Resumen de Isosurface modelling of DatSCAN images for Parkinson disease diagnosis

M. Martínez Ibáñez, A. Ortiz Barragan, J. Munilla, Diego Salas González, Juan Manuel Górriz Sáez, J. J. Ramírez Palanca

• This paper proposes the computing of isosurfaces as a wayto extract relevant features from 3D brain images. These isosurfaces are then used to implement a Computer aided diagnosis system to assist in the diagnosis of Parkinson’s Disease (PD) which uses a most well-known Convolutional Neural Networks (CNN) architecture, LeNet, to classify DaTScan images with an average accuracy of 95.1% and AUC = 97%,obtaining comparable (slightly better) values to those obtained for most of the recently proposed systems. It can be concluded therefore that the computation of isosurfaces reduces the complexity of the inputs significantly, resulting in high classification accuracies with reduced computational burden