1
|
Compound muscle action potential of whole-forearm flexors: A clinical biomarker for inclusion body myositis. Clin Neurophysiol Pract 2024; 9:162-167. [PMID: 38707484 PMCID: PMC11066998 DOI: 10.1016/j.cnp.2024.03.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2023] [Revised: 03/13/2024] [Accepted: 03/18/2024] [Indexed: 05/07/2024] Open
Abstract
Objective This study aimed to investigate the potential of whole-forearm flexor muscle (WFFM) compound muscle action potential (CMAP) as a quantitative biomarker for inclusion body myositis (IBM) pathology. Methods We prospectively enrolled 14 consecutive patients (10 men and 4 women) diagnosed with IBM based on muscle biopsies. We evaluated the baseline-to-peak amplitude of the WFFM CMAP and other quantitative parameters, including grip and pinch strength, Inclusion Body Myositis Functional Rating Scale (IBMFRS) score, and other routine muscle CMAP amplitudes. Results The WFFM CMAP was strongly correlated with disease duration and the IBMFRS score. The WFFM CMAP on the more affected side was lower than that on the less affected side. Furthermore, grip power was strongly correlated with the WFFM CMAP, whereas lateral pinch strength was strongly correlated with the WFFM and first dorsal interosseous CMAPs. The 3-point pinch strength was also correlated with the WFFM CMAP. Conclusions This study demonstrates that the WFFM CMAP may serve as a biomarker of severity in IBM. Significance Identification of this biomarker can support drug development, diagnosis, prognosis, and treatment options for patients with IBM.
Collapse
|
2
|
255th ENMC workshop: Muscle imaging in idiopathic inflammatory myopathies. 15th January, 16th January and 22nd January 2021 - virtual meeting and hybrid meeting on 9th and 19th September 2022 in Hoofddorp, The Netherlands. Neuromuscul Disord 2023; 33:800-816. [PMID: 37770338 DOI: 10.1016/j.nmd.2023.08.014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2023] [Revised: 08/20/2023] [Accepted: 08/25/2023] [Indexed: 09/30/2023]
Abstract
The 255th ENMC workshop on Muscle Imaging in Idiopathic Inflammatory myopathies (IIM) aimed at defining recommendations concerning the applicability of muscle imaging in IIM. The workshop comprised of clinicians, researchers and people living with myositis. We aimed to achieve consensus on the following topics: a standardized protocol for the evaluation of muscle images in various types of IIMs; the exact parameters, anatomical localizations and magnetic resonance imaging (MRI) techniques; ultrasound as assessment tool in IIM; assessment methods; the pattern of muscle involvement in IIM subtypes; the application of MRI as biomarker in follow-up studies and clinical trials, and the place of MRI in the evaluation of swallowing difficulty and cardiac manifestations. The following recommendations were formulated: In patients with suspected IIM, muscle imaging is highly recommended to be part of the initial diagnostic workup and baseline assessment. MRI is the preferred imaging modality due to its sensitivity to both oedema and fat accumulation. Ultrasound may be used for suspected IBM. Repeat imaging should be considered if patients do not respond to treatment, if there is ongoing diagnostic uncertainty or there is clinical or laboratory evidence of disease relapse. Quantitative MRI is established as a sensitive biomarker in IBM and could be included as a primary or secondary outcome measure in early phase clinical trials, or as a secondary outcome measure in late phase clinical trials. Finally, a research agenda was drawn up.
