datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
tekno21-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.autotrain-data-stroke-classifier
AutoTrain Dataset for project: stroke-classifier
Dataset Description
This dataset has been automatically processed by AutoTrain for project stroke-classifier.
Languages
The BCP-47 code for the dataset's language is unk.
Dataset Structure
Data Instances
A sample from this dataset looks as follows:
[
{
"image": "<233x197 L PIL image>",
"target": 0
},
{
"image": "<233x197 L PIL image>",
"target": 0
}]
Dataset… See the full description on the dataset page: https://huggingface.co/datasets/Neurogpt/autotrain-data-stroke-classifier.tekno21-brain-stroke-dataset-binary
Dataset Card for BTX24/tekno21-brain-stroke-dataset-binary
Dataset Description
📌 EN:The TEKNO21 Brain Stroke Dataset consists of 7,369 anonymized brain CT scans in DICOM and PNG formats, labeled by seven expert radiologists. It includes acute/hyperacute ischemic and hemorrhagic stroke cases, as well as non-stroke images. Each annotation was verified for accuracy. The dataset was curated from the Turkish Ministry of Health’s e-Pulse and Teleradiology System (2019–2020) as… See the full description on the dataset page: https://huggingface.co/datasets/BTX24/tekno21-brain-stroke-dataset-binary.