IDC QIN-SARCOMA: Sarcomas MRI (15 patients)

Provider
NCI Imaging Data Commons; QIN-SARCOMA contributors; tables and sample by Scigantic
License
Per series (series.parquet license_short_name): CC BY 4.0 2,168. Cite the source DOI(s) and the IDC.
Size
4 parquet tables plus 36 sample DICOM files (7 MB)
Records
15 patients, 38 studies, 2,168 series; 10.05 GB in IDC
Stored at
Amazon S3, s3://scigantic-idc-open/qin_sarcoma (us-east-1)
Access
Free and public. No account with the data provider is needed.
DOI
10.7937/k9/tcia.2016.fxl9sess
Category
Health & Biomedical
Source
https://portal.imaging.datacommons.cancer.gov/explore/filters/?collection_id=qin_sarcoma

About IDC QIN-SARCOMA: Sarcomas MRI (15 patients)

QIN-SARCOMA on the NCI Imaging Data Commons (IDC v25): 15 patients, 38 studies, 2,168 DICOM series, 10.05 GB. Cancer type: Sarcomas; location: breast, calf, chest, elbow, knee, leg, shoulder, thigh. Modalities: MR 2,168 series. This Scigantic archive is the collection's complete series-, study- and patient-level metadata as parquet (from idc-index, IDC v25), and a real sample of the images: one MR series, complete (7 MB, CC BY 4.0). Every series row carries its public S3 location (s3://idc-open-data/ /), so any series can be pulled on demand with anonymous boto3; the collection itself is not copied. License: CC BY 4.0 (2,168 series). IDC's description: Longitudinal dynamic contrast-enhanced (DCE) MRI of 15 patients with soft-tissue sarcoma, acquired at Oregon Health & Science University to assess response to preoperative chemoradiation. Patients were imaged at up to three time points: before treatment, after the first cycle of chemotherapy, and after about 8 more weeks of chemoradiation, before surgery. Formerly limited-access, the collection was made public by TCIA in April 2026. Please see the QIN-SARCOMA (https://doi.org/10.7937/k9/tcia.2016.fxl9sess) page to learn more about the images and to obtain any supporting metadata for this collection.

How to load IDC QIN-SARCOMA: Sarcomas MRI (15 patients) in Python

# QIN-SARCOMA: what is in the collection, and one real MR series from the sample folder
import os, glob, pandas as pd, numpy as np
M = os.environ.get('SCIGANTIC_MOUNT_PATH', '/mnt/archive')
series = pd.read_parquet(f'{M}/series.parquet')
print(series.groupby('Modality').agg(series=('SeriesInstanceUID', 'count'), patients=('PatientID', 'nunique'), GB=('series_size_MB', lambda s: round(s.sum() / 1024, 1))))
import pydicom
files = sorted(glob.glob(f'{M}/sample/MR_1.3.6.1.4.1.14519.5.2.1.2103.7008.148748890262413575891881694575/*.dcm'))
ds = pydicom.dcmread(files[0])
print(len(files), 'files;', ds.Modality, ds.get('Rows'), 'x', ds.get('Columns'), ds.get('ImageType'))

Written for a Scigantic notebook, where /mnt/archive is the mounted dataset.

Data structure

Fields

collection_idstr
PatientIDstr
SeriesInstanceUIDstr
StudyInstanceUIDstr
source_DOIstr
PatientAgestr
PatientSexstr
StudyDatestr
BodyPartExaminedstr
Modalitystr
Manufacturerstr
SeriesDescriptionstr
instanceCountInt64
license_short_namestr
aws_bucketstr
crdc_series_uuidstr
series_aws_urlstr
series_size_MBfloat64

Files

patients.parquet  15 x 7
samples.parquet  1 x 13
series.parquet  2,168 x 31
studies.parquet  38 x 9
sample/MR_1.3.6.1.4.1.14519.5.2.1.2103.7008.148748890262413575891881694575/  36 .dcm (6.6 MB, CC BY 4.0)

Example file: series.parquet row: PatientID QIN-SARCOMA-01-0001, Modality MR, 16 instances, 3.3 MB, s3://idc-open-data/ee5f127d-0078-4b92-b889-379ec823d42b/*

Sample notebook

Sample notebook for IDC QIN-SARCOMA: Sarcomas MRI (15 patients): worked code with the output it printed.

Analyze this dataset without downloading it

On Scigantic, IDC QIN-SARCOMA: Sarcomas MRI (15 patients) opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Health & Biomedical datasets