How to install datasets
May 17, 2026 · View on GitHub
Our study includes 11 biomedical image classification datasets. Place all the datasets in one directory under data to ease management. The file structure looks like
data/
|–– BRISC/
|–– BTMRI/
|–– BTMRI-P/
|–– BTMRI-S/
|–– BUID/
|–– BUSBRA/
|–– BUSI/
|–– CHMNIST/
|–– COVID_19/
|–– CTKidney/
|–– DermaMNIST/
|–– KneeXray/
|–– Kvasir/
|–– LungColon/
|–– OCTMNIST/
|–– RETINA/
|–– UDIAT/
Datasets Description
| Modality | Organ(s) | Name | Classes | # train/val/test |
|---|---|---|---|---|
| Computerized Tomography | Kidney | CTKidney | Kidney Cyst, Kidney Stone, Kidney Tumor, Normal Kidney | 6221/2487/3738 |
| Dermatoscopy | Skin | DermaMNIST | Actinic Keratosis, Basal Cell Carcinoma, Benign Keratosis, Dermatofibroma, Melanocytic nevus, Melanoma, Vascular Lesion | 7007/1003/2005 |
| Endoscopy | Colon | Kvasir | Dyed Lifted Polyps, Normal Cecum, Esophagitis, Dyed Resection Margins, Normal Pylorus, Normal Z Line, Polyps, Ulcerative Colitis | 2000/800/1200 |
| Fundus Photography | Retina | RETINA | Cataract, Diabetic Retinopathy, Glaucoma, Normal Retina | 2108/841/1268 |
| Histopathology | Lung, Colon | LC25000 | Colon Adenocarcinoma, Colon Benign Tissue, Lung Adenocarcinoma, Lung Benign Tissue, Lung Squamous Cell Carcinoma | 12500/5000/7500 |
| Histopathology | Colorectal | CHMNIST | Adipose Tissue, Complex Stroma, Debris, Empty Background, Immune Cells, Normal Mucosal Glands, Simple Stroma, Tumor Epithelium | 2496/1000/1504 |
| Magnetic Resonance Imaging | Brain | BTMRI | Glioma Tumor, Meningioma Tumor, Normal Brain, Pituitary Tumor | 2854/1141/1717 |
| Magnetic Resonance Imaging | Brain | BTMRI-P | Glioma Tumor, Meningioma Tumor, Normal Brain, Pituitary Tumor | 8000/0/1000 |
| Magnetic Resonance Imaging | Brain | BTMRI-S | Glioma Tumor, Meningioma Tumor, Normal Brain, Pituitary Tumor | 2451/0/529 |
| Magnetic Resonance Imaging | Brain | BRISC | Glioma Tumor, Meningioma Tumor, Normal Brain, Pituitary Tumor | 2498/0/1000 |
| Optical Coherence Tomography | Retina | OCTMNIST | Choroidal Neovascularization, Drusen, Diabetic Macular Edema, Normal | 97477/10832/1000 |
| Ultrasound | Breast | BUSI | Benign Tumors, Malignant Tumors, Normal Scans | 389/155/236 |
| Ultrasound | Breast | BUID | Benign Tumors, Malignant Tumors | 162/0/36 |
| Ultrasound | Breast | BUSBRA | Benign Tumors, Malignant Tumors | 1311/0/283 |
| Ultrasound | Breast | UDIAT | Benign Tumors, Malignant Tumors | 113/0/26 |
| X-Ray | Chest | COVID-QU-Ex | COVID-19, Lung Opacity, Normal Lungs, Viral Pneumonia | 10582/4232/6351 |
| X-Ray | Knee | KneeXray | No, Doubtful, Minimal, Moderate, and Severe Osteoarthritis | 5778/826/1656 |
Download the datasets
All the datasets can be found here on HuggingFace. Download each dataset seperately:
- BTMRI [Drive | HuggingFace]
- BUSI [Drive | HuggingFace]
- CHMNIST [Drive | HuggingFace]
- COVID_19 [Drive | HuggingFace]
- CTKidney [Drive | HuggingFace]
- DermaMNIST [Drive | HuggingFace]
- KneeXray [Drive | HuggingFace]
- Kvasir [Drive | HuggingFace]
- LungColon [Drive | HuggingFace]
- OCTMNIST [Drive | HuggingFace]
- RETINA [Drive | HuggingFace]
Domain Generalization Datasets
- BTMRI-P HuggingFace
- BTMRI-S HuggingFace
- BRISC HuggingFace
- BUID HuggingFace
- BUSBRA HuggingFace
- UDIAT HuggingFace
After downloading each dataset, unzip and place each under its respective directory like the following
BTMRI/
|–– BTMRI/
| |–– glioma_tumor/
| |–– meningioma_tumor/
| |–– normal_brain/
| |–– pituitary_tumor/
|–– split_BTMRI.json