Dynamic Facial Expressions Analysis Based Parkinson's Disease Auxiliary Diagnosis

TL;DR

This paper introduces a novel dynamic facial expression analysis method leveraging multimodal neural networks to assist in Parkinson's disease diagnosis, achieving high accuracy by analyzing hypomimia-related facial features.

Contribution

It presents a new multimodal facial expression analysis network using CLIP and LSTM for PD diagnosis, focusing on hypomimia symptoms.

Findings

Achieved 93.1% diagnostic accuracy.

Outperformed existing PD diagnostic approaches.

Provided a convenient, non-invasive detection method.

Abstract

Parkinson's disease (PD), a prevalent neurodegenerative disorder, significantly affects patients' daily functioning and social interactions. To facilitate a more efficient and accessible diagnostic approach for PD, we propose a dynamic facial expression analysis-based PD auxiliary diagnosis method. This method targets hypomimia, a characteristic clinical symptom of PD, by analyzing two manifestations: reduced facial expressivity and facial rigidity, thereby facilitating the diagnosis process. We develop a multimodal facial expression analysis network to extract expression intensity features during patients' performance of various facial expressions. This network leverages the CLIP architecture to integrate visual and textual features while preserving the temporal dynamics of facial expressions. Subsequently, the expression intensity features are processed and input into an LSTM-based classification network for PD diagnosis. Our method achieves an accuracy of 93.1%, outperforming other in-vitro PD diagnostic approaches. This technique offers a more convenient detection method for potential PD patients, improving their diagnostic experience.