Datasets

In our researches, we have been using the following dermoscopic datasets:

The Interactive Atlas of Dermoscopy (EDRA):

A multimedia guide (Booklet + CD-ROM) intended for training medical personnel to diagnose skin lesions. It has 1000+ clinical cases, each with at least two images of the lesion: close-up clinical image (acquired with a Nikon F3 camera mounted on a Wild M650 stereomicroscope), and dermoscopic image (acquired with a Dermaphot/Optotechnik dermoscope).

Most images are 768 pixels wide x 512 high. Each case has clinical data, histopathological results, diagnosis, and level of difficulty. The latter measures how difficult (low, medium and high) the case is considered to diagnose by a trained human. The diagnoses include, besides melanoma (several subtypes), basal cell carcinoma, blue nevus, Clark's nevus, combined nevus, congenital nevus, dermal nevus, dermatofibroma, lentigo, melanosis, recurrent nevus, Reed nevus, seborrheic keratosis, and vascular lesion. There is also a small number of cases classified simply as `miscelaneous'. It is cited as:

Argenziano, G., Soyer, H. P., De Giorgi, V., Piccolo, D., Carli, P., & Delfino, M. (2002). Dermoscopy: a tutorial. EDRA, Medical Publishing & New Media, 35.

The Atlas can be acquired at Dermoscopy.org. The images can be download at this link.

Dermofit Image Library:

The Dermofit Image Library is a collection of 1,300 skin lesion images and their segmentation masks divided among 10 classes (Actinic Keratosis, Basal Cell Carcinoma, Melanocytic Nevus, Seborrhoeic Keratosis, Squamous Cell Carcinoma, Intraepithelial Carcinoma, Pyogenic Granuloma, Haemangioma, Dermatofibroma and Malignant Melanoma). The diagnoses were provided by expert dermatologists and dermatopathologists, generating a gold standard groundtruth. Although this dataset is not publicly available, it can be purchased. Its main publication is:

Ballerini, L., Fisher, R. B., Aldridge, B., & Rees, J. (2013). A color and texture based hierarchical K-NN approach to the classification of non-melanoma skin lesions. In Color Medical Image Analysis (pp. 63-86). Springer Netherlands.

The Dermofit Library can be acquired here.

International Skin Imaging Collaboration: Melanoma Project (ISIC):

The ISIC Project is an academia/industry partnership, coordinated by the International Society for Digital Imaging of the Skin, to acquire and annotate skin lesion images.

The images can freely download at http://isdis.net/isic-project/.

PH² Dataset:

PH² is a dermoscopic image database acquired at the Dermatology Service of Hospital Pedro Hispano, Matosinhos, Portugal. This image database contains a total of 200 dermoscopic images of melanocytic lesions, including 80 common nevi, 80 atypical nevi, and 40 melanomas. The PH² database includes medical annotation of all the images namely medical segmentation of the lesion, clinical and histological diagnosis and the assessment of several dermoscopic criteria (colors; pigment network; dots/globules; streaks; regression areas; blue-whitish veil). The main publication is:

Teresa Mendonça, Pedro M. Ferreira, Jorge Marques, Andre R. S. Marcal, Jorge Rozeira. PH² - A dermoscopic image database for research and benchmarking, 35th International Conference of the IEEE Engineering in Medicine and Biology Society, July 3-7, 2013, Osaka, Japan.

The images can freely download at https://www.fc.up.pt/addi/ph2%20database.html.

IRMA Dataset:

The dataset is a third-party development and was created by the Department of Medical Informatics, RWTH Aachen University. It is composed of 747 dermoscopic images with resolution of 512x512 pixels, of which 187 images are melanomas and 560 images are benign skin lesions.

It is available as part of the IRMA (Image Retrieval in Medical Applications) Project. Unfortunately, the IRMA Dataset is no longer available.