SkinDisNet: A Multi-Class Clinical Images and Metadata for Skin Disease

Purpose : Classification and identification of six different skin disease categories for automatic diagnosis.
Type of data: Image files (512 x 512 pixels)
Data format: Joint Photographic Expert Group (JPG) and Comma Separated Values (CSV) file formats
Number of classes: Six (Atopic Dermatitis, Contact Dermatitis, Eczema, Scabies, Seborrheic Dermatitis, and Tinea Corporis)
Number of images: Preprocessed Folder: 1710 images
Augmented Folder: 11970 images
Metadata: The metadata associated with each skin lesion is composed of 7 attributes. All attributes are available in a CSV document. In total, there are 416 patients and 1,710 skin disease images present in the dataset. Each image/sample has a reference to the patient and the skin disease in the metadata.

Data Acquisition: Images were captured using smartphone cameras during the patients’ consultations with dermatologists.
Data source: Clinical sources:
1. Institution: Rangpur Medical College, City: Rangpur, Country: Bangladesh
2. Institution: Shahid Syed Nazrul Islam Medical College, City: Kishoreganj, Country: Bangladesh

Applications: Skin disease detection and classification, diagnosis systems, medical image analysis, computer vision and more.