Skip to content

CHAOS: abdominal CT and MR (T1 in/out-phase, T2 SPIR) as DICOM series, 40 patients

pl.load("chaos_abdomen") loads this dataset. The Combined Healthy Abdominal Organ Segmentation challenge training set: 20 CT and 20 MR patients as anonymised DICOM series, read series by series out of the 890 MB zip on Zenodo (HTTP Range; a series is fetched as a folder of .dcm files). Ground-truth masks are PNG slice stacks in the same archive (folders Ground/) and are not mapped here. Sample ids are set/case (CT/1, MR/1 are different patients).

import pardesline as pl

ds = pl.load("chaos_abdomen")
print(ds.describe())  # roles, frames, units, labels, licence, citation
s = ds[0]
obj = s.ct  # fetched now, cached under ~/.cache/pardesline/datasets/chaos_abdomen

Provenance and licence
Source remote archive read by HTTP Range: https://zenodo.org/records/3431873/files/CHAOS_Train_Sets.zip
Scheme archive
Size of the whole source 891 MB
Licence CC-BY-NC-SA-4.0
Commercial use not allowed (non-commercial licence)
Redistribution allowed
Licence note CC BY-NC-SA 4.0 on the Zenodo record (checked 2026-10-14): non-commercial, share-alike.
Terms https://zenodo.org/records/3431873
Homepage https://chaos.grand-challenge.org/
Cite Kavur A.E., Gezer N.S., Baris M., et al. CHAOS Challenge - combined (CT-MR) healthy abdominal organ segmentation. Med Image Anal 69:101950, 2021.
Samples grouped by case

Roles (what each sample contains)

Role Type Frame Units Labels / layout Pattern or file
ct volume (CT) from the file header from the file header Train_Sets/{set}/{case}/DICOM_anon/*.dcm
Abdominal CT, DICOM series (set CT)
mr_t1_inphase volume (MR) from the file header from the file header Train_Sets/{set}/{case}/T1DUAL/DICOM_anon/InPhase/*.dcm
T1-DUAL in-phase, DICOM series (set MR)
mr_t1_outphase volume (MR) from the file header from the file header Train_Sets/{set}/{case}/T1DUAL/DICOM_anon/OutPhase/*.dcm
T1-DUAL out-of-phase, DICOM series (set MR)
mr_t2_spir volume (MR) from the file header from the file header Train_Sets/{set}/{case}/T2SPIR/DICOM_anon/*.dcm
T2-SPIR, DICOM series (set MR)

Standardized layout

Files are fetched on first access into the dataset cache and stay in their original format; ds.export(folder) writes every sample as standard files (PLY for points and meshes, MetaImage for volumes and label maps) with a .pardesline.json sidecar carrying frame, units, labels, licence and provenance, plus a manifest for the folder. Label maps become exact surfaces with to_mesh(label=k), DICOM series become one volume, raw arrays are decoded through the layout above.

ds = pl.load("chaos_abdomen").take(2)
ds.export("./standardized")        # PLY / MetaImage + sidecars + manifest.json

Algorithms and models that run on it

Generated from src/pardesline/data/manifests/chaos_abdomen.json on 2026-10-14.