TotalSegmentator MRI dataset v1.0.0: 298 MRI volumes with 56 anatomical structures¶
pl.load("totalsegmentator_mri") loads this dataset. 298 MRI examinations (various sequences and regions) with 56 structures segmented as one binary mask per structure. Read subject by subject out of the 2.4 GB zip on Zenodo by HTTP Range.
import pardesline as pl
ds = pl.load("totalsegmentator_mri")
print(ds.describe()) # roles, frames, units, labels, licence, citation
s = ds[0]
obj = s.mri # fetched now, cached under ~/.cache/pardesline/datasets/totalsegmentator_mri
Provenance and licence¶
| Source | remote archive read by HTTP Range: https://zenodo.org/records/11367005/files/TotalsegmentatorMRI_dataset_v100.zip |
| Scheme | archive |
| Size of the whole source | 2.3 GB |
| Licence | CC-BY-NC-SA-2.0 |
| Commercial use | not allowed (non-commercial licence) |
| Redistribution | allowed |
| Licence note | CC BY-NC-SA 2.0 on the Zenodo record (checked 2026-10-14): non-commercial, share-alike. |
| Terms | https://zenodo.org/records/11367005 |
| Homepage | https://github.com/wasserth/TotalSegmentator |
| Cite | D'Antonoli T.A., Berger L.K., Indrakanti A.K., et al. TotalSegmentator MRI: Sequence-Independent Segmentation of 59 Anatomical Structures in MR images. Radiology 314(2), 2025. |
| Samples grouped by | id |
Roles (what each sample contains)¶
| Role | Type | Frame | Units | Labels / layout | Pattern or file |
|---|---|---|---|---|---|
mri |
volume (MR) | from the file header | from the file header | {id}/mri.nii.gzMRI image (NIfTI, LPS mm from the header) |
|
adrenal_gland_left |
labels | from the file header | from the file header | 1=adrenal_gland_left | {id}/segmentations/adrenal_gland_left.nii.gz |
adrenal_gland_right |
labels | from the file header | from the file header | 1=adrenal_gland_right | {id}/segmentations/adrenal_gland_right.nii.gz |
aorta |
labels | from the file header | from the file header | 1=aorta | {id}/segmentations/aorta.nii.gz |
autochthon_left |
labels | from the file header | from the file header | 1=autochthon_left | {id}/segmentations/autochthon_left.nii.gz |
autochthon_right |
labels | from the file header | from the file header | 1=autochthon_right | {id}/segmentations/autochthon_right.nii.gz |
brain |
labels | from the file header | from the file header | 1=brain | {id}/segmentations/brain.nii.gz |
colon |
labels | from the file header | from the file header | 1=colon | {id}/segmentations/colon.nii.gz |
duodenum |
labels | from the file header | from the file header | 1=duodenum | {id}/segmentations/duodenum.nii.gz |
esophagus |
labels | from the file header | from the file header | 1=esophagus | {id}/segmentations/esophagus.nii.gz |
femur_left |
labels | from the file header | from the file header | 1=femur_left | {id}/segmentations/femur_left.nii.gz |
femur_right |
labels | from the file header | from the file header | 1=femur_right | {id}/segmentations/femur_right.nii.gz |
fibula |
labels | from the file header | from the file header | 1=fibula | {id}/segmentations/fibula.nii.gz |
gallbladder |
labels | from the file header | from the file header | 1=gallbladder | {id}/segmentations/gallbladder.nii.gz |
gluteus_maximus_left |
labels | from the file header | from the file header | 1=gluteus_maximus_left | {id}/segmentations/gluteus_maximus_left.nii.gz |
gluteus_maximus_right |
labels | from the file header | from the file header | 1=gluteus_maximus_right | {id}/segmentations/gluteus_maximus_right.nii.gz |
gluteus_medius_left |
labels | from the file header | from the file header | 1=gluteus_medius_left | {id}/segmentations/gluteus_medius_left.nii.gz |
gluteus_medius_right |
labels | from the file header | from the file header | 1=gluteus_medius_right | {id}/segmentations/gluteus_medius_right.nii.gz |
gluteus_minimus_left |
labels | from the file header | from the file header | 1=gluteus_minimus_left | {id}/segmentations/gluteus_minimus_left.nii.gz |
gluteus_minimus_right |
labels | from the file header | from the file header | 1=gluteus_minimus_right | {id}/segmentations/gluteus_minimus_right.nii.gz |
heart |
labels | from the file header | from the file header | 1=heart | {id}/segmentations/heart.nii.gz |
hip_left |
labels | from the file header | from the file header | 1=hip_left | {id}/segmentations/hip_left.nii.gz |
hip_right |
labels | from the file header | from the file header | 1=hip_right | {id}/segmentations/hip_right.nii.gz |
humerus_left |
labels | from the file header | from the file header | 1=humerus_left | {id}/segmentations/humerus_left.nii.gz |
humerus_right |
labels | from the file header | from the file header | 1=humerus_right | {id}/segmentations/humerus_right.nii.gz |
iliac_artery_left |
labels | from the file header | from the file header | 1=iliac_artery_left | {id}/segmentations/iliac_artery_left.nii.gz |
iliac_artery_right |
labels | from the file header | from the file header | 1=iliac_artery_right | {id}/segmentations/iliac_artery_right.nii.gz |
iliac_vena_left |
labels | from the file header | from the file header | 1=iliac_vena_left | {id}/segmentations/iliac_vena_left.nii.gz |
