Abstract
Neuromuscular disorders are rare diseases for which few therapeutic strategies currently exist. Assessment of therapeutic strategies efficiency is limited by the lack of biomarkers sensitive to the slow progression of neuromuscular diseases (NMD). Magnetic resonance imaging (MRI) has emerged as a tool of choice for the development of qualitative scores for the study of NMD. The recent emergence of quantitative MRI has enabled to provide quantitative biomarkers more sensitive to the evaluation of pathological changes in muscle tissue. However, in order to extract these biomarkers from specific regions of interest, muscle segmentation is mandatory. The time-consuming aspect of manual segmentation has limited the evaluation of these biomarkers on large cohorts. In recent years, several methods have been proposed to make the segmentation step automatic or semi-automatic. The purpose of this study was to review these methods and discuss their reliability, reproducibility, and limitations in the context of NMD. A particular attention has been paid to recent deep learning methods, as they have emerged as an effective method of image segmentation in many other clinical contexts.
Highlights
Neuromuscular pathologies are rare diseases that can occur in both children and adults
This review highlighted the lack of fully automated approaches that could produce accurate segmentations of muscle images of patients with neuromuscular disorders
The few validated methods that addressed the difficulty of segmenting images with severe infiltrated muscles were proposed for the whole muscle only
Summary
Neuromuscular pathologies are rare diseases that can occur in both children and adults. A few limitations has to be acknowledged for these kinds of methods They are still time consuming and require a manual initialization so that reliable full automatic segmentation methods are still warranted for individual muscles. Manual segmentation methods are not applicable for 3D datasets and the follow-up of neuromuscular diseases They have been recognized as time consuming (5 h per subject for the 3D manual segmentation of 4 muscles) and operator dependent (3.1% volume error for the quadriceps femoris in healthy subjects) [9]. We introduce insights into semi-automatic methods that could potentially break the barrier between research and clinics These methods could provide clinicians with userfriendly tools that generate biomarkers for individual muscles over an entire 3D dataset. The emerging segmentation methods based on deep learning approaches have been included in a dedicated section as they are still emerging
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
