An ordinal CNN approach for the assessment of neurological damage in Parkinson’s disease patients

J. Barbero-Gómez , P. Gutiérrez, V. Vargas, J. Vallejo-Casas, C. Hervás-Martínez

Expert Systems with Applications, Vol. 182, pp. 1-12, 2021 Indexed in JCR. Impact factor: 8.7, Position: 21/145 (Q1) in COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE JCR

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 CNNs 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) method, which applies a gamma probability distribution for inter-class data generation. A modification of OGO-SP is proposed, the OGO-SP- 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- yields better performance than OGO-SP.

Cite this publication

BibTex

@article{barbero-gomez2021an,
    author = {Javier Barbero-Gómez and Pedro Antonio Gutiérrez and Víctor Manuel Vargas and Juan Antonio Vallejo-Casas and César Hervás-Martínez},
    title = {An ordinal CNN approach for the assessment of neurological damage in Parkinson’s disease patients},
    journal = {Expert Systems with Applications},
    year = {2021},
    volume = {182},
    number = {0},
    pages = {1--12},
    doi = {10.1016/j.eswa.2021.115271}
}

APA

Barbero-Gómez, J., Gutiérrez, P., Vargas, V., Vallejo-Casas, J., Hervás-Martínez, C. (2021). An ordinal CNN approach for the assessment of neurological damage in Parkinson’s disease patients. Expert Systems with Applications, 182(0), 1-12.

J. Barbero-Gómez (CA), P.A. Gutiérrez, V.M. Vargas, J.A. 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(0), pp. 1-12, 2021. (Q1, IF: 8.7)

RIS

TY  - JOUR
T1  - An ordinal CNN approach for the assessment of neurological damage in Parkinson’s disease patients
AU  - Barbero-Gómez, Javier
AU  - Gutiérrez, Pedro Antonio
AU  - Vargas, Víctor Manuel
AU  - Vallejo-Casas, Juan Antonio
AU  - Hervás-Martínez, César
JO  - Expert Systems with Applications
VL  - 182
IS  - 0
SP  - 1
EP  - 12
PY  - 2021
DO  - 10.1016/j.eswa.2021.115271
ER  -