Multi-modal multi-class Parkinson disease classification using CNN and decision level fusion

TL;DR

This paper presents a multi-modal CNN-based approach for three-class Parkinson's disease classification using MRI and DTI data, achieving high accuracy through decision-level fusion.

Contribution

It introduces a novel multi-modal fusion method combining CNNs on MRI and DTI data for direct three-class PD classification.

Findings

Achieved 95.53% accuracy on PPMI database.

Demonstrated effectiveness of decision-level fusion.

Validated approach with ablation studies.

Abstract

Parkinson disease is the second most common neurodegenerative disorder, as reported by the World Health Organization. In this paper, we propose a direct three-Class PD classification using two different modalities, namely, MRI and DTI. The three classes used for classification are PD, Scans Without Evidence of Dopamine Deficit and Healthy Control. We use white matter and gray matter from the MRI and fractional anisotropy and mean diffusivity from the DTI to achieve our goal. We train four separate CNNs on the above four types of data. At the decision level, the outputs of the four CNN models are fused with an optimal weighted average fusion technique. We achieve an accuracy of 95.53 percentage for the direct three class classification of PD, HC and SWEDD on the publicly available PPMI database. Extensive comparisons including a series of ablation studies clearly demonstrate the effectiveness of our proposed solution.