Automatic skin lesion analysis using relatively small learning set
Conference: CNNA 2018 - The 16th International Workshop on Cellular Nanoscale Networks and their Applications
08/28/2018 - 08/30/2018 at Budapest, Hungary
Proceedings: CNNA 2018
Pages: 4Language: englishTyp: PDFPersonal VDE Members are entitled to a 10% discount on this title
Heri, Orsolya (Computational Optical Sensing and Processing Laboratory, Institute for Computer Science and Control, Hungarian Academy of Sciences, Hungary)
Hiba, Antal; Zarandy, Akos (Computational Optical Sensing and Processing Laboratory, Institute for Computer Science and Control, Hungarian Academy of Sciences, Hungary & Faculty of Information Technology and Bionics, Peter Pazmany Catholic University, Hungary)
Automatic analytics and visual decision making, based of artificial intelligence is a well-studied area of medical imaging. Early identification of malignant skin lesions is very critical from treatability point of views, therefore many attempts can be found in literature to make high quality precision approaches. The reached precision is partially based on the developed method, partially on the test data base. However, large data bases are not available for research. Therefore, a method is developed, which uses a medium sized data base contains a few thousand classified images.