stroke
Datasets
All datasets matching “stroke”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.Brain-Stroke-Diagnosissynthetic-stroke-patients-v3
Synthetic Stroke Patient Episodes v3
Release status: PILOT_ONLY. Clinical use is not approved.
This repository contains 1,000 wholly synthetic adult stroke episodes with 130 structured dimensions, compositional clinical notes, and 5,000 time-indexed educational task examples. It contains no real patient records.
Splits
Train: 700 patients
Validation: 100 patients
Test: 100 patients
Challenge: 100 patients
Each episode is also represented at five information… See the full description on the dataset page: https://huggingface.co/datasets/therayelab/synthetic-stroke-patients-v3.Stroketekno21-brain-stroke-dataset-multi
Dataset Card for BTX24/tekno21-brain-stroke-dataset-multi
🔗 Dataset Sources
Dataset Source: TEKNOFEST-2021 Stroke Dataset
Kaggle: İnme Veri Seti (Stroke Dataset)
Sağlık Bakanlığı Açık Veri Portalı: İnme Veri Seti
Dataset Structure
Format: PNG
Total Images: 7,369
Categories:
hemorajik/ (Hemorrhagic stroke images)
iskemik/ (Ischemic stroke images)
normal/ (Non-stroke images)
The dataset is structured in a folder-based format where images are grouped into… See the full description on the dataset page: https://huggingface.co/datasets/BTX24/tekno21-brain-stroke-dataset-multi.stroke-classification
Stroke Classification: Pre-processed Brain CT Dataset
Related resources
Live demo
Training code
Distilled model
Summary
Task: Binary CT image classification (No-Stroke = 0, Stroke = 1)
Dataset Size: ~16.5k images per fold, ~49.5k files across folds on disk. ~3 GB total
Structure: 3-fold cross-validation (Fold1, Fold2, Fold3), each containing train/ and test/ splits
Labeling Strategy: Original classes (No Stroke, Bleeding, Ischemia) were converted into a… See the full description on the dataset page: https://huggingface.co/datasets/melisklc0/stroke-classification.