IDC TCGA-SKCM: Cutaneous Melanoma whole-slide microscopy (470 patients): sample notebook
A worked notebook for IDC TCGA-SKCM: Cutaneous Melanoma whole-slide microscopy (470 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; TCGA-SKCM contributors; tables and sample by Scigantic
- License
- Per series (series.parquet license_short_name): CC BY 4.0 2,210, CC BY 3.0 950. Cite the source DOI(s) and the IDC.
- Size
- 8 parquet tables plus 4 sample DICOM files (19 MB)
- Stored at
- Amazon S3, s3://scigantic-idc-open/tcga_skcm (us-east-1)
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.5281/zenodo.12690039
The notebook
TCGA-SKCM on the Imaging Data Commons: 470 patients, 3,160 series, 1,314.41 GB
Cutaneous Melanoma imaging of the skin from the NCI Imaging Data Commons (IDC). Series by modality: SEG 1,763, SM 950, ANN 447.
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 SEG series (CC BY 4.0); one SM slide (thumbnail + two smallest pyramid levels) (CC BY 3.0). 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("tcga_skcm"), idc.read_sample and idc.pull_series. Run anywhere else, the same calls read s3://scigantic-idc-open/tcga_skcm/ 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 = 'tcga_skcm'
# 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 tcga_skcm from /mnt/archive
TCGA-SKCM | IDC v25 | built 2026-11-17
470 patients, 470 studies, 3,160 series, 1,314.4 GB in the IDC buckets
series patients GB
Modality
SEG 1763 433 422.75
SM 950 470 721.46
ANN 447 405 170.20
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 1.0
Modality combinations per study (top 8):
modalities
ANN, SEG, SM 405
SM 37
SEG, SM 28
BodyPartExamined: {}
Licenses (per series): {'CC BY 4.0': 2210, 'CC BY 3.0': 950}
2. The sample segmentation
sample/SEG_1.2.826.0.1.3680043.10.511.3.28041848985407671789677911082551142/ is a DICOM SEG series of patient TCGA-FW-A3R5 (0.0 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"TCGA-SKCM: sample SEG, frame {i + 1}", fontsize=9); plt.tight_layout()
Output:
SEG Stony Brook Inception-V4 Binary TIL Map | 1 frames of 75 x 117 | segments: [(1, 'TILs Present', 'AUTOMATIC')] drawn on the SM series of patient TCGA-FW-A3R5: 4 instances, 122.3 MB, CC BY 3.0, s3://idc-open-data/9184b19e-d0d9-4866-812c-a6eba3277a8b/* 243 labelled pixels over 1 frames; densest frame 1
3. Open the sample whole-slide image
Slide microscopy in IDC is DICOM WSI: every resolution level of the pyramid is its own instance, tiled into frames. sample/SM_1.3.6.1.4.1.5962.99.1.3343016496.1521983479.1639725589040.2.0/ holds the thumbnail and the two smallest levels of one slide of patient TCGA-FW-A3TU (the full slide is 99 MB in 4 instances). idc.read_sample lists the levels, lowest resolution first, and level(i) assembles one from its tiles (idc.assemble_level(path) does the same for any WSI instance on disk); idc.slides is the slide table with the stain flattened to text. wsidicom (installed here) reads arbitrary regions of a full slide.
slide = idc.read_sample(C, 'SM') # SlideLevels: one entry per pyramid instance, lowest resolution first
for lv in slide.levels: print(f'{lv.width:6d} px wide {lv.image_type}')
top = slide.levels[-1]
img = slide.level(top.index) # tiles assembled row-major into one array
print(f'assembled {img.shape[1]} x {img.shape[0]} px from {top.n_frames} tiles of {top.rows} x {top.cols}' + (f', {top.um_per_px:.2f} um/px at this level' if top.um_per_px else ''))
stains = idc.slides(C)['stain'].dropna() # sm_series joined to series, list-valued stain codes flattened to text
print('stains in the collection:', stains.value_counts().head(4).to_dict())
step = max(1, int(np.ceil(max(img.shape[:2]) / 700))) # show at most ~700 px on the long side
shown = img[::step, ::step]
fig, ax = plt.subplots(figsize=(6, 6 * shown.shape[0] / shown.shape[1])); ax.imshow(shown, cmap=None if shown.ndim == 3 else 'gray'); ax.axis('off'); ax.set_title(f"TCGA-SKCM: sample slide, patient TCGA-FW-A3TU"); plt.tight_layout()
Output:
1024 px wide THUMBNAIL
2240 px wide VOLUME
4481 px wide VOLUME
assembled 4481 x 3263 px from 266 tiles of 240 x 240, 1.98 um/px at this level
stains in the collection: {'hematoxylin stain, water soluble eosin stain': 950}
4. Clinical tables
IDC ships 1 clinical table(s) for this collection (tcga_skcm_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, 'tcga_skcm_clinical')
dictionary = idc.clinical_dictionary(C)
print(clin.shape, 'rows x cols in', 'tcga_skcm_clinical')
print(dictionary[dictionary.short_table_name == 'tcga_skcm_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:
(470, 74) rows x cols in tcga_skcm_clinical
column column_label
dicom_patient_id idc_provenance_dicom_patient_id
source_batch idc_provenance_source_batch
case_gdc_id case_gdc_id
case_barcode case_barcode
program_name program_name
disease_code disease_code
project_short_name project_short_name
age_at_diagnosis age_at_diagnosis
age_began_smoking_in_years age_began_smoking_in_years
anatomic_neoplasm_subdivision anatomic_neoplasm_subdivision
batch_number batch_number
bcr bcr
bmi bmi
...
5. Pull any series from IDC on demand
The collection is 1,314.41 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='SM', 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:
TCGA-FW-A3R5 SEG 1 instances, 0.0 MB -> s3://idc-open-data/221e15fe-b373-4b2f-80ab-0d204dd6d991/* IDC viewer: https://viewer.imaging.datacommons.cancer.gov/viewer/2.25.136153614945744820819854779536034188291?seriesInstanceUID=1.2.826.0.1.3680043.10.511.3.28041848985407671789677911082551142 1 files downloaded; SEG Stony Brook Inception-V4 Binary TIL Map 75 x 117
Try this in the AI assistant
The chat panel is prefilled with the first of these.
- *Which segments does the sample SEG contain, and how many slices does each cover?*
- *Assemble the largest sample slide level, estimate how much of it is tissue versus background, and describe the stain.*
- *Which clinical variables in tcga_skcm_clinical are most complete, and how do they relate to the imaging studies per patient?*
- *Mount the companion GDC SKCM archive and tell me which imaged patients have TP53 mutations.*
- *Pick the smallest CT or MR series for three different patients, download them, and compare voxel spacing and field of view.*
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.