Isosurface modelling of DatSCAN images for Parkinson disease diagnosis
- M. Martínez-Ibañez
- A. Ortiz
- J. Munilla
- Diego Salas-Gonzalez
- J. M. Gorriz
- J. Ramírez
- José Manuel Ferrández Vicente (dir. congr.)
- José Ramón Álvarez-Sánchez (dir. congr.)
- Félix de la Paz López (dir. congr.)
- Javier Toledo Moreo (dir. congr.)
- Hojjat Adeli (dir. congr.)
Editorial: Springer Suiza
ISBN: 978-3-030-19591-5
Any de publicació: 2019
Pàgines: 360-368
Tipus: Capítol de llibre
Resum
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