Using MRI to quantify skeletal muscle pathology in Duchenne muscular dystrophy: A systematic mapping review

Alic, Lejla; Griffin, John F.; Eresen, Aydın; Kornegay, Joe N.; Ji, Jim

doi:10.1002/mus.27133

Cited by 12 publications

(5 citation statements)

References 153 publications

(486 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Quantitative magnetic resonance imaging (qMRI) provides promising surrogate biomarkers in the evaluation of disease progression and monitoring of therapeutic options in neuromuscular diseases (NMD) [1,2]. This non-invasive technique can reveal subclinical changes in muscle pathophysiology which can precede changes in muscle function assessed by clinical examination [3].…”

Section: Introductionmentioning

confidence: 99%

3D Automated Segmentation of Lower Leg Muscles Using Machine Learning on a Heterogeneous Dataset

et al. 2021

View full text Add to dashboard Cite

Quantitative MRI combines non-invasive imaging techniques to reveal alterations in muscle pathophysiology. Creating muscle-specific labels manually is time consuming and requires an experienced examiner. Semi-automatic and fully automatic methods reduce segmentation time significantly. Current machine learning solutions are commonly trained on data from healthy subjects using homogeneous databases with the same image contrast. While yielding high Dice scores (DS), those solutions are not applicable to different image contrasts and acquisitions. Therefore, the aim of our study was to evaluate the feasibility of automatic segmentation of a heterogeneous database. To create a heterogeneous dataset, we pooled lower leg muscle images from different studies with different contrasts and fields-of-view, containing healthy controls and diagnosed patients with various neuromuscular diseases. A second homogenous database with uniform contrasts was created as a subset of the first database. We trained three 3D-convolutional neuronal networks (CNN) on those databases to test performance as compared to manual segmentation. All networks, training on heterogeneous data, were able to predict seven muscles with a minimum average DS of 0.75. U-Net performed best when trained on the heterogeneous dataset (DS: 0.80 ± 0.10, AHD: 0.39 ± 0.35). ResNet and DenseNet yielded higher DS, when trained on a heterogeneous dataset (both DS: 0.86), as compared to a homogeneous dataset (ResNet DS: 0.83, DenseNet DS: 0.76). In conclusion, a CNN trained on a heterogeneous dataset achieves more accurate labels for predicting a heterogeneous database of lower leg muscles than a CNN trained on a homogenous dataset. We propose that a large heterogeneous database is needed, to make automated segmentation feasible for different kinds of image acquisitions.

show abstract

Section: Introductionmentioning

confidence: 99%

3D Automated Segmentation of Lower Leg Muscles Using Machine Learning on a Heterogeneous Dataset

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Demonstration of improved or stabilised muscle function is highly desirable (to reflect reduced myonecrosis), although function is usually a longerterm consequence of drug benefit in clinical trials. Ideally, this is done in conjunction with some analysis of muscle composition to quantify the progression of the dystropathology over time: this can be achieved using non-invasive magnetic resonance imaging [81], although specialised facilities are required and this can be expensive and time consuming.…”

Section: Biomarkers To Rapidly Assess Drug Efficacymentioning

confidence: 99%

Considering the Promise of Vamorolone for Treating Duchenne Muscular Dystrophy

Grounds,

Lloyd

2023

Journal of Neuromuscular Diseases

View full text Add to dashboard Cite

This commentary provides an independent consideration of data related to the drug vamorolone (VBP15) as an alternative steroid proposed for treatment of Duchenne muscular dystrophy (DMD). Glucocorticoids such as prednisone and deflazacort have powerful anti-inflammatory benefits and are the standard of care for DMD, but their long-term use can result in severe adverse side effects; thus, vamorolone was designed as a unique dissociative steroidal anti-inflammatory drug, to retain efficacy and minimise these adverse effects. Extensive clinical trials (ongoing) have investigated the use of vamorolone for DMD, with two trials also for limb-girdle muscular dystrophies including dysferlinopathy (current), plus a variety of pre-clinical trials published. Vamorolone looks very promising, with similar efficacy and some reduced adverse effects (e.g., related to height) compared with other glucocorticoids, specifically prednisone/prednisolone, although it has not yet been directly compared with deflazacort. Of particular interest to clarify is the optimal clinical dose and other aspects of vamorolone that are proposed to provide additional benefits for membranes of dystrophic muscle: to stabilise and protect the sarcolemma from damage and enhance repair. The use of vamorolone (and other glucocorticoids) needs to be evaluated in terms of overall long-term efficacy and cost, and also in comparison with many candidate non-steroidal drugs with anti-inflammatory and other benefits for DMD.

show abstract

“…Muscle MRI has been increasingly used for quantification of muscle properties in longitudinal studies to evaluate efficacy of therapeutic interventions or to document disease effects over time [ [163] , [164] , [165] , [166] , [167] , [168] , [169] , [170] ] Only a few multicenter trials have been published [ [171] , [172] , [173] , [174] , [175] , [176] ]. Outcome of clinical trials is typically the comparison of percentage change over time between a treated and a control group for a given quantitative parameter such as PDFF.…”

Section: Muscle Imaging In Clinical Trialsmentioning

confidence: 99%

Magnetic resonance imaging techniques for the quantitative analysis of skeletal muscle: State of the art

Engelke,

Chaudry,

Gast

et al. 2023

Journal of Orthopaedic Translation

View full text Add to dashboard Cite

Using MRI to quantify skeletal muscle pathology in Duchenne muscular dystrophy: A systematic mapping review

Cited by 12 publications

References 153 publications

3D Automated Segmentation of Lower Leg Muscles Using Machine Learning on a Heterogeneous Dataset

3D Automated Segmentation of Lower Leg Muscles Using Machine Learning on a Heterogeneous Dataset

Considering the Promise of Vamorolone for Treating Duchenne Muscular Dystrophy

Magnetic resonance imaging techniques for the quantitative analysis of skeletal muscle: State of the art

Contact Info

Product

Resources

About