An application of deep learning to chest disease detection using images and clinical data

04 Pubblicazione in atti di convegno
DI CIACCIO Agostino, Crobu Federica

In the last few years, computer-assisted diagnosis systems have obtained a growing interest from researchers thanks to the use of deep learning techniques. We propose a deep neural network based on a multi-input architecture that allows to use all the information available to physicians during the diagnosis. The results obtained show an interesting improvement in performance in terms of predictive skill compared to the results in the literature.

© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma