VitaminP ORION-CRC: paired H&E and Hoechst immunofluorescence patches of colorectal cancer with nucleus and whole-cell masks

Provider
Yasin Shokrollahi (VitaminP); ORION data from Jia-Ren Lin, Peter Sorger et al.; packaged by SPORA (csmp-hub)
License
CC-BY-4.0 (source)
Size
18 files
Format
CSV, PNG (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/csmp-hub/vitaminp-orion-crc)
Access
Free and public. No account with the data provider is needed.
DOI
10.5281/zenodo.21224234
Category
Health & Biomedical
Source
https://doi.org/10.1038/s43018-023-00576-1

About this dataset

VitaminP ORION-CRC is the colorectal cancer subset of the VitaminP release for cross-modal whole-cell segmentation in histopathology. It holds 3,337 patches of 512x512 pixels from 41 tissue samples of 40 cases, each pairing a color H&E image with two co-registered fluorescence channels from the ORION same-section imaging platform: Hoechst (nuclei) and a combined E-cadherin plus CD45 cell-boundary signal. Nucleus and whole-cell instance masks were produced by segmentation models, and pathologists selected regions where outlines were reliable; 158,851 nucleus-to-cell links are provided. The original train, validation and test splits are kept with each case in one split. Fluorescence is stored as uint16 TIFF and masks as uint32 TIFF bytes inside train.parquet, val.parquet and test.parquet, about 3.9 GB (measured 2026-11-21); read with pandas or polars plus tifffile and Pillow. Pixel spacing is not recorded. Use for whole-cell segmentation from H&E, H&E-to-immunofluorescence translation and nucleus segmentation. This is a different product from the 19-channel ORION-CRC crops. Repackaged by SPORA (csmp-hub) from Zenodo DOI 10.5281/zenodo.21224234, released under CC BY 4.0; cite Shokrollahi 2026 and Lin et al., Nature Cancer 2023 (doi 10.1038/s43018-023-00576-1).

How to load this dataset in Python

import pandas as pd
df = pd.read_csv("hf://datasets/csmp-hub/vitaminp-orion-crc/crc-source-splits.csv")
df.head()

Data structure

File types in sampled files: CSV, PNG

Files

Example file: crc-source-splits.csv

Analyze this dataset without downloading it

On Scigantic, VitaminP ORION-CRC: paired H&E and Hoechst immunofluorescence patches of colorectal cancer with nucleus and whole-cell masks opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Health & Biomedical datasets