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

• Published in: Computers in biology and medicine 2021-08, Vol.135, p.104623-104623, Article 104623
• Main Authors: Marzola, Francesco, van Alfen, Nens, Doorduin, Jonne, Meiburger, Kristen M.
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial intelligence; Cartilage; Clinical medicine; Computer aided analysis; Convolutional neural network; Correlation analysis; Correlation coefficient; Correlation coefficients; Datasets; Deep learning; Disease; Gray scale; Image acquisition; Image processing; Image segmentation; Machine learning; Mathematical analysis; Medical imaging; Muscles; Neural networks; Neurology; Neuromuscular diseases; Open source software; Regression analysis; Robustness; Teaching methods; Test sets; Ultrasonic imaging; Ultrasonography; Ultrasound
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2021.104623

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 ± 21 years, 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