This work is designed to assist doctors in diagnosing Alzheimer’s disease (AD). The proposal consists in the creation of an artificial intelligence, a study and a series of tests, and a solution for the submission of a human being or an AD holder. Through graphs based on the probability of the response obtained from the program User know the correct answer with precision and details. The resonance classifier was built using a Google TensorFlow API on the Git Bash virtual machine, emulating the Linux operating system, with analytical data from the mobile-net algorithm. It was prepared for the Machine Learning process, using magnetic resonance imaging of patients with AD and healthy. The project aims to diagnose the disease before them. Thus, medication is easier, in addition to preparing the patient and his family for their future situation. The results of the tests prove a viability of the system, since it activates only 9.21% of error, beating experts in Alzheimer’s.
CITATION STYLE
de Brito Sanchez, R., de Barros, L., Rodrigues, S. C. M., Fernandes, J. C. L., Bondioli, A. C. V., de Campos Mundin, H. A., … da Silva, L. H. B. O. (2019). Artificial Intelligence to Detect Alzheimer’s in Magnetic Resonances. In IFMBE Proceedings (Vol. 70, pp. 59–63). Springer. https://doi.org/10.1007/978-981-13-2517-5_9
Mendeley helps you to discover research relevant for your work.