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

TL;DR

This paper introduces a 3D CNN ordinal model with a novel data augmentation method for assessing neurological damage in Parkinson's disease, demonstrating improved performance on a new dataset.

Contribution

It proposes an ordinal CNN model combined with a modified data augmentation technique using beta distribution for better synthetic data generation.

Findings

Ordinal methodology improves assessment accuracy.

OGO-SP-$\beta$ outperforms original OGO-SP.

Model achieves promising results on a new dataset.

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-$\beta$ 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 Sof\'ia' (C\'ordoba, 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.