IDC ISPY2: Breast Cancer MRI (719 patients): sample notebook

A worked notebook for IDC ISPY2: Breast Cancer MRI (719 patients), with 6 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; ISPY2 contributors; tables and sample by Scigantic
License
Per series (series.parquet license_short_name): CC BY 4.0 32,411. Cite the source DOI(s) and the IDC.
Size
6 parquet tables plus 161 sample DICOM files (8 MB)
Stored at
Amazon S3, s3://scigantic-idc-open/ispy2 (us-east-1)
Access
Free and public. No account with the data provider is needed.
DOI
10.7937/tcia.d8z0-9t85

The notebook

ISPY2 on the Imaging Data Commons: 719 patients, 32,411 series, 1,705.31 GB

Breast Cancer imaging of the breast from the NCI Imaging Data Commons (IDC). Series by modality: MR 29,723, SEG 2,688.

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 MR series (CC BY 4.0); one SEG 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("ispy2"), idc.read_sample and idc.pull_series. Run anywhere else, the same calls read s3://scigantic-idc-open/ispy2/ 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 = 'ispy2'
# 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 ispy2 from /mnt/archive
ISPY2 | IDC v25 | built 2026-11-17
719 patients, 2,688 studies, 32,411 series, 1,705.3 GB in the IDC buckets

          series  patients       GB
Modality                           
MR         29723       719  1680.25
SEG         2688       719    25.06

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%    4.0
max    4.0

Modality combinations per study (top 8):
modalities
MR, SEG    2688

PatientSex: {'F': 719}

BodyPartExamined: {'BREAST': 12079, 'TSPINE': 24}

Licenses (per series): {'CC BY 4.0': 32411}

2. Open the sample MR series

sample/MR_1.3.6.1.4.1.14519.5.2.1.267946271023036289136838713088710880597/ is the complete series of patient ISPY2-934459 (160 instances, 6.3 MB, CC BY 4.0), copied byte-for-byte from s3://idc-open-data/62fdc9b3-8a96-4180-871b-da5646d3a86f/*. One .dcm per slice; idc.read_sample sorts them on ImagePositionPatient[2] (InstanceNumber as a fallback) and stacks them. The pydicom datasets are in vol.datasets.

try:
    vol = idc.read_sample(C, 'MR')  # Volume: instances sorted by ImagePositionPatient z then InstanceNumber
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 = np.percentile(vol.array, 1), np.percentile(vol.array, 99)
        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"ISPY2: sample MR series, patient ISPY2-934459"); plt.tight_layout()

Output:

MR 160 instances, image shapes [(128, 128)] | spacing [1.3671875, 1.3671875] mm, slice thickness 1 mm | SIEMENS Avanto | ISPY2: VOLSER: uni-lateral cropped: PE5

3. The sample segmentation

sample/SEG_1.3.6.1.4.1.14519.5.2.1.88946055166063666498180186362420292828/ is a DICOM SEG series of patient ISPY2-725455 (1.8 MB, CC BY 4.0): a stack of binary frames, one per segment and source slice, with SegmentSequence naming each segment and ReferencedSeriesSequence pointing at the image series it was drawn on. A few collections label ordinary image instances (one label map per slice) as SEG; the cell handles both. idc.sample_files lists the files; on the mount they are read in place, and elsewhere the same series is pulled from IDC with idc.pull_series. The source image series can be pulled from IDC the same way as any other row of series.parquet.

