu, Murong and Amiranashvili, Tamaz and Navarro, Fernando and Fritsak, Maksym and Hamamci, Ibrahim Ethem and Shit, Suprosanna and Wittmann, Bastian and Er, Sezgin and Christ, Sebastian M. and de la Rosa, Ezequiel and Deseoe, Julian and Graf, Robert and Möller, Hendrik and Sekuboyina, Anjany and Peeken, Jan C. and Becker, Sven and Baldini, Giulia and Haubold, Johannes and Nensa, Felix and Hosch, René and Mirajkar, Nikhil and Khalid, Saad and Zachow, Stefan and Weber, Marc-André and Langs, Georg and Wasserthal, Jakob and Ozdemir, Mehmet Kemal and Fedorov, Andrey and Kikinis, Ron and Tanadini-Lang, Stephanie and Kirschke, Jan S. and Combs, Stephanie E. and Menze, Bjoern},
journal={arXiv preprint arXiv:2507.22953},
year={2025}
}
```