Title: Explainable Screening of Oral Cancer via Artificial Intelligence and Case-based Reasoning
Abstract: Oral cancer is characterized by significant mortality and morbidity. Dental professionals can play an important role in its early detection, thanks to the availability of embedded smart cameras for oral photos and remote screening supported by Artificial Intelligence (AI). Despite the promising results of AI for automated detection and classification of oral lesions, its effectiveness is based on a clearly defined protocol, on the explainability of results, and on periodic cases collection. An innovative approach, combining AI and Case-Based Reasoning (CBR) can allow the post-hoc explanation of the system answer. The method uses explainability tools organized in a protocol defined in the Business Process Model and Notation (BPMN) to allow its experimental validation. The AI and a related workflow have been developed and publicly released, to foster the collaboration between clinical centers in collecting more data on regional/national basis, as well as the collaboration between AI development centers in order to achieve effectiveness in this field. The approach provides integrated management of cases base and training set, as well as support for concept drift. The proposed decision process is able to correctly address even resident doctors when dealing with border line cases.
Bio: Mario G.C.A. Cimino is an Associate Professor at the Department of Information Engineering of the University of Pisa (Italy). His research lies in the areas of Information Systems and Artificial intelligence. He is (co-)author of about 120 international scientific publications. He is an Associate Editor of the Journal of Granular Computing (Springer) and the Journal of Ambient Intelligence and Humanized Computing (Springer). He is IEEE senior member and Chair of the IEEE CIS Task Force "Intelligent Agents", IEEE Computational Intelligence Society. He was co-chair of the 2021 and 2022 IEEE Symposium on Intelligent Agents (IEEE SSCI).