Collapse
|
3
|
Imaging biomarkers in the idiopathic inflammatory myopathies. Front Neurol 2023; 14:1146015. [PMID: 37181575 PMCID: PMC10166883 DOI: 10.3389/fneur.2023.1146015] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2023] [Accepted: 04/03/2023] [Indexed: 05/16/2023] Open
Abstract
Idiopathic inflammatory myopathies (IIMs) are a group of acquired muscle diseases with muscle inflammation, weakness, and other extra-muscular manifestations. IIMs can significantly impact the quality of life, and management of IIMs often requires a multi-disciplinary approach. Imaging biomarkers have become an integral part of the management of IIMs. Magnetic resonance imaging (MRI), muscle ultrasound, electrical impedance myography (EIM), and positron emission tomography (PET) are the most widely used imaging technologies in IIMs. They can help make the diagnosis and assess the burden of muscle damage and treatment response. MRI is the most widely used imaging biomarker of IIMs and can assess a large volume of muscle tissue but is limited by availability and cost. Muscle ultrasound and EIM are easy to administer and can even be performed in the clinical setting, but they need further validation. These technologies may complement muscle strength testing and laboratory studies and provide an objective assessment of muscle health in IIMs. Furthermore, this is a rapidly progressing field, and new advances are going to equip care providers with a better objective assessment of IIMS and eventually improve patient management. This review discusses the current state and future direction of imaging biomarkers in IIMs.
Collapse
|
4
|
Abstract
Imaging is an important tool in the evaluation of idiopathic inflammatory myopathies. It plays a role in diagnosis, assessment of disease activity and follow-up, and as a non-invasive biomarker. Among the different modalities, nuclear magnetic resonance imaging (MRI), ultrasound (US), and positron emission tomography (PET) may have the most clinical utility in myositis. MRI is currently the best modality to evaluate skeletal muscle and provides excellent characterization of muscle edema and fat replacement through the use of T1-weighted and T2-weighted fat suppressed/STIR sequences. Although MRI can be read qualitatively for the presence of abnormalities, a more quantitative approach using Dixon sequences and the generation of water T2 parametric maps would be preferable for follow-up. Newer protocols such as diffusion-weighted imaging, functional imaging measures, and spectroscopy may be of interest to provide further insights into myositis. Despite the advantages of MRI, image acquisition is relatively time-consuming, expensive, and not accessible to all patients. The use of US to evaluate skeletal muscle in myositis is gaining interest, especially in chronic disease, where fat replacement and fibrosis are detected readily by this modality. Although easily deployed at the bedside, it is heavily dependent on operator experience to recognize disease states. Further, systematic characterization of muscle edema by US is still needed. PET provides valuable information on muscle function at a cellular level. Fluorodeoxyglucose (FDG-PET) has been the most common application in myositis to detect pathologic uptake indicative of inflammation. The use of neurodegenerative markers is now also being utilized for inclusion body myositis. These different modalities may prove to be complementary methods for myositis evaluation.
Collapse
|
5
|
Application of ultrasound in a case of eosinophilic fasciitis mimicking stiff-person syndrome. Neuromuscul Disord 2022; 32:590-593. [DOI: 10.1016/j.nmd.2022.05.009] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2021] [Revised: 04/21/2022] [Accepted: 05/16/2022] [Indexed: 11/16/2022]
|
6
|
Muscle Sonography in Inclusion Body Myositis: A Systematic Review and Meta-Analysis of 944 Measurements. Cells 2022; 11:cells11040600. [PMID: 35203250 PMCID: PMC8869828 DOI: 10.3390/cells11040600] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2021] [Revised: 01/28/2022] [Accepted: 02/04/2022] [Indexed: 01/14/2023] Open
Abstract
Inclusion body myositis (IBM) is a slowly progressive muscle weakness of distal and proximal muscles, which is diagnosed by clinical and histopathological criteria. Imaging biomarkers are inconsistently used and do not follow international standardized criteria. We conducted a systematic review and meta-analysis to investigate the diagnostic value of muscle ultrasound (US) in IBM compared to healthy controls. A systematic search of PubMed/MEDLINE, Scopus and Web of Science was performed. Articles reporting the use of muscle ultrasound in IBM, and published in peer-reviewed journals until 11 September 2021, were included in our study. Seven studies were included, with a total of 108 IBM and 171 healthy controls. Echogenicity between IBM and healthy controls, which was assessed by three studies, demonstrated a significant mean difference in the flexor digitorum profundus (FDP) muscle, which had a grey scale value (GSV) of 36.55 (95% CI, 28.65–44.45, p < 0.001), and in the gastrocnemius (GC), which had a GSV of 27.90 (95% CI 16.32–39.48, p < 0.001). Muscle thickness in the FDP showed no significant difference between the groups. The pooled sensitivity and specificity of US in the differentiation between IBM and the controls were 82% and 98%, respectively, and the area under the curve was 0.612. IBM is a rare disease, which is reflected in the low numbers of patients included in each of the studies and thus there was high heterogeneity in the results. Nevertheless, the selected studies conclusively demonstrated significant differences in echogenicity of the FDP and GC in IBM, compared to controls. Further high-quality studies, using standardized operating procedures, are needed to implement muscle ultrasound in the diagnostic criteria.
