ISLES
Datasets
All datasets matching “ISLES”isles24-stroke
ISLES'24 Stroke Training Dataset
Multi-center longitudinal multimodal acute ischemic stroke training dataset from the ISLES'24 Challenge.
Overview
149 acute ischemic stroke training cases with:
Admission imaging (ses-01): Non-contrast CT, CT angiography, 4D CT perfusion
Follow-up imaging (ses-02): Post-treatment MRI (DWI, ADC)
Clinical data: Demographics, patient history, admission NIHSS, 3-month mRS outcomes
Annotations: Infarct masks, large vessel occlusion masks… See the full description on the dataset page: https://huggingface.co/datasets/hugging-science/isles24-stroke.ISLES-26isles2017
ISLES 2017 — Ischemic Stroke Lesion Segmentation Challenge (Outcome Prediction)
Multispectral brain MRI from the MICCAI 2017 edition of the Ischemic
Stroke Lesion Segmentation (ISLES) challenge. The 2017 task is lesion outcome
prediction: estimate the final infarct (segmented on a ~90-day follow-up
scan) from acute multispectral MRI.
This repository contains the public training split only (43 cases), every
case carrying its expert ground-truth lesion mask. The 32-case test split… See the full description on the dataset page: https://huggingface.co/datasets/MedOtter/isles2017.isles2024
ISLES'24 - Ischemic Stroke Lesion Segmentation Challenge 2024
A real-world, longitudinal, multimodal acute-stroke dataset: acute admission
CT (NCCT, CTA, 4D CT-perfusion + derived perfusion maps), follow-up MRI
(DWI/ADC), and clinical tabular data, with the final infarct lesion as the
segmentation target.
This repository mirrors the public TRAINING set only (149 cases). The
98-case ISLES'24 test set is withheld by the organizers for challenge scoring
on Grand Challenge and is… See the full description on the dataset page: https://huggingface.co/datasets/MedOtter/isles2024.isles2022
ISLES 2022 Dataset
Dataset Description
The ISLES 2022 dataset for ischemic stroke lesion segmentation. This dataset contains MRI (ADC, DWI) scans with dense segmentation annotations.
Dataset Details
Modality: MRI (ADC, DWI)
Target: stroke lesion
Format: NIfTI (.nii.gz)
Dataset Structure
Each sample in the JSONL file contains:
{
"image": "path/to/image.nii.gz",
"mask": "path/to/mask.nii.gz",
"label": ["organ1", "organ2", ...]… See the full description on the dataset page: https://huggingface.co/datasets/MedOtter/isles2022.isles2018
ISLES 2018 — Ischemic Stroke Lesion Segmentation Challenge 2018
CT-perfusion (CTP) infarct-core segmentation in acute anterior-circulation ischemic
stroke. 103 patients / 156 CTP acquisitions ("cases") pooled from the DEFUSE 2 study
and a companion prospective cohort (4 centers: 3 US, 1 Australian; Cereda et al. 2016).
Because CTP z-coverage was limited (4.4-16 cm), some patients were scanned as two
separate slabs (A/B) — each slab is its own case_N folder.
Split
Cases… See the full description on the dataset page: https://huggingface.co/datasets/MedOtter/isles2018.