Deep learning segmentation of transverse musculoskeletal ultrasound images for neuromuscular disease assessment. (August 2021)

• Record Type: Journal Article
• Authors: Marzola, Francesco; van Alfen, Nens; Doorduin, Jonne; Meiburger, Kristen M.
• Is Part Of: Computers in biology and medicine. Volume 135(2021)
• Publication Date: 2021-08
• Subjects: Computer aided analysis -- Convolutional neural network -- Image segmentation -- Neurology -- Open source software -- Ultrasonography; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2021.104623
• Languages: English
• ISSNs: 0010-4825

Abstract

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 ± 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 < 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. Graphical abstract: Image 1 Highlights: A deep learning method for cross-sectional area segmentation in transverse musculoskeletal ultrasound images is presented. The developed and validated method is a helpful tool for clinicians in neuromuscular disease diagnosis and follow-up. A large database of 3917 images including 3 muscles (BB, TA and GM) acquired on 1283 patients is employed. The entire dataset and code are made available for the research community.