Collapse
|
7
|
Dancing muscles: the value of real-time ultrasound evaluation of muscle in myositis and mimics. Rheumatology (Oxford) 2021; 60:e275-e276. [PMID: 33502477 DOI: 10.1093/rheumatology/keab088] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
|
8
|
Abstract
A 23-year-old woman was admitted for slowly progressive proximal limb muscle weakness from childhood with elevated muscle enzyme levels. Although muscular diseases were suspected, an electromyogram showed remarkable neurogenic changes, and a muscle echogram indicated selective muscle involvement, including dissociation between the soleus and gastrocnemius, which was consistent with previous reports using magnetic resonance imaging (MRI). She was diagnosed with SMA type 3 following genetic testing, and nusinersen was soon initiated. An early diagnosis is mandatory to maximize the benefit of treatment. A muscle echogram may facilitate an early diagnosis in a non-invasive and time-saving manner compared to MRI.
Collapse
|
9
|
MRI and muscle imaging for idiopathic inflammatory myopathies. Brain Pathol 2021; 31:e12954. [PMID: 34043260 PMCID: PMC8412099 DOI: 10.1111/bpa.12954] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2021] [Accepted: 03/11/2021] [Indexed: 12/22/2022] Open
Abstract
Although idiopathic inflammatory myopathies (IIM) are a heterogeneous group of diseases nearly all patients display muscle inflammation. Originally, muscle biopsy was considered as the gold standard for IIM diagnosis. The development of muscle imaging led to revisiting not only the IIM diagnosis strategy but also the patients' follow-up. Different techniques have been tested or are in development for IIM including positron emission tomography, ultrasound imaging, ultrasound shear wave elastography, though magnetic resonance imaging (MRI) remains the most widely used technique in routine. Whereas guidelines on muscle imaging in myositis are lacking here we reviewed the relevance of muscle imaging for both diagnosis and myositis patients' follow-up. We propose recommendations about when and how to perform MRI on myositis patients, and we describe new techniques that are under development.
