Deep Learning of Ultrasound Imaging for Evaluating Ambulatory Function of Individuals with Duchenne Muscular Dystrophy.

Ai-Ho Liao,Jheng-Ru Chen,Po-Hsiang Tsui,Chun-Hao Lu,Shi-Hong Liu,Chia-Wei Lin,Jeng-Yi Shieh,Wen-Chin Weng

doi:10.3390/diagnostics11060963

Abstract

Duchenne muscular dystrophy (DMD) results in loss of ambulation and premature death. Ultrasound provides real-time, safe, and cost-effective routine examinations. Deep learning allows the automatic generation of useful features for classification. This study utilized deep learning of ultrasound imaging for classifying patients with DMD based on their ambulatory function. A total of 85 individuals (including ambulatory and nonambulatory subjects) underwent ultrasound examinations of the gastrocnemius for deep learning of image data using LeNet, AlexNet, VGG-16, VGG-16TL, VGG-19, and VGG-19TL models (the notation TL indicates fine-tuning pretrained models). Gradient-weighted class activation mapping (Grad-CAM) was used to visualize features recognized by the models. The classification performance was evaluated using the confusion matrix and receiver operating characteristic (ROC) curve analysis. The results show that each deep learning model endows muscle ultrasound imaging with the ability to enable DMD evaluations. The Grad-CAMs indicated that boundary visibility, muscular texture clarity, and posterior shadowing are relevant sonographic features recognized by the models for evaluating ambulatory function. Of the proposed models, VGG-19 provided satisfying classification performance (the area under the ROC curve: 0.98; accuracy: 94.18%) and feature recognition in terms of physical characteristics. Deep learning of muscle ultrasound is a potential strategy for DMD characterization.

Highlights

Duchenne muscular dystrophy (DMD), an X-linked recessive condition, is a rare genetic disorder caused by the absence of functional dystrophin proteins due to gene mutations [1]
This study has demonstrated the value of deep learning in muscle ultrasound evaluations of individuals with DMD by clinical data analysis
The results indicate that the basic architectures and pretrained convolutional neural network (CNN) models performed well in differentiating individuals with ambulatory and nonambulatory DMD

Summary

Introduction

Duchenne muscular dystrophy (DMD), an X-linked recessive condition, is a rare genetic disorder caused by the absence of functional dystrophin proteins due to gene mutations [1]. Affected boys initially exhibit progressive muscle weakness of the lower proximal extremities [3]. The gradual muscle tissue loss and motor function deterioration eventually lead to ambulation loss, with respiratory and cardiac failure at the end stage of the disease [4,5]. Multidisciplinary care and health management are useful strategies to prolong lifespan, improve quality of life, and reduce complications [4]. Several drugs, including corticosteroids, have been conditionally approved for their potential effect on muscle strength and function [6]. Noninvasive approaches that reliably evaluate DMD are required to support different integrated care plans

Methods

Discussion

Conclusion