How to open IDC cervical cancer whole-slide DICOM images in a Jupyter notebook
Read the collection index with pandas (pd.read_parquet on series.parquet) and a slide with pydicom (pydicom.dcmread). In a Scigantic notebook the collection tables and a sample slide series are mounted at /mnt/archive, and each index row gives the public S3 location of its full series.
The code on this page runs in a Scigantic hosted notebook, where the dataset is mounted read-only at /mnt/archive. The same path is in the SCIGANTIC_MOUNT_PATH environment variable and linked from ~/archive. The public source is s3://scigantic-idc-open/cgci_htmcp_cc/ (AWS us-east-1, public); full series in s3://idc-open-data.
Open IDC CGCI-HTMCP-CC cervical cancer slides on SciganticOpen the sample notebook: Cervical cancer slides joined to their clinical and RNA-seq records
Code
Summarize the collection and read one slide series
# CGCI-HTMCP-CC: what is in the collection, and one real SM 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/SM_1.3.6.1.4.1.5962.99.1.4104543974.2138018538.1773631102694.4.0/*.dcm'))
ds = pydicom.dcmread(files[0])
print(len(files), 'files;', ds.Modality, ds.get('Rows'), 'x', ds.get('Columns'), ds.get('ImageType'))
The starter cell from this dataset's schema card. It ran without error on 2026-11-14 in the Scigantic notebook image against the mounted data.
What the files are
CGCI-HTMCP-CC is a cervical squamous cell carcinoma collection in the NCI Imaging Data Commons (IDC): whole-slide microscopy for 211 patients, 525 DICOM series and 144.2 GB of images in total.
This archive holds Parquet tables that index the collection at patient, study and series level, a table of slide-specific attributes, and a real sample to test code against: one slide series with its thumbnail and lowest pyramid levels.
How the files are laid out
| Path under the mount | What it holds |
|---|---|
| series.parquet | 525 rows by 31 columns. One row per DICOM series, with modality, instance count, size, license and the s3://idc-open-data/... location of the files. |
| sm_series.parquet | 525 rows by 20 columns of slide microscopy attributes. |
| patients.parquet, studies.parquet | 211 rows each: patient-level and study-level summaries. |
| sample/SM_<SeriesInstanceUID>/ | Three .dcm files, 3.9 MB: the thumbnail and lowest pyramid levels of one slide. |
Size, format and license
| Format | Parquet tables and DICOM whole-slide microscopy |
|---|---|
| Size | 5 Parquet tables plus 3 sample DICOM files (4 MB). The full slides stay in the IDC bucket. |
| License | CC BY 4.0 for all 525 series. Cite the source DOI 10.5281/zenodo.17381404 and the IDC. |
| Provider | NCI Imaging Data Commons and the CGCI-HTMCP-CC contributors; tables and sample by Scigantic |
| Public source | s3://scigantic-idc-open/cgci_htmcp_cc/ (AWS us-east-1, public); full series in s3://idc-open-data |
| Notebook image | Pathology and medical imaging (pydicom and pandas preinstalled) |
Things to know before you read it
- A slide series is several DICOM files, one per resolution level or image type; check
ImageTypeon each, as the code prints. sample/holds one series only. For any other slide, use the S3 location in itsseries.parquetrow.
Run it
Start a notebook from the IDC CGCI-HTMCP-CC cervical cancer slides archive page. The data is mounted when the notebook opens, so the code above runs as written and nothing is downloaded first. For a longer worked example, open the sample notebook Cervical cancer slides joined to their clinical and RNA-seq records.
Related guides
- How to load CMMD mammography DICOM files and clinical data in a Jupyter notebook
- How to open CAMELYON lymph node whole-slide images from S3 in a Jupyter notebook
- How to browse CZ CryoET Data Portal datasets in a Jupyter notebook
- How to open OME-Zarr volumes in a Jupyter notebook
Last checked 2026-11-21. All dataset guides.