IDC CPTAC-PDA: Ductal Adenocarcinoma CT, whole-slide microscopy, MRI, PET (195 patients): sample notebook

A worked notebook for IDC CPTAC-PDA: Ductal Adenocarcinoma CT, whole-slide microscopy, MRI, PET (195 patients), with 5 code cells and the output each one printed. On Scigantic it opens in a hosted JupyterLab with the dataset already mounted, so nothing is downloaded first.

Provider
NCI Imaging Data Commons; CPTAC-PDA contributors; tables and sample by Scigantic
License
Per series (series.parquet license_short_name): CC BY 4.0 2,226. Cite the source DOI(s) and the IDC.
Size
8 parquet tables plus 520 sample DICOM files (30 MB)
Stored at
Amazon S3, s3://scigantic-idc-open/cptac_pda (us-east-1)
Access
Free and public. No account with the data provider is needed.
DOI
10.7937/k9/tcia.2018.sc20fo18

The notebook

CPTAC-PDA on the Imaging Data Commons: 195 patients, 2,226 series, 166.17 GB

Ductal Adenocarcinoma imaging of the pancreas from the NCI Imaging Data Commons (IDC). Series by modality: CT 757, SM 557, RTSTRUCT 536, MR 365, PT 8, US 3.

This mount is the collection's index plus a real sample, not the collection: series.parquet (one row per DICOM series, with the public S3 location of each), studies.parquet, patients.parquet, the IDC clinical tables, and sample/ folders holding one CT series (CC BY 4.0); one MR series (CC BY 4.0); one PT series (CC BY 4.0). Anything else is one anonymous S3 read away. README.md and BUILD_REPORT.json at the mount root say exactly how this was built (idc-index, IDC v25).

The code below reads all of it with the scigantic-nci package (pip install "scigantic-nci[dicom]", already installed in this image): from scigantic_nci import idc, then calls such as idc.series("cptac_pda"), idc.read_sample and idc.pull_series. Run anywhere else, the same calls read s3://scigantic-idc-open/cptac_pda/ anonymously.

import os, json
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import pydicom
from scigantic_nci import idc, NciError
plt.rcParams['figure.dpi'] = 72  # keeps the saved figures small enough for the notebook preview
try:
    from matplotlib_inline.backend_inline import set_matplotlib_formats
    set_matplotlib_formats('jpeg')  # slide renders are photographic; JPEG is a fifth the size of PNG here
except ImportError:
    pass

C = 'cptac_pda'
# scigantic_nci reads the mounted archive when its BUILD_REPORT.json names this collection, else s3://scigantic-idc-open/<collection>/ anonymously.
M = os.environ.get('SCIGANTIC_MOUNT_PATH', '/mnt/archive')
on_mount = os.path.exists(f'{M}/BUILD_REPORT.json') and json.load(open(f'{M}/BUILD_REPORT.json')).get('collection_id') == C
print('reading', C, 'from', M if on_mount else f's3://scigantic-idc-open/{C}/')

report = idc.report(C)
series = idc.series(C)  # one row per DICOM series, with its public S3 location
patients = idc.patients(C)
studies = idc.studies(C)
print(report['collection_name'], '| IDC', report['idc_data_version'], '| built', report['built_at'][:10])
print(f"{len(patients):,} patients, {len(studies):,} studies, {len(series):,} series, {series.series_size_MB.sum()/1024:,.1f} GB in the IDC buckets\n")
by_mod = series.groupby('Modality').agg(series=('SeriesInstanceUID', 'count'), patients=('PatientID', 'nunique'), GB=('series_size_MB', lambda s: round(s.sum() / 1024, 2))).sort_values('series', ascending=False)
print(by_mod.to_string())
fig, ax = plt.subplots(figsize=(7, 3))
by_mod['patients'].plot.bar(ax=ax, color='#4a6fa5'); ax.set_ylabel('patients'); ax.set_title(f"{report['collection_name']}: patients per modality"); plt.tight_layout()

