The objectives of the research presented in this book focused on exploring artificial intelligence in conjunction with image processing to aid in decision-making for the early detection of keratoconus. First, we highlight the contribution of machine learning techniques to medical image analysis, demonstrating their relevance and effectiveness for the early screening of keratoconus, a progressive corneal disease that requires reliable and early detection. Next, we show that deep learning approaches, particularly those based on convolutional neural networks, offer superior performance for the automated classification of medical images, while also enabling the generation of synthetic images to enrich databases and improve model robustness. Taken together, these contributions highlight the considerable potential of artificial intelligence methods to enhance diagnostic accuracy, optimize the interpretation of medical images, and effectively support clinical decision-making.
Die Inhaltsangabe kann sich auf eine andere Ausgabe dieses Titels beziehen.
Imen Fourati Kallel, nata a Sfax nel giugno 1981, ha conseguito la laurea in ingegneria e un master in elettronica (ENIS, 2004-2005). Ha conseguito il dottorato in elettronica (ENIS) e in informatica (Università della Franca Contea, 2009) e ha ottenuto l'HDR nel 2025. Dal 2011 è assistente presso la Scuola Nazionale di Elettronica e Telecomunicazioni (ENET'Com).
„Über diesen Titel“ kann sich auf eine andere Ausgabe dieses Titels beziehen.
Anbieter: Home-set, Mannheim, Deutschland
Softcover/Taschenbuch. Zustand: Neu. The objectives of the research presented in this book focused on exploring artificial intelligence in conjunction with image processing to aid in decision-making for the early detection of keratoconus. First, we highlight the contribution of machine learning techniques to medical image analysis, demonstrating their relevance and effectiveness for the early screening of keratoconus, a progressive corneal disease that requires reliable and early detection. Next, we show that deep learning approaches, particularly those based on convolutional neural networks, offer superior performance for the automated classification of medical images, while also enabling the generation of synthetic images to enrich databases and improve model robustness. Taken together, these contributions highlight the considerable potential of artificial intelligence methods to enhance diagnostic accuracy, optimize the interpretation of medical images, and effectively support clinical decision-making. Sprache: Englisch Gewicht in Gramm: 155. Artikel-Nr. IB-486070
Anzahl: 2 verfügbar