An ordinal CNN approach for the assessment of neurological damage in Parkinson's disease patients
Javier Barbero-Gómez 
Pedro Antonio Gutiérrez 
Víctor Manuel Vargas-Yun 
César Hervás-Martínez Expert Systems with Applications
COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Abstract
3D image scans are an assessment tool for neurological damage in Parkinson's disease (PD) patients. This diagnosis process can be automatized to help medical staff through Decision Support Systems (DSSs), and Convolutional Neural Networks (CNNs) are good candidates, because they are effective when applied to spatial data. This paper proposes a 3D CNN ordinal model for assessing the level or neurological damage in PD patients. Given that CNN need large datasets to achieve acceptable performance, a data augmentation method is adapted to work with spatial data. We consider the Ordinal Graph-based Oversampling via Shortest Paths (OGO-SP) OGO-SP method, which applies a gamma probability distribution for inter-class data generation. A modification of OGO-SP is proposed, the OGO-SP-beta algorithm, which applies the beta distribution for generating synthetic samples in the inter-class region, a better suited distribution when compared to gamma. The evaluation of the different methods is based on a novel 3D image dataset provided by the Hospital Universitario Reina Sofía (Córdoba, Spain). We show how the ordinal methodology improves the performance with respect to the nominal one, and how OGO-SP-beta yields better performance than OGO-SP.
Keywords
BibTex Citation
@article{Barbero2021ordinal,
author = {Barbero-G{\' o}mez, Javier and Guti{\' e}rrez, Pedro Antonio and Vargas-Yun, V{\' i}ctor Manuel and Vallejo-Casas, Juan-Antonio and Herv{\' a}s-Mart{\' i}nez, C{\' e}sar},
journal = {Expert Systems with Applications},
doi = {10.1016/j.eswa.2021.115271},
year = {2021},
pages = {115271},
title = {An ordinal {CNN} approach for the assessment of neurological damage in {Parkinson}'s disease patients},
url = {https://www.sciencedirect.com/science/article/pii/S0957417421007028},
howpublished = {https://www.sciencedirect.com/science/article/pii/S0957417421007028},
volume = {182},
}
BibTex Unicode Citation
@article{Barbero2021ordinal,
author = {Barbero-Gómez, Javier and Gutiérrez, Pedro Antonio and Vargas-Yun, Víctor Manuel and Vallejo-Casas, Juan-Antonio and Hervás-Martínez, César},
journal = {Expert Systems with Applications},
doi = {10.1016/j.eswa.2021.115271},
year = {2021},
pages = {115271},
title = {An ordinal {CNN} approach for the assessment of neurological damage in {Parkinson}'s disease patients},
url = {https://www.sciencedirect.com/science/article/pii/S0957417421007028},
howpublished = {https://www.sciencedirect.com/science/article/pii/S0957417421007028},
volume = {182},
}
APA Citation
Barbero-Gómez, J., Gutiérrez, P. A., Vargas-Yun, V. M., Vallejo-Casas, J.-A., & Hervás-Martínez, C. (2021). An ordinal CNN approach for the assessment of neurological damage in Parkinson’s disease patients. Expert Systems with Applications, 182, 115271. https://doi.org/10.1016/j.eswa.2021.115271
RIS Citation
TY - JOUR
AU - Barbero-Gómez, Javier
AU - Gutiérrez, Pedro Antonio
AU - Vargas-Yun, Víctor Manuel
AU - Vallejo-Casas, Juan-Antonio
AU - Hervás-Martínez, César
DA - 2021///
PY - 2021
DO - 10.1016/j.eswa.2021.115271
ID - temp_id_385846373144
SP - 115271
T2 - Expert Systems with Applications
TI - An ordinal CNN approach for the assessment of neurological damage in P
arkinson's disease patients
UR - https://www.sciencedirect.com/science/article/pii/S0957417421007028
VL - 182
ER -
CV Citation
J. Barbero-Gómez (CA), P.A. Gutiérrez, V.M. Vargas-Yun, J. Vallejo-Casas, C. Hervás-Martínez (3/5). "An ordinal CNN approach for the assessment of neurological damage in Parkinson's disease patients". Expert Systems with Applications, Vol. 182, pp. 115271, 2021. (Q1, IF: 8.7).