iliac_vena_right |
labels | from the file header | from the file header | 1=iliac_vena_right | {id}/segmentations/iliac_vena_right.nii.gz |
iliopsoas_left |
labels | from the file header | from the file header | 1=iliopsoas_left | {id}/segmentations/iliopsoas_left.nii.gz |
iliopsoas_right |
labels | from the file header | from the file header | 1=iliopsoas_right | {id}/segmentations/iliopsoas_right.nii.gz |
inferior_vena_cava |
labels | from the file header | from the file header | 1=inferior_vena_cava | {id}/segmentations/inferior_vena_cava.nii.gz |
intervertebral_discs |
labels | from the file header | from the file header | 1=intervertebral_discs | {id}/segmentations/intervertebral_discs.nii.gz |
kidney_left |
labels | from the file header | from the file header | 1=kidney_left | {id}/segmentations/kidney_left.nii.gz |
kidney_right |
labels | from the file header | from the file header | 1=kidney_right | {id}/segmentations/kidney_right.nii.gz |
liver |
labels | from the file header | from the file header | 1=liver | {id}/segmentations/liver.nii.gz |
lung_left |
labels | from the file header | from the file header | 1=lung_left | {id}/segmentations/lung_left.nii.gz |
lung_right |
labels | from the file header | from the file header | 1=lung_right | {id}/segmentations/lung_right.nii.gz |
pancreas |
labels | from the file header | from the file header | 1=pancreas | {id}/segmentations/pancreas.nii.gz |
portal_vein_and_splenic_vein |
labels | from the file header | from the file header | 1=portal_vein_and_splenic_vein | {id}/segmentations/portal_vein_and_splenic_vein.nii.gz |
prostate |
labels | from the file header | from the file header | 1=prostate | {id}/segmentations/prostate.nii.gz |
quadriceps_femoris_left |
labels | from the file header | from the file header | 1=quadriceps_femoris_left | {id}/segmentations/quadriceps_femoris_left.nii.gz |
quadriceps_femoris_right |
labels | from the file header | from the file header | 1=quadriceps_femoris_right | {id}/segmentations/quadriceps_femoris_right.nii.gz |
sacrum |
labels | from the file header | from the file header | 1=sacrum | {id}/segmentations/sacrum.nii.gz |
sartorius_left |
labels | from the file header | from the file header | 1=sartorius_left | {id}/segmentations/sartorius_left.nii.gz |
sartorius_right |
labels | from the file header | from the file header | 1=sartorius_right | {id}/segmentations/sartorius_right.nii.gz |
small_bowel |
labels | from the file header | from the file header | 1=small_bowel | {id}/segmentations/small_bowel.nii.gz |
spinal_cord |
labels | from the file header | from the file header | 1=spinal_cord | {id}/segmentations/spinal_cord.nii.gz |
spleen |
labels | from the file header | from the file header | 1=spleen | {id}/segmentations/spleen.nii.gz |
stomach |
labels | from the file header | from the file header | 1=stomach | {id}/segmentations/stomach.nii.gz |
thigh_medial_compartment_left |
labels | from the file header | from the file header | 1=thigh_medial_compartment_left | {id}/segmentations/thigh_medial_compartment_left.nii.gz |
thigh_medial_compartment_right |
labels | from the file header | from the file header | 1=thigh_medial_compartment_right | {id}/segmentations/thigh_medial_compartment_right.nii.gz |
thigh_posterior_compartment_left |
labels | from the file header | from the file header | 1=thigh_posterior_compartment_left | {id}/segmentations/thigh_posterior_compartment_left.nii.gz |
thigh_posterior_compartment_right |
labels | from the file header | from the file header | 1=thigh_posterior_compartment_right | {id}/segmentations/thigh_posterior_compartment_right.nii.gz |
tibia |
labels | from the file header | from the file header | 1=tibia | {id}/segmentations/tibia.nii.gz |
urinary_bladder |
labels | from the file header | from the file header | 1=urinary_bladder | {id}/segmentations/urinary_bladder.nii.gz |
vertebrae |
labels | from the file header | from the file header | 1=vertebrae | {id}/segmentations/vertebrae.nii.gz |
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("totalsegmentator_mri").take(2)
ds.export("./standardized") # PLY / MetaImage + sidecars + manifest.json
Algorithms and models that run on it¶
- labels roles:
mask.to_mesh(label=k),mask.to_numpy(), metrics:dice,hd95(evaluation-metrics-3d) ; catalog modules:pyvista_volume_processing,simpleitk_registration,simpleitk_segmentation - volume roles:
volume.align(moving),volume.segment(lower, upper),volume.to_mesh(isovalue=...),volume.to_sitk(); catalog modules:pyvista_volume_processing,simpleitk_registration,simpleitk_segmentation - Supervised segmentation:
prepare_nnunet_dataset.pywrites this dataset in the nnU-Net v2 raw layout; PointNet trains on the label surfaces. - Self-supervised pretraining: 3D JEPA reads the volumes directly.
Related¶
- Datasets catalog · How to download a medical imaging dataset in Python · Add a dataset
- Tags:
medical,mri,segmentation,nifti,whole-body,totalsegmentator
Generated from src/pardesline/data/manifests/totalsegmentator_mri.json on 2026-10-14.