DATASET for "Deep learning segmentation of transverse musculoskeletal ultrasound images for neuromuscular disease assessment"

Here we provide the entire dataset and code for the article "Deep learning segmentation of transverse musculoskeletal ultrasound images for neuromuscular disease assessment" published in Computers in Biology and Medicine (DOI: 10.1016/j.compbiomed.2021.104623).
Any results obtained using the published dataset MUST cite the original research article (https://www.sciencedirect.com/science/article/abs/pii/S0010482521004170). See the ReadMe file "readme.txt" for all details.

Abstract:
"Ultrasound imaging is a patient-friendly and robust technique for studying physiological and pathological muscles. An automatic deep learning (DL) system for the analysis of ultrasound images could be useful to support an expert operator, allowing the study of large datasets requiring less human interaction. The purpose of this study is to present a deep learning algorithm for the cross-sectional area (CSA) segmentation in transverse musculoskeletal ultrasound images, providing a quantitative grayscale analysis which is useful for studying muscles, and to validate the results in a large dataset. The dataset included 3917 images of biceps brachii, tibialis anterior and gastrocnemius medialis acquired on 1283 subjects (mean age 50 years ± 21, 729 male). The algorithm was based on multiple deep-learning architectures, and its performance was compared to a manual expert segmentation. We compared the mean grayscale value inside the automatic and manual CSA using Bland-Altman plots and a correlation analysis. Classification in healthy and abnormal muscles between automatic and manual segmentation were compared using the grayscale value z-scores. In the test set, a Precision of 0.88 ± 0.12 and a Recall of 0.92 ± 0.09 was achieved. The network segmentation performance was slightly less in abnormal muscles, without a loss of discrimination between healthy and abnormal muscle images. Bland-Altman plots showed no clear trend in the error distribution and the two readings have a 0.99 Pearson’s correlation coefficient (p<0.001, test set). The ICC(A,1) calculated between the z-score readings was 0.99. The algorithm achieves robust CSA segmentation performance and gives mean grayscale level information comparable to a manual operator. This could provide a helpful tool for clinicians in neuromuscular disease diagnosis and follow-up. The entire dataset and code are made available for the research community."

本研究公开了发表于《生物医学中的计算机（Computers in Biology and Medicine）》（DOI: 10.1016/j.compbiomed.2021.104623）的论文《深度学习分割横向肌肉骨骼超声图像用于神经肌肉疾病评估》的完整数据集与代码。
凡使用本公开数据集所得研究成果，必须引用该原创研究论文（https://www.sciencedirect.com/science/article/abs/pii/S0010482521004170）。完整细节请参阅readme.txt文件。

摘要：
超声成像是一种患者友好且稳定性优异的技术，可用于研究生理与病理状态下的肌肉。用于超声图像分析的自动化深度学习（Deep Learning, DL）系统可辅助专业操作人员完成分析工作，能够支持对大规模数据集的研究，且所需人工交互更少。本研究旨在提出一种针对横向肌肉骨骼超声图像的横截面积（Cross-Sectional Area, CSA）分割深度学习算法，提供可用于肌肉研究的定量灰度分析方法，并在大规模数据集上验证算法性能。
本数据集包含1283名受试者的3917张肱二头肌、胫骨前肌及内侧腓肠肌超声图像，受试者平均年龄为50岁±21岁，其中男性729名。
本算法基于多种深度学习架构构建，并将算法分割结果与专家手动分割结果进行对比。我们通过Bland-Altman图与相关分析，对比了自动与手动分割区域内的平均灰度值；通过灰度值Z评分，对比了自动与手动分割对肌肉健康与异常状态的分类结果。
在测试集上，本算法的精确率（Precision）为0.88±0.12，召回率（Recall）为0.92±0.09。异常肌肉的网络分割性能略低于健康肌肉，但并未影响健康与异常肌肉图像的区分能力。Bland-Altman图显示误差分布无明显趋势，两种标注结果的皮尔逊相关系数（Pearson’s Correlation Coefficient）为0.99（p<0.001，测试集）。Z评分结果的组内相关系数ICC(A,1)为0.99。
本算法可实现稳定可靠的CSA分割，所得平均灰度水平信息与人工操作结果相当，可为临床医生开展神经肌肉疾病诊断与随访工作提供有力辅助工具。本研究的完整数据集与代码已向全球科研社区公开。