Currently, the analysis of a suspicious skin lesions is done through biopsy, a process than usually takes several weeks until the definitive diagnosis is obtained. This means high personal costs, due to the uncertainty during the wait, and high economical costs to the health system, attributable to the cost of the procedure and consequent visits to the physician. Besides, the incidence of melanoma has nearly doubled in the last 10 years in the Basque Country and is growing at 10% rate per year in Spain. The 23th of May is the World Melanoma day.

Tecnalia works in collaboration with the University of the Basque Country, Ibermática and NorayBio on the development of a computer aided diagnosis tool (CAD) for the early diagnosis of melanoma and basal cell carcinoma (BCC) based on images and clinical data. Molecular data related to prognosis is also being studied, as it can help to define personalized treatments for the patients.

The tool uses Optical Coherence Tomography (OCT) images of the skin, an imaging diagnosis modality similar to echography, but with microscopic resolution. The consortium applies machine learning techniques with the goal to generate diagnosis and prognosis models of the diseases. The Computer Vision group at Tecnalia, works on the analysis of OCT and clinical images applying deep learning techniques.

This new tool with help improving in-situ diagnosis of suspicious lesions by means of “optical biopsy”, as it is a non-invasive technique.

This computer aided diagnosis tool in being developed in ASTONISH – Advancing Smart Optical Imaging and Sensing for Health, an European project where more than twenty partners are collaborating.