• Making the web (really) world wide
• PlenoISLA: Plenoptic Imaging for Skin Lesion Assessment
• DeToxSTM: Denoise Toolbox for Scanning Tunelling Microscopy Images
• CONQUEST: Carrier Aggregation and Spectrum Sharing in HetNets with Small Cells
• Where are you now? Joana Silva
Melanoma is a form of skin cancer that arises when pigment-producing cells (melanocytes) mutate and become cancerous. According to American Cancer Society, across all stages of melanoma, the average five-year survival rate in the U.S. is 92 percent. The estimated five-year survival rate for patients whose melanoma is detected early is about 98 percent. The survival rate falls to 64 percent when the disease reaches the lymph nodes and 23 percent when the disease metastasizes to distant organs. Thus, early detection and full characterization of suspicious skin lesions is the key to reduce mortality rates associated to this type of skin cancer.
Developed in IT in Leiria, under the coordinatior of Sérgio Faria, the PlenoISLA project aims to investigate computational methods for skin lesion diagnosis to assist dermatologists and to support expert systems. To this end, a dataset of light fields (SKINL2) is being acquired at Centro Hospitalar de Leiria, which is the first publicity available dataset of skin lesions in the world (http://on.ipleiria.pt/plenoisla). The 3D information, which can be extracted from the light fields, will allow to improve the performance of computer vision techniques and artificial intelligence algorithms to automatically classify not only melanomas but also other types of skin lesions. The outcomes of PlenoISLA are expected to impact and benefit all the parties in the dermatological area, from researchers that will have a new type of data to develop new algorithms and tools, to users who will benefit from the technology, and also practitioners that may increase the reliability of their diagnosis.