Automatic Classification of Neuromuscular Diseases in Children Using Photoacoustic Imaging

TL;DR

This study explores using deep learning on photoacoustic and ultrasound images to automatically classify neuromuscular diseases in children, aiming for faster, more reliable diagnosis of conditions like DMD and SMA.

Contribution

It demonstrates the feasibility of deep learning classifiers based on VGG16 for differentiating healthy and diseased muscle tissue in pediatric neuromuscular diseases.

Findings

Achieved over 86% accuracy in 3-class classification

Proves potential for early diagnosis and monitoring of NMDs

Supports use of photoacoustic imaging with deep learning

Abstract

Neuromuscular diseases (NMDs) cause a significant burden for both healthcare systems and society. They can lead to severe progressive muscle weakness, muscle degeneration, contracture, deformity and progressive disability. The NMDs evaluated in this study often manifest in early childhood. As subtypes of disease, e.g. Duchenne Muscular Dystropy (DMD) and Spinal Muscular Atrophy (SMA), are difficult to differentiate at the beginning and worsen quickly, fast and reliable differential diagnosis is crucial. Photoacoustic and ultrasound imaging has shown great potential to visualize and quantify the extent of different diseases. The addition of automatic classification of such image data could further improve standard diagnostic procedures. We compare deep learning-based 2-class and 3-class classifiers based on VGG16 for differentiating healthy from diseased muscular tissue. This work shows promising results with high accuracies above 0.86 for the 3-class problem and can be used as a proof of concept for future approaches for earlier diagnosis and therapeutic monitoring of NMDs.