Abstract:Severe spinal cord injury (SCI) leads to skeletal muscle atrophy and adipose tissue infiltration in the skeletal muscle, which can result in compromised muscle mechanical output and lead to health-related complications. In this study, we developed a novel automatic 3-D approach for volumetric segmentation and quantitative assessment of thigh Magnetic Resonance Imaging (MRI) volumes in individuals with chronic SCI as well as non-disabled individuals. In this framework, subcutaneous adipose tissue, inter-muscula… Show more
“…Our method shows advantages compared to other studies that tackled this challenging task in recent years [21][22][23][24][25]. Kemnitz et al [21] developed a semiautomated thigh muscle segmentation method using an active shape model.…”
Section: Discussionmentioning
confidence: 99%
“…They segmented the entire muscle region without distinguishing any muscle groups. Mesbah et al [ 24 ] segmented three thigh muscle groups on the fat and water images utilizing a 3-D Joint Markov Gibbs Random Field model. The approach was performed on the preselected 50 central slices in a total of seven steps, which might make it difficult to apply in clinical settings.…”
Section: Discussionmentioning
confidence: 99%
“…Such a process can lower the accuracy and reproducibility, which is also not feasible for clinical adoption. Although recent studies developed semiautomated or automated algorithms [21][22][23][24][25], they are either based on nonquantitative MRI or difficult to apply in clinical settings [26]. A faster, simpler and fully automated thigh muscle segmentation method for reproducible fat fraction quantification is highly desired.…”
Background
Time-efficient and accurate whole volume thigh muscle segmentation is a major challenge in moving from qualitative assessment of thigh muscle MRI to more quantitative methods. This study developed an automated whole thigh muscle segmentation method using deep learning for reproducible fat fraction quantification on fat–water decomposition MRI.
Results
This study was performed using a public reference database (Dataset 1, 25 scans) and a local clinical dataset (Dataset 2, 21 scans). A U-net was trained using 23 scans (16 from Dataset 1, seven from Dataset 2) to automatically segment four functional muscle groups: quadriceps femoris, sartorius, gracilis and hamstring. The segmentation accuracy was evaluated on an independent testing set (3 × 3 repeated scans in Dataset 1 and four scans in Dataset 2). The average Dice coefficients between manual and automated segmentation were > 0.85. The average percent difference (absolute) in volume was 7.57%, and the average difference (absolute) in mean fat fraction (meanFF) was 0.17%. The reproducibility in meanFF was calculated using intraclass correlation coefficients (ICCs) for the repeated scans, and automated segmentation produced overall higher ICCs than manual segmentation (0.921 vs. 0.902). A preliminary quantitative analysis was performed using two-sample t test to detect possible differences in meanFF between 14 normal and 14 abnormal (with fat infiltration) thighs in Dataset 2 using automated segmentation, and significantly higher meanFF was detected in abnormal thighs.
Conclusions
This automated thigh muscle segmentation exhibits excellent accuracy and higher reproducibility in fat fraction estimation compared to manual segmentation, which can be further used for quantifying fat infiltration in thigh muscles.
“…Our method shows advantages compared to other studies that tackled this challenging task in recent years [21][22][23][24][25]. Kemnitz et al [21] developed a semiautomated thigh muscle segmentation method using an active shape model.…”
Section: Discussionmentioning
confidence: 99%
“…They segmented the entire muscle region without distinguishing any muscle groups. Mesbah et al [ 24 ] segmented three thigh muscle groups on the fat and water images utilizing a 3-D Joint Markov Gibbs Random Field model. The approach was performed on the preselected 50 central slices in a total of seven steps, which might make it difficult to apply in clinical settings.…”
Section: Discussionmentioning
confidence: 99%
“…Such a process can lower the accuracy and reproducibility, which is also not feasible for clinical adoption. Although recent studies developed semiautomated or automated algorithms [21][22][23][24][25], they are either based on nonquantitative MRI or difficult to apply in clinical settings [26]. A faster, simpler and fully automated thigh muscle segmentation method for reproducible fat fraction quantification is highly desired.…”
Background
Time-efficient and accurate whole volume thigh muscle segmentation is a major challenge in moving from qualitative assessment of thigh muscle MRI to more quantitative methods. This study developed an automated whole thigh muscle segmentation method using deep learning for reproducible fat fraction quantification on fat–water decomposition MRI.
Results
This study was performed using a public reference database (Dataset 1, 25 scans) and a local clinical dataset (Dataset 2, 21 scans). A U-net was trained using 23 scans (16 from Dataset 1, seven from Dataset 2) to automatically segment four functional muscle groups: quadriceps femoris, sartorius, gracilis and hamstring. The segmentation accuracy was evaluated on an independent testing set (3 × 3 repeated scans in Dataset 1 and four scans in Dataset 2). The average Dice coefficients between manual and automated segmentation were > 0.85. The average percent difference (absolute) in volume was 7.57%, and the average difference (absolute) in mean fat fraction (meanFF) was 0.17%. The reproducibility in meanFF was calculated using intraclass correlation coefficients (ICCs) for the repeated scans, and automated segmentation produced overall higher ICCs than manual segmentation (0.921 vs. 0.902). A preliminary quantitative analysis was performed using two-sample t test to detect possible differences in meanFF between 14 normal and 14 abnormal (with fat infiltration) thighs in Dataset 2 using automated segmentation, and significantly higher meanFF was detected in abnormal thighs.
Conclusions
This automated thigh muscle segmentation exhibits excellent accuracy and higher reproducibility in fat fraction estimation compared to manual segmentation, which can be further used for quantifying fat infiltration in thigh muscles.
“…Very recently, Mesbah et al ( 53 ) introduced a Markov random field model combining appearance and spatial models with the prior shape information from atlases and so in order to segment the three main muscle groups of the thigh. They reported good DSC scores (0.89 ± 0.05 to 0.95 ± 0.03) but the HD scores were of poor quality with an average ranging from 10.51 ± 6.37 to 31.53 ± 14.24 mm for the medial compartment.…”
Section: Evolution Of Segmentation Strategiesmentioning
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.
“…Short axis length and short axis: long axis ratio on MRI correlate with distal motor latency (DML) results, and may be used as a less invasive confirmatory findings [9]. Automatic segmentation using machine learning algorithms has shown high levels of accuracy in thigh muscles secondary to chronic spinal cord injuries [19]. It is possible that other muscle groups with denervation atrophy may be similarly amenable to evaluation using machine learning algorithms.…”
A 42-year-old female, who worked as a full-time secretary for 15 years, was referred by her family physician to the neurology department with persistent pain, increasing numbness, and tingling in her right wrist and hand. The symptoms started intermittently some months prior, and worsened in the last 3 weeks. The pain and tingling increased in intensity during wrist flexion, and radiated to the first three fingers, and occasionally to the fourth. At the time of consultation, she was unable to grip or hold objects with her right hand. She did not recall any direct trauma to the wrist, and had no history of systemic disease or inflammatory disorders. She had no fever or other signs of infection, and had not traveled out of the country for at least 5 years. On physical examination, there was no swelling, discoloration, or scars. Pain and tingling were reproducible by wrist
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.