PanopTILs Refined: breast cancer H&E regions with nucleus and tissue masks from 150 TCGA patients
- Provider
- Mohamed Amgad et al. (PanopTILs); curated by SPORA
- License
- CC0-1.0 (source)
- Size
- 10 files
- Format
- PNG, Parquet (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/csmp-hub/panoptils_refined)
- Access
- Free and public. No account with the data provider is needed.
- Category
- Health & Biomedical
- Source
- https://doi.org/10.1101/2022.01.08.22268814
About this dataset
PanopTILs Refined is a selected subset of PanopTILs, the crowdsourced panoptic segmentation of tumor-infiltrating lymphocytes (TILs) in breast cancer built on the BCSS and NuCLS annotations of TCGA whole-slide images. It contains 1,349 H&E regions of interest from 150 TCGA breast cancer patients, each 1024x1024 pixels at 0.25 micrometers per pixel, with instance and class masks for individual nuclei (six nucleus classes, model-assisted labels) and hand-drawn tissue region masks (six tissue classes). Patient-level splits keep all images from one patient together: train.parquet (1,068 ROIs, 120 patients), val.parquet (130, 15) and test.parquet (151, 15), with patient lists in manifest.json; these splits differ from the original PanopTILs folds. About 5.7 GB (measured 2026-11-17). Images and masks are stored as PNG or TIFF bytes inside Parquet; read them with polars or pandas plus Pillow, or with Hugging Face datasets. Use for panoptic segmentation, nucleus classification and TIL scoring. Curated and packaged on Hugging Face by the SPORA project (csmp-hub), which keeps the original license and citation files. The original PanopTILs site states the dataset is licensed CC0 1.0; cite Amgad et al., medRxiv 2022.01.08.22268814, and the BCSS and NuCLS papers.
How to load this dataset in Python
from datasets import load_dataset
ds = load_dataset("csmp-hub/panoptils_refined")
print(ds)Data structure
File types in sampled files: PNG, Parquet
Files
Example file: panoptils_refined.parquet
Analyze this dataset without downloading it
On Scigantic, PanopTILs Refined: breast cancer H&E regions with nucleus and tissue masks from 150 TCGA patients 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
- Phillips CTCL: cutaneous T-cell lymphoma skin biopsy H&E with CODEX cell regions and 23 cell types
- IDC Mouse-Astrocytoma: Glioblastoma Multiforme MRI (48 mouse subjects)
- MOGaMBO: T2-weighted pelvic MRI of 94 cervical cancer brachytherapy patients with organ-at-risk contours
- Malaria Atlas Project: Plasmodium vivax Parasite Rate (PvPR), 5 km annual maps
- IDC BoneMarrowWSI-PediatricLeukemia: Leukemia whole-slide microscopy (246 patients)
- VerSe 2019 + 2020: vertebrae labelling and segmentation in spine CT (CC BY-SA subset)
- ISIC 2017 Task 1: dermoscopy skin lesion segmentation, 2,750 images of melanoma, seborrheic keratosis and nevi with masks
- IDC Pelvic-Reference-Data: Prostate Cancer, Anal Cancer CT (58 patients)