Automatic Assessment of Functional Movement Screening Exercises with Deep Learning Architectures

TL;DR

This paper presents a deep learning system using CNN, LSTM, and Dense layers to automatically evaluate functional movement exercises from IMU data, aiming to support physiotherapy with high accuracy.

Contribution

It introduces a novel neural network architecture optimized for IMU-based exercise assessment and compares different CNN structures for improved performance.

Findings

Achieves convincing classification of known subjects' repetitions

Performs less well on data from unknown subjects

Performance varies significantly across different exercises

Abstract

(1) Background: The success of physiotherapy depends on the regular and correct performance of movement exercises. A system that automatically evaluates these could support the therapy. Previous approaches in this area rarely rely on Deep Learning methods and do not yet fully use their potential. (2) Methods: Using a measurement system consisting of 17 IMUs, a dataset of four Functional Movement Screening (FMS) exercises is recorded. Exercise execution is evaluated by physiotherapists using the FMS criteria. This dataset is used to train a neural network that assigns the correct FMS score to an exercise repetition. We use an architecture consisting of CNN, LSTM and Dense layers. Based on this framework, we apply various methods to optimize the performance of the network. For the optimization, we perform a extensive hyperparameter optimization. In addition, we are comparing different CNN structures that have been specifically adapted for use with IMU data. Finally, the developed network is trained with the data of different FMS exercises and the performance is compared. (3) Results: The evaluation shows that the presented approach achieves a convincing performance in the classification of unknown repetitions of already known subjects. However, the trained network is yet unable to achieve consistent performance on the data of a previously unknown subjects. Additionally, it can be seen that the performance of the network differs significantly depending on the exercise it is trained for.