# scigantic_nci has no SEG reader, and read_sample decodes one frame per instance, which pydicom cannot do for some 1-bit SEG objects,
# so the SEG files are read whole with pydicom: in place on the mount (sample_files gives paths relative to the archive root), else pulled from IDC.
seg_sample = idc.samples(C).query("modality == 'SEG'").iloc[0]
if on_mount:
    seg_files = [os.path.join(M, f) for f in idc.sample_files(C, 'SEG')]
else:
    seg_files = idc.pull_series(series[series.SeriesInstanceUID == seg_sample.SeriesInstanceUID].iloc[0], '/tmp/idc_pull/' + seg_sample.SeriesInstanceUID)
seg_ds = [pydicom.dcmread(f) for f in seg_files]
seg = seg_ds[0]
if 'SegmentSequence' in seg:  # a DICOM Segmentation object
    print(seg.Modality, seg.get('SeriesDescription'), '|', int(seg.get('NumberOfFrames', 1)), 'frames of', seg.Rows, 'x', seg.Columns, '|', seg.get('ContentCreatorName'))
    print('segments:', [(int(x.SegmentNumber), str(x.SegmentLabel), str(x.get('SegmentAlgorithmType'))) for x in seg.SegmentSequence][:8])
    mask = seg.pixel_array
else:  # labelled SEG but stored as ordinary images: one label map per slice
    seg_ds.sort(key=lambda d: (float(d.ImagePositionPatient[2]) if 'ImagePositionPatient' in d else 0.0, int(d.get('InstanceNumber', 0))))
    print(seg.Modality, seg.get('SeriesDescription'), '|', len(seg_ds), seg.SOPClassUID.name, 'instances of', seg.Rows, 'x', seg.Columns, '(label maps, not a Segmentation object)')
    mask = np.stack([d.pixel_array for d in seg_ds])
    values, counts = np.unique(mask, return_counts=True)
    mask = mask != values[counts.argmax()]  # label maps carry a nonzero background value; everything else is labelled
ref = seg.ReferencedSeriesSequence[0].SeriesInstanceUID if 'ReferencedSeriesSequence' in seg else None
src = series[series.SeriesInstanceUID == ref]
if len(src):
    r = src.iloc[0]
    print(f'drawn on the {r.Modality} series of patient {r.PatientID}: {int(r.instanceCount)} instances, {r.series_size_MB:.1f} MB, {r.license_short_name}, {r.series_aws_url}')
mask = (mask[None] if mask.ndim == 2 else mask) > 0
i = int(mask.reshape(mask.shape[0], -1).sum(1).argmax())  # the frame with the most labelled pixels
print(f'{int(mask.sum()):,} labelled pixels over {mask.shape[0]} frames; densest frame {i + 1}')
fig, ax = plt.subplots(figsize=(3.8, 3.8)); ax.imshow(mask[i], cmap='gray'); ax.axis('off'); ax.set_title(f"ISPY2: sample SEG, frame {i + 1}", fontsize=9); plt.tight_layout()

Output:

SEG ISPY2: VOLSER: uni-lateral cropped: Analysis Mask | 106 frames of 128 x 128 | 
segments: [(1, 'VOLSER Analysis Mask', 'SEMIAUTOMATIC')]
1,732,824 labelled pixels over 106 frames; densest frame 1

4. Clinical tables

IDC ships 1 clinical table(s) for this collection (ispy2_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, 'ispy2_clinical')
dictionary = idc.clinical_dictionary(C)
print(clin.shape, 'rows x cols in', 'ispy2_clinical')
print(dictionary[dictionary.short_table_name == 'ispy2_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:

(985, 12) rows x cols in ispy2_clinical
           column                    column_label
 dicom_patient_id idc_provenance_dicom_patient_id
     source_batch     idc_provenance_source_batch
       patient_id                      Patient_ID
              arm                             Arm
               hr                              HR
             her2                            HER2
               mp                              MP
              pcr                             pCR
 age_at_screening                Age_at_Screening
             race                            Race
menopausal_status               menopausal_status
        ethnicity                       ethnicity

...

5. Pull any series from IDC on demand

The collection is 1,705.31 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='MR', 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:

ISPY2-767934 MR 80 instances, 10.9 MB -> s3://idc-open-data/75a2e0f6-484b-479f-9848-26d7a1d9d019/*
IDC viewer: https://viewer.imaging.datacommons.cancer.gov/viewer/1.3.6.1.4.1.14519.5.2.1.3746756847691315418864235077366344431?seriesInstanceUID=1.3.6.1.4.1.14519.5.2.1.97835477892921438479510157879677681066
80 files downloaded; MR ISPY2: VOLSER: uni-lateral cropped: PE5 256 x 256

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.