A Two-stream Convolutional Network for Musculoskeletal and Neurological Disorders Prediction

TL;DR

This paper presents a two-stream convolutional neural network that combines joint position and inter-joint features for improved prediction of musculoskeletal and neurological disorders from walking motion data, achieving high accuracy on a benchmark dataset.

Contribution

The proposed two-stream framework explicitly models both joint and inter-joint features, enhancing disorder prediction from small-scale medical datasets.

Findings

Achieved 95.56% prediction accuracy, outperforming existing methods.

Validated the effectiveness of dual-stream architecture with mid-layer fusion.

Demonstrated improved diagnosis performance on a 3D skeleton motion dataset.

Abstract

Musculoskeletal and neurological disorders are the most common causes of walking problems among older people, and they often lead to diminished quality of life. Analyzing walking motion data manually requires trained professionals and the evaluations may not always be objective. To facilitate early diagnosis, recent deep learning-based methods have shown promising results for automated analysis, which can discover patterns that have not been found in traditional machine learning methods. We observe that existing work mostly applies deep learning on individual joint features such as the time series of joint positions. Due to the challenge of discovering inter-joint features such as the distance between feet (i.e. the stride width) from generally smaller-scale medical datasets, these methods usually perform sub-optimally. As a result, we propose a solution that explicitly takes both individual joint features and inter-joint features as input, relieving the system from the need of discovering more complicated features from small data. Due to the distinctive nature of the two types of features, we introduce a two-stream framework, with one stream learning from the time series of joint position and the other from the time series of relative joint displacement. We further develop a mid-layer fusion module to combine the discovered patterns in these two streams for diagnosis, which results in a complementary representation of the data for better prediction performance. We validate our system with a benchmark dataset of 3D skeleton motion that involves 45 patients with musculoskeletal and neurological disorders, and achieve a prediction accuracy of 95.56%, outperforming state-of-the-art methods.