Leveraging Gait Patterns as Biomarkers: An attention-guided Deep Multiple Instance Learning Network for Scoliosis Classification

2025-04-04

AI Summary

Scoliosis is challenging to detect early; conventional X-ray screening entails ionizing radiation exposure and relies heavily on expert interpretation, hindering large-scale adolescent screening. To address this, we propose the first non-invasive gait-based biomarker identification framework for early scoliosis screening—Gait-MIL—a novel attention-guided deep multiple instance learning architecture that jointly models gait sequences and disentangles biomechanically relevant features. Evaluated on the first large-scale gait-based scoliosis classification dataset, Gait-MIL achieves state-of-the-art performance, significantly improving accuracy for ambiguous “Neutral” cases and demonstrating robustness under severe class imbalance. The framework enables high-throughput, low-barrier community-level screening, eliminating both radiation exposure and dependence on clinical expertise.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Scoliosis is a spinal curvature disorder that is difficult to detect early and can compress the chest cavity, impacting respiratory function and cardiac health. Especially for adolescents, delayed detection and treatment result in worsening compression. Traditional scoliosis detection methods heavily rely on clinical expertise, and X-ray imaging poses radiation risks, limiting large-scale early screening. We propose an Attention-Guided Deep Multi-Instance Learning method (Gait-MIL) to effectively capture discriminative features from gait patterns, which is inspired by ScoNet-MT's pioneering use of gait patterns for scoliosis detection. We evaluate our method on the first large-scale dataset based on gait patterns for scoliosis classification. The results demonstrate that our study improves the performance of using gait as a biomarker for scoliosis detection, significantly enhances detection accuracy for the particularly challenging Neutral cases, where subtle indicators are often overlooked. Our Gait-MIL also performs robustly in imbalanced scenarios, making it a promising tool for large-scale scoliosis screening.

Problem

• Early detection of scoliosis using gait patterns
• Reducing reliance on X-rays and clinical expertise
• Improving accuracy in challenging Neutral cases

Innovation

• Attention-Guided Deep Multi-Instance Learning
• Gait patterns as biomarkers
• Robust in imbalanced scenarios