Dermofit Image Library
The Dermofit Image Library provides a collection of high quality skin lesion images for use as a research tool in computer science and medical imaging.
The Dermofit Image Library is a collection of 1,300 focal high quality skin lesion images collected under standardised conditions with internal colour standards. The lesions span across ten different classes including melanomas, seborrhoeic keratosis and basal cell carcinomas. Each image has a gold standard diagnosis based on expert opinion (including dermatologists and dermatopathologists). Images consist of a snapshot of the lesion surrounded by some normal skin. A binary segmentation mask that denotes the lesion area is included with each lesion. The categories of lesions and number of associated images is listed below.
|Lesion Type||Number of images|
|Basal Cell Carcinoma||239|
|Melanocytic Nevus (mole)||331|
|Squamous Cell Carcinoma||88|
The Dermofit Image Library is available under an academic licence. There is a one-off £75 licence fee associated with this product.
Licensing requirements - PLEASE READ
To ensure that your request for the Dermofit Image Library is not rejected, the following conditions must be met:
(1) you must submit your order via an account with an institutional email address (i.e. not a third party email account);
(2) the licence agreement must be approved by an authorised representative of your institution before the product can be released. (Self approval is not permitted)
In the case of academic institutions, this is normally an officer from your Research Services, Technology Transfer or Legal Office.
We strongly recommend that you liaise with appropriate colleagues PRIOR to completing your click-thru application.
(3) you must provide specific details of the intended use for the Dermofit Image Library.
The Dermofit Image Library is made available only under the terms and conditions of the associated licence agreement.
This permits a single research group of the Licensee to use the image dataset for computer science or medical image research.
A limited number of images can be included in academic papers in accordance with the licence agreement, but not published on the web directly.
Images will remain the property of the University of Edinburgh and publications must reference the use of the Dermofit Image Library.
Images cannot be used for educational or commercial purposes under this agreement.
Please ensure you read and comply with the full terms and conditions of the Licence Agreement.
- Rees, Aldridge, Fisher, Ballerini (2013), A Color and Texture Based Hierarchical K-NN Approach to the Classification of Non-melanoma Skin Lesions, Color Medical Image Analysis, Lecture Notes in Computational Vision and Biomechanics 6 (M. E. Celebi, G. Schaefer (eds.))
swap_vertical_circlecloud_downloadSupporting documents (0)Additional files may be available once you've completed the transaction for this product. If you've already done so, please log into your account and visit My account / Downloads section to view them.