IDC Breast-Cancer-Screening-DBT: Breast Cancer, Non-Cancer mammography (5,060 patients): sample notebook

A worked notebook for IDC Breast-Cancer-Screening-DBT: Breast Cancer, Non-Cancer mammography (5,060 patients), with 3 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; Breast-Cancer-Screening-DBT contributors; tables and sample by Scigantic
License
Per series (series.parquet license_short_name): CC BY-NC 4.0 22,032. No series bytes are mirrored: CC BY-NC allows non-commercial use only. Cite the source DOI(s) and the IDC.
Size
4 parquet tables
Stored at
Amazon S3, s3://scigantic-idc-open/breast_cancer_screening_dbt (us-east-1)
Access
Free and public. No account with the data provider is needed.
DOI
10.7937/e4wt-cd02

The notebook

Breast-Cancer-Screening-DBT on the Imaging Data Commons: 5,060 patients, 22,032 series, 1,599.43 GB

Breast Cancer, Non-Cancer imaging of the breast from the NCI Imaging Data Commons (IDC). Series by modality: MG 22,032.

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, and no sample/ folder: the series are CC BY-NC (non-commercial use only) and Scigantic does not redistribute them, so the images below are read straight from the IDC bucket. 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("breast_cancer_screening_dbt"), idc.read_sample and idc.pull_series. Run anywhere else, the same calls read s3://scigantic-idc-open/breast_cancer_screening_dbt/ 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 = 'breast_cancer_screening_dbt'
# 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 breast_cancer_screening_dbt from /mnt/archive
Breast-Cancer-Screening-DBT | IDC v25 | built 2026-11-17
5,060 patients, 5,610 studies, 22,032 series, 1,599.4 GB in the IDC buckets

          series  patients       GB
Modality                           
MG         22032      5060  1599.43

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    3.0

Modality combinations per study (top 8):
modalities
MG    5610

PatientSex: {'F': 5059, 'M': 1}

BodyPartExamined: {'BREAST': 22032}

Licenses (per series): {'CC BY-NC 4.0': 22032}

2. Pull the smallest MG series from IDC and open it

Every MG series of this collection is licensed CC BY-NC (non-commercial use only, with attribution), and Scigantic does not redistribute CC BY-NC bytes, so nothing is under sample/ on this mount. The cell below reads the smallest MG series straight from IDC's public bucket into the pod's /tmp (anonymous S3, no credentials). It stays under the CC BY-NC terms: use it non-commercially, cite the collection DOI, and do not copy it into a product or a public bucket. Every row of series.parquet has aws_bucket and crdc_series_uuid; the objects under that prefix are the series' instances, one .dcm per slice. idc.pull_series(row, dest) downloads them and returns the local paths, which pydicom reads below. Uncompressed transfer syntaxes are preferred so the read needs no decoder plugin. Check series_size_MB before pulling a bigger one: a pod has a few GB of local disk.

cand = idc.series(C, modality='MG')  # the modality filter is pushed down to parquet
if 'MG' in ('CT', 'MR', 'PT') and (cand.instanceCount >= 10).any():
    cand = cand[cand.instanceCount >= 10]  # a real stack, not a scout
cand = cand.assign(_compressed=cand.transfer_syntax_name.fillna('').str.contains('JPEG|RLE', regex=True))
row = cand.sort_values(['_compressed', 'series_size_MB']).iloc[0]
print(row.PatientID, row.Modality, int(row.instanceCount), 'instances,', round(idc.series_size(row), 1), 'MB,', row.license_short_name, '->', row.series_aws_url)
print('IDC viewer:', idc.viewer_url(row))
folder = '/tmp/idc_pull/' + row.crdc_series_uuid
files = idc.pull_series(row, folder)  # anonymous read of s3://<aws_bucket>/<crdc_series_uuid>/, folder marker skipped
print(len(files), 'files ->', folder)
# scigantic_nci returns file paths for a pulled series (read_sample only reads the mirrored samples), so pydicom stacks them here
ds = [pydicom.dcmread(f) for f in files]
ds = [d for d in ds if 'PixelData' in d]
try:
    ds[0].pixel_array
except RuntimeError as e:  # compressed transfer syntax with no decoder plugin in this image
    print(f'This series is stored as {ds[0].file_meta.TransferSyntaxUID.name}; this image cannot decode it (pip install "pylibjpeg[all]" adds the decoder). Skipping the render.')
    ds = []
if ds:
    ds.sort(key=lambda d: (float(d.ImagePositionPatient[2]) if 'ImagePositionPatient' in d else 0.0, int(d.get('InstanceNumber', 0))))
    def frame(d):
        a = d.pixel_array
        return a[a.shape[0] // 2] if int(d.get('NumberOfFrames', 1) or 1) > 1 else a  # multi-frame instance (grayscale or RGB): middle frame
    shapes = sorted({frame(d).shape for d in ds})
    if len(shapes) == 1 and len(ds) >= 3:
        vol = np.stack([frame(d) for d in ds]).astype(np.float32)
        lo, hi = np.percentile(vol, 1), np.percentile(vol, 99)
        picks = [(vol[i], f'slice {i + 1}/{len(ds)}') for i in (len(ds) // 4, len(ds) // 2, 3 * len(ds) // 4)]
    else:  # 2D modalities or a series that mixes image sizes (scouts, crops): show instances one by one
        picks = []
        for d in ds[:3]:
            img = frame(d).astype(np.float32) * float(d.get('RescaleSlope', 1)) + float(d.get('RescaleIntercept', 0))
            picks.append((img, f'{d.get("SeriesDescription", "")} {img.shape[1]}x{img.shape[0]}'))
        vol = np.concatenate([p[0].ravel() for p in picks]); lo, hi = np.percentile(vol, 1), np.percentile(vol, 99)
    d0 = ds[0]
    print(f'{d0.Modality} {len(ds)} 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"Breast-Cancer-Screening-DBT: smallest MG series, patient {row.PatientID} ({row.license_short_name})"); plt.tight_layout()

Output:

DBT-P00136 MG 1 instances, 2.3 MB, CC BY-NC 4.0 -> s3://idc-open-data-cr/8217b99a-d12f-4de7-914d-1f762dc38006/*
IDC viewer: https://viewer.imaging.datacommons.cancer.gov/viewer/1.2.826.0.1.3680043.8.498.80413322927371786762295012224107057412?seriesInstanceUID=1.2.826.0.1.3680043.8.498.66785618348005305674256553902909034786
1 files -> /tmp/idc_pull/8217b99a-d12f-4de7-914d-1f762dc38006
MG 1 instances, image shapes [(2457, 1996)] | spacing None mm, slice thickness None mm | HOLOGIC, Inc. Selenia Dimensions | None

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); the CC BY-NC series are for non-commercial use only and Scigantic mirrors none of their bytes. 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.