Paper Info
Title
A 3D Convolutional Neural Network Approach for the Diagnosis of Parkinson's Disease.
Abstract
Parkinsonism is the second most common neurodegenerative disease, originated by a dopamine decrease in the striatum. Single Photon Emission Computed Tomography (SPECT) images acquired using the DaTSCAN drug are a widely extended tool in the diagnosis of Parkinson's Disease (PD), since they can measure the amount of dopamine transporters in the striatum. Many automatic systems have been developed to aid in the diagnosis of PD, using traditional feature extraction methods. In this paper, we propose a novel system based on three-dimensional Convolutional Neural Networks (CNNs), that aims to differenciate between PD-affected patients and unaffected subjects. The proposed system achieves up to a 95.5% accuracy and 96.2% sensitivity in the diagnosis of PD.
Year
DOI
Venue
2017
10.1007/978-3-319-59740-9_32
Lecture Notes in Computer Science
Field
DocType
Volume
Single-photon emission computed tomography,Parkinson's disease,Computer science,Convolutional neural network,Striatum,Parkinsonism,Feature extraction,Dopamine,Artificial intelligence,Progressive supranuclear palsy,Machine learning
Conference
10337
ISSN
Citations 
PageRank 
0302-9743
5
0.42
References 
Authors
6
8
Name
Order
Citations
PageRank
Francisco Jesús Martínez-Murcia17417.08
Andrés Ortiz219525.64
Juan Manuel Górriz Sáez328935.14
Javier Ramírez465668.23
Fermín Segovia57914.71
D. Salas-Gonzalez631226.61
Diego Castillo-Barnes7248.00
I. Illán8719.24