Output:

reading cptac_pda from /mnt/archive
CPTAC-PDA | IDC v25 | built 2026-11-17
195 patients, 302 studies, 2,226 series, 166.2 GB in the IDC buckets

          series  patients      GB
Modality                          
CT           757        99   57.37
SM           557       168  100.49
RTSTRUCT     536       103    0.01
MR           365        17    7.89
PT             8         2    0.10
US             3         3    0.29

1. Studies and patients

A study is one imaging visit (all series acquired together); a patient may have several. studies.parquet collapses the series table to one row per study with the modalities present, patients.parquet to one row per patient.

print('Studies per patient:'); print(patients.n_studies.describe()[['min', '50%', 'max']].to_string())
print('\nModality combinations per study (top 8):'); print(studies.modalities.value_counts().head(8).to_string())
sex = patients.PatientSex.replace('', np.nan).dropna()
if len(sex): print('\nPatientSex:', sex.value_counts().to_dict())
ages = pd.to_numeric(series.PatientAge.dropna().astype(str).str.extract(r'(\d+)')[0], errors='coerce')
if ages.notna().sum() > 10: print(f'PatientAge at imaging: median {ages.median():.0f} y (IQR {ages.quantile(.25):.0f}-{ages.quantile(.75):.0f}) on {ages.notna().sum():,} series')
if 'BodyPartExamined' in series: print('\nBodyPartExamined:', series.BodyPartExamined.dropna().value_counts().head(6).to_dict())
print('\nLicenses (per series):', series.license_short_name.value_counts().to_dict())

Output:

Studies per patient:
min    1.0
50%    1.0
max    5.0

Modality combinations per study (top 8):
modalities
SM                  168
CT, RTSTRUCT        103
MR, RTSTRUCT         16
CT                    8
US                    3
CT, PT                2
MR                    1
CT, PT, RTSTRUCT      1
...

2. Open the sample CT series

sample/CT_1.3.6.1.4.1.14519.5.2.1.1078.3273.214462738419975120883984813484/ is the complete series of patient C3L-03632 (29 instances, 15.3 MB, CC BY 4.0), copied byte-for-byte from s3://idc-open-data/423d7993-e46a-4f2b-a88c-1e54ae9ba183/*. One .dcm per slice; idc.read_sample sorts them on ImagePositionPatient[2] (InstanceNumber as a fallback) and stacks them, applying RescaleSlope/RescaleIntercept so values are Hounsfield units. The pydicom datasets are in vol.datasets.

try:
    vol = idc.read_sample(C, 'CT')  # Volume: instances sorted by ImagePositionPatient z then InstanceNumber, CT in Hounsfield units
except NciError as e:  # compressed transfer syntax with no decoder plugin in this image
    print(e, 'Skipping the render.')
    vol = None
if vol is not None:
    n = len(vol.datasets)
    if vol.array is not None and n >= 3:
        lo, hi = -160, 240  # soft-tissue window in Hounsfield units
        picks = [(vol.array[i], f'slice {i + 1}/{n}') for i in (n // 4, n // 2, 3 * n // 4)]
    else:  # 2D modalities or a series that mixes image sizes (scouts, crops): show instances one by one
        imgs = vol.images if vol.ragged else list(vol.array)
        picks = [(img, f'{d.get("SeriesDescription", "")} {img.shape[1]}x{img.shape[0]}') for img, d in zip(imgs[:3], vol.datasets[:3])]
        flat = np.concatenate([p[0].ravel() for p in picks]); lo, hi = np.percentile(flat, 1), np.percentile(flat, 99)
    shapes = sorted({im.shape for im in vol.images}) if vol.ragged else [vol.array.shape[1:]]
    d0 = vol.datasets[0]
    print(f'{vol.modality} {n} instances, image shapes {shapes} | spacing {d0.get("PixelSpacing") or d0.get("ImagerPixelSpacing")} mm, slice thickness {d0.get("SliceThickness")} mm | {d0.get("Manufacturer")} {d0.get("ManufacturerModelName")} | {d0.get("SeriesDescription")}')
    fig, axes = plt.subplots(1, len(picks), figsize=(3.6 * len(picks), 3.8))
    for ax, (img, label) in zip(np.atleast_1d(axes), picks):
        ax.imshow(img if img.ndim == 2 else np.clip((img - lo) / max(hi - lo, 1e-6), 0, 1), cmap='gray', vmin=lo, vmax=hi); ax.set_title(label, fontsize=9); ax.axis('off')  # RGB (ultrasound) is scaled to 0-1
    plt.suptitle(f"CPTAC-PDA: sample CT series, patient C3L-03632"); plt.tight_layout()

