# ISLES 2017: stroke lesion outcome prediction from acute diffusion and perfusion MRI, 43 training cases with 90-day infarct masks

## Facts

- Provider: Stefan Winzeck, Mauricio Reyes et al. (ISLES organizers); mirrored by MedOtter
- License: CC-BY-4.0 (https://zenodo.org/records/17736412)
- Size: 824 files
- Format: CSV, NIfTI (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/MedOtter/isles2017
- Access: public, readable without an account
- DOI: https://doi.org/10.5281/zenodo.17736412
- Category: Neuroscience
- Source: https://doi.org/10.3389/fneur.2018.00679
- Page: https://scigantic.com/archive/ae56d182-13af-5e92-8c06-5f4a0ed15113
- Keywords: Neuroscience, MRI, image segmentation, benchmark, CSV, NIfTI, Hugging Face

## About

Training data of the MICCAI 2017 ISLES (Ischemic Stroke Lesion Segmentation) challenge, whose task is to predict where brain tissue will end up dead after a stroke. Inputs are acute multispectral MRI: an apparent diffusion coefficient (ADC) map, perfusion maps (MTT, rCBF, rCBV, Tmax, TTP, computed with Olea Sphere) and the raw 4D perfusion-weighted series (PWI); the target is the final infarct traced by a neuroradiologist on a follow-up T2 scan about 90 days later and mapped back to the acute grid. There are 43 training cases (IDs up to 48, non-contiguous), eight co-registered NIfTI (.nii) volumes per case including the OT ground-truth mask, in the original VSD/SMIR folder naming, plus a preview Parquet, about 6.5 GB (measured 2026-11-21); read with nibabel. ISLES 2017 contains the ISLES 2016 cohort, so do not benchmark the two as independent. The organizers re-deposited the data on Zenodo (DOI 10.5281/zenodo.17736412) under CC BY 4.0; the original SMIR release carried ODbL. Cite Winzeck et al., Frontiers in Neurology 9:679 (2018).

## Load the data

```python
import pandas as pd
df = pd.read_csv("hf://datasets/MedOtter/isles2017/training_1/VSD.Brain.XX.O.MR_4DPWI.127015/VSD.Brain.XX.O.MR_4DPWI.127015.csv")
df.head()
```

## Data structure

File types in sampled files: CSV, NIfTI

Example file: `training_1/VSD.Brain.XX.O.MR_4DPWI.127015/VSD.Brain.XX.O.MR_4DPWI.127015.csv`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/ae56d182-13af-5e92-8c06-5f4a0ed15113
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/ae56d182-13af-5e92-8c06-5f4a0ed15113
- Over MCP: `get_schema_card` with id `ae56d182-13af-5e92-8c06-5f4a0ed15113` at https://api.scigantic.com/mcp

## Related topics

- [Neuroscience datasets](https://scigantic.com/topics/neuroscience)
- [MRI datasets](https://scigantic.com/topics/mri)
- [CSV datasets](https://scigantic.com/topics/csv)
- [Benchmark datasets](https://scigantic.com/topics/benchmark)
- [Image segmentation datasets](https://scigantic.com/topics/image-segmentation)
- [NIfTI datasets](https://scigantic.com/topics/nifti)
