Facial Point Graphs for Amyotrophic Lateral Sclerosis Identification

TL;DR

This paper introduces Facial Point Graphs, a novel computational method analyzing facial geometry to automatically identify ALS, demonstrating superior performance over existing techniques on the Toronto Neuroface dataset.

Contribution

The paper presents a new facial analysis approach using point graphs for early ALS detection, improving accuracy and efficiency over prior methods.

Findings

Outperformed state-of-the-art methods on Toronto Neuroface dataset

Demonstrated effectiveness of facial geometry analysis for ALS detection

Facilitated early diagnosis with a simple, cost-effective approach

Abstract

Identifying Amyotrophic Lateral Sclerosis (ALS) in its early stages is essential for establishing the beginning of treatment, enriching the outlook, and enhancing the overall well-being of those affected individuals. However, early diagnosis and detecting the disease's signs is not straightforward. A simpler and cheaper way arises by analyzing the patient's facial expressions through computational methods. When a patient with ALS engages in specific actions, e.g., opening their mouth, the movement of specific facial muscles differs from that observed in a healthy individual. This paper proposes Facial Point Graphs to learn information from the geometry of facial images to identify ALS automatically. The experimental outcomes in the Toronto Neuroface dataset show the proposed approach outperformed state-of-the-art results, fostering promising developments in the area.