Output:

CT 29 instances, image shapes [(512, 512)] | spacing [0.703125, 0.703125] mm, slice thickness 5.000000 mm | GE MEDICAL SYSTEMS LightSpeed VCT | LUNG

3. Clinical tables

IDC ships 1 clinical table(s) for this collection (cptac_pda_clinical; idc.clinical_tables lists them), keyed by dicom_patient_id = PatientID. clinical/dictionary.parquet (idc.clinical_dictionary) carries the human-readable label and the coded values for every column; coded columns store the code.

clin = idc.clinical(C, 'cptac_pda_clinical')
dictionary = idc.clinical_dictionary(C)
print(clin.shape, 'rows x cols in', 'cptac_pda_clinical')
print(dictionary[dictionary.short_table_name == 'cptac_pda_clinical'][['column', 'column_label']].head(15).to_string(index=False))
joined = patients.merge(clin, left_on='PatientID', right_on='dicom_patient_id', how='left')
print(f'\n{joined.dicom_patient_id.notna().sum()} of {len(patients)} imaged patients have a clinical row')

Output:

(140, 100) rows x cols in cptac_pda_clinical
              column                    column_label
    dicom_patient_id idc_provenance_dicom_patient_id
        source_batch     idc_provenance_source_batch
        submitter_id                    submitter_id
             case_id                         case_id
        primary_site                    primary_site
        disease_type                    disease_type
          index_date                      index_date
    lost_to_followup                lost_to_followup
          proj__name                      proj__name
    proj__project_id                proj__project_id
demo__demographic_id            demo__demographic_id
        demo__gender                    demo__gender
          demo__race                      demo__race
...

4. Pull any series from IDC on demand

The collection is 166.17 GB in s3://idc-open-data (and idc-open-data-cr for CC BY-NC series); it is not on this mount. Every row of series.parquet has aws_bucket and crdc_series_uuid; the objects under that prefix are the series' instances. idc.pull_series(row, dest) takes such a row and downloads the instances anonymously, so this needs no credentials. Check series_size_MB before pulling: a pod has a few GB of local disk.

cand = idc.series(C, modality='CT', max_size_mb=20).sort_values('series_size_MB')  # filters pushed down to parquet
row = cand.iloc[len(cand) // 2] if len(cand) else series.sort_values('series_size_MB').iloc[0]
print(row.PatientID, row.Modality, int(row.instanceCount), 'instances,', round(idc.series_size(row), 1), 'MB ->', row.series_aws_url)
print('IDC viewer:', idc.viewer_url(row))
files = idc.pull_series(row, '/tmp/idc_pull')  # anonymous read of s3://<aws_bucket>/<crdc_series_uuid>/, returns the local paths
d = pydicom.dcmread(files[0], stop_before_pixels=True)
print(len(files), 'files downloaded;', d.Modality, d.get('SeriesDescription'), d.get('Rows'), 'x', d.get('Columns'))

Output:

C3L-03639 CT 6 instances, 3.2 MB -> s3://idc-open-data/7261790e-d763-4bff-bc3a-9b1b52326bfc/*
IDC viewer: https://viewer.imaging.datacommons.cancer.gov/viewer/1.3.6.1.4.1.14519.5.2.1.1078.3707.249966304594680029097984239242?seriesInstanceUID=1.3.6.1.4.1.14519.5.2.1.1078.3707.533325062660524419589945423046
6 files downloaded; CT COR VENOUS A/P 512 x 512

Try this in the AI assistant

The chat panel is prefilled with the first of these.

Licenses are per series (license_short_name in series.parquet). Cite the collection DOI(s) in README.md and the IDC papers (Fedorov et al. 2021, 2023) when you publish.

Run it

Open this notebook to run it, see the dataset page for the full description, or browse the full catalog.