Gait Patterns as Biomarkers: A Video-Based Approach for Classifying Scoliosis

TL;DR

This paper introduces a novel video-based gait analysis method for scoliosis detection, utilizing a large-scale dataset and deep learning models to enable non-invasive, accurate screening, addressing limitations of traditional diagnostic techniques.

Contribution

The study presents Scoliosis1K, the first large-scale video dataset for scoliosis classification, and develops ScoNet-MT, a multi-task deep learning model that improves diagnostic accuracy for practical use.

Findings

Gait patterns can serve as non-invasive biomarkers for scoliosis.

ScoNet-MT achieves promising diagnostic accuracy.

The dataset and models are publicly available.

Abstract

Scoliosis presents significant diagnostic challenges, particularly in adolescents, where early detection is crucial for effective treatment. Traditional diagnostic and follow-up methods, which rely on physical examinations and radiography, face limitations due to the need for clinical expertise and the risk of radiation exposure, thus restricting their use for widespread early screening. In response, we introduce a novel video-based, non-invasive method for scoliosis classification using gait analysis, effectively circumventing these limitations. This study presents Scoliosis1K, the first large-scale dataset specifically designed for video-based scoliosis classification, encompassing over one thousand adolescents. Leveraging this dataset, we developed ScoNet, an initial model that faced challenges in handling the complexities of real-world data. This led to the development of ScoNet-MT, an enhanced model incorporating multi-task learning, which demonstrates promising diagnostic accuracy for practical applications. Our findings demonstrate that gait can serve as a non-invasive biomarker for scoliosis, revolutionizing screening practices through deep learning and setting a precedent for non-invasive diagnostic methodologies. The dataset and code are publicly available at https://zhouzi180.github.io/Scoliosis1K/.