Spectro-Image Analysis with Vision Graph Neural Networks and Contrastive Learning for Parkinson’s Disease Detection

TL;DR

This paper introduces a new method using Vision Graph Neural Networks and contrastive learning to detect Parkinson’s disease from speech signals with high accuracy.

Contribution

The novel integration of ViGs with supervised contrastive learning for spectro-temporal analysis of speech in PD detection.

Findings

The ViG-M-GELU architecture achieved 91.78% test accuracy in PD classification.

The method outperforms traditional CNN approaches by capturing complex spectro-temporal relationships.

The framework works well with limited labeled data and across multi-institutional datasets.

Abstract

This study presents a novel framework that integrates Vision Graph Neural Networks (ViGs) with supervised contrastive learning for enhanced spectro-temporal image analysis of speech signals in Parkinson’s disease (PD) detection. The approach introduces a frequency band decomposition strategy that transforms raw audio into three complementary spectral representations, capturing distinct PD-specific characteristics across low-frequency (0–2 kHz), mid-frequency (2–6 kHz), and high-frequency (6 kHz+) bands. The framework processes mel multi-band spectro-temporal representations through a ViG architecture that models complex graph-based relationships between spectral and temporal components, trained using a supervised contrastive objective that learns discriminative representations distinguishing PD-affected from healthy speech patterns. Comprehensive experimental validation on multi-institutional datasets from Italy, Colombia, and Spain demonstrates that the proposed ViG-contrastive framework achieves superior classification performance, with the ViG-M-GELU architecture achieving 91.78% test accuracy. The integration of graph neural networks with contrastive learning enables effective learning from limited labeled data while capturing complex spectro-temporal relationships that traditional Convolution Neural Network (CNN) approaches miss, representing a promising direction for developing more accurate and clinically viable speech-based diagnostic tools for PD.

Figures