Dermoscopy (dermatoscopy, skin surface microscopy) is a non-invasive diagnostic technique for the in vivo observation of pigmented skin lesions used in dermatology. There is currently a great interest in the prospects of automatic image analysis methods for dermoscopy, both to provide quantitative information about a lesion, which can be of relevance for the clinician, and as a stand alone early warning tool. The effective implementation of such a tool could lead to a reduction in the number of cases selected for exeresis, with obvious benefits both to the patients and to the health care system. The aim of this project is to develop a computer based diagnosis system for dermatology, also suitable for tele-dermoscopy and tele-medicine.
This multidisciplinary project joins medical doctors from the Pedro Hispano Hospital (HPH) and academic researchers from different fields of Engineering and Mathematics from the University of Porto (FCUP), University of Aveiro (UA) and Instituto Superior Tecnico (IST). The driving force for this research proposal was the several years of experience in dermoscopy, tele-dermoscopy and telemedicine at the HPH Service of Dermatology, and the lack of an efficient automatic image analysis system for dermoscopic images. The HPH database is a valuable resource, with over 4000 clinical cases using dermoscopic images. The database will be enriched, both through normalisation and by the inclusion of the performance of selected cases on standard dermoscopy early warning methods. This database and the extensive clinical experience of the HPH team members, together with the eclecticism of the research team, will be major assets of the project.
The final prototype will perform the automatic identification of the skin lesion on a dermoscopic image, using image segmentation techniques. It will then extract a number of features from the lesion, which will be used, together with the knowledge gathered on the existing database of clinical cases, to perform a simplified lesion classification. We believe that the key for a reliable and accurate lesion classification is the successful establishment of a link between the features used on human based early screening diagnosis methods (ex. ABCD rule, 7 point checklist) and those produced by an algorithm implemented on a computer based systems.
A complementary objective of the project is to use the enriched database and the software prototype created for simulation and educational purposes. An educational tool will be developed in the later stages of the project, which will be suitable for clinicians and health-care staff, as well as researchers in the image processing area, in order to become familiar with dermatology, dermoscopy and tele-dermoscopy.