RT Journal Article
T1 Morphological Characterization of Functional Brain Imaging by Isosurface Analysis in Parkinson’s Disease.
A1 Castillo-Barnes, Diego
A1 Martínez-Murcia, Francisco J.
A1 Ortiz-García, Andrés
A1 Salas-González, Diego
A1 Ramírez, Javier
A1 Górriz-Sáez, Juan Manuel
K1 Parkinson, Enfermedad de - Imágenes
K1 Cerebro - Imágenes
K1 Diagnóstico por imagen
K1 Medicina - Proceso de datos
K1 Diagnóstico - Proceso de datos
K1 Aprendizaje automático (Inteligencia artificial)
AB Finding new biomarkers to model Parkinson’s Disease (PD) is a challenge not only to help discerning between Healthy Control (HC) subjects and patients with potential PD, but also as a way to measure quantitatively the loss of dopaminergic neurons mainly concentrated at substantia nigra. Within this context, the work presented here tries to provide a set of imaging features based on morphological characteristics extracted from I[123]-Ioflupane SPECT scans to discern between HC and PD participants in a balanced set of 386 scans from Parkinson’s Progression Markers Initiative (PPMI) database. These features, obtained from isosurfaces of each scan at different intensity levels, have been classified through the use of classical Machine Learning classifiers such as Support-Vector-Machines (SVM) or Na¨ıve Bayesian and compared with the results obtained using a Multi-Layer Perceptron (MLP). The proposed system, based on a Mann-Whitney-Wilcoxon U-Test for feature selection and the SVM approach, yielded a 97.04% balanced accuracy when the performance was evaluated using a 10-fold cross-validation. This proves the reliability of these biomarkers, especially those related to sphericity, center of mass, number of vertices, 2D-projected perimeter or the 2D-projected eccentricity; among others, but including both internal and external isosurfaces.
PB World Scientific
YR 2020
FD 2020-08-12
LK https://hdl.handle.net/10630/28113
UL https://hdl.handle.net/10630/28113
LA spa
NO Castillo-Barnes, Diego & Martinez-Murcia, Francisco & Ortiz, Andrés & Salas-Gonzalez, Diego & Ramírez, Javier & Gorriz, Juan. (2020). Morphological Characterization of Functional Brain Imaging by Isosurface Analysis in Parkinson'S Disease. International Journal of Neural Systems. 30. 10.1142/S0129065720500446.
NO This work was supported by the MINECO/FEDER under the RTI2018-098913-B-I00 and PGC2018- 098813-B-C32 projects and the General Secretariat of Universities, Research and Technology, Junta de Andalucía under the Excellence FEDER Project ATIC-117-UGR18.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026