Collapse
|
10
|
Conventional ultrasound and elastography as imaging outcome tools in autoimmune myositis: A systematic review by the OMERACT ultrasound group. Semin Arthritis Rheum 2020; 51:661-676. [PMID: 33386164 DOI: 10.1016/j.semarthrit.2020.11.001] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2020] [Revised: 11/11/2020] [Accepted: 11/19/2020] [Indexed: 10/22/2022]
Abstract
AIMS To analyze whether there is sufficient data from published literature to demonstrate that ultrasound, including elastography, present good metric properties (truth, discrimination and feasibility) in autoimmune myositis (AIM). METHODS A population, intervention, comparator and outcome-structured (PICO) search was performed in Medline, Cochrane Library and Embase database from 01/01/1973 to 08/05/2019. The inclusion criteria required original research involving adult humans, reported in English, assessing ultrasound and elastography in patients with an AIM. Conference abstracts and computer-assisted diagnostics that focused on technique and not ultrasound domains were excluded. RESULTS Approximately 2670 articles were identified. Forty-one full-text articles were included in the final analysis. There were 551 AIM patients studied. Eighteen studies (43.9%) had a control group, of which 15 (63.3%) were healthy controls. The age of participants (including controls) varied from 18 to 86 years, and most were females (59%). Diagnosis of AIM was largely biopsy-proven, although some were derived through clinical presentation, positive clinical imaging (ultrasound or otherwise) and/or electromyography and steroid responsiveness. The features examined with ultrasound in the 41 included articles consisted of: muscle echogenicity, bulk, atrophy, architecture, power Doppler, perfusion characteristics, shear wave modulus, shear wave velocity, elasticity index and fasciculations. Twelve studies (29.2%) used quantitative methods to assess these characteristics, whilst others used semi-quantitative, dichotomous/binary and descriptive scoring systems. Criterion validity was met in 14 studies (12/14, 85.7%) and construct validity in 22 studies (22/25, 88.0%). Most published articles reported Level 3b to Level 5 evidence with varying degrees of bias. There was only one longitudinal study examining discrimination. Reliability and feasibility were under-reported. CONCLUSION This is the first systematic review studying the utility of ultrasound, including elastography, in AIM. There is some evidence for criterion and construct validity, suggesting that ultrasound may be a promising outcome measurement instrument in AIM. Agreement on the standardization of acquisition, and the definitions of target domains, is required. Additionally, further validation studies are required to determine discrimination, reliability and feasibility.
Collapse
|
11
|
Abstract
Purpose of Review The purpose of this review is to critically discuss the use of ultrasound in the evaluation of muscle disorders with a particular focus on the emerging use in inflammatory myopathies. Recent Findings In myopathies, pathologic muscle shows an increase in echogenicity. Muscle echogenicity can be assessed visually, semi-quantitatively, or quantitatively using grayscale analysis. The involvement of specific muscle groups and the pattern of increase in echogenicity can further point to specific diseases. In pediatric neuromuscular disorders, the value of muscle ultrasound for screening and diagnosis is well-established. It has also been found to be a responsive measure of disease change in muscular dystrophies. In chronic forms of myositis like inclusion body myositis, ultrasound is very suitable for detecting markedly increased echogenicity and atrophy in affected muscles. Acute cases of muscle edema show only a mild increase in echogenicity, which can also reverse with successful treatment. Summary Muscle ultrasound is an important imaging modality that is highly adaptable to study various muscle conditions. Although its diagnostic value for neuromuscular disorders is high, the evidence in myositis has only begun to accrue in earnest. Further systematic studies are needed, especially in its role for detecting muscle edema.
Collapse
|
12
|
Texture analysis of sonographic muscle images can distinguish myopathic conditions. THE JOURNAL OF MEDICAL INVESTIGATION 2020; 66:237-247. [PMID: 31656281 DOI: 10.2152/jmi.66.237] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022]
Abstract
Given the recent technological advent of muscle ultrasound (US), classification of various myopathic conditions could be possible, especially by mathematical analysis of muscular fine structure called texture analysis. We prospectively enrolled patients with three neuromuscular conditions and their lower leg US images were quantitatively analyzed by texture analysis and machine learning methodology in the following subjects : Inclusion body myositis (IBM) [N=11] ; myotonic dystrophy type 1 (DM1) [N=19] ; polymyositis/dermatomyositis (PM-DM) [N=21]. Although three-group analysis achieved up to 58.8% accuracy, two-group analysis of IBM plus PM-DM versus DM1 showed 78.4% accuracy. Despite the small number of subjects, texture analysis of muscle US followed by machine learning might be expected to be useful in identifying myopathic conditions. J. Med. Invest. 66 : 237-240, August, 2019.
Collapse
|
13
|
Ultrasound can differentiate inclusion body myositis from disease mimics. Muscle Nerve 2020; 61:783-788. [PMID: 32239702 PMCID: PMC7317807 DOI: 10.1002/mus.26875] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2019] [Revised: 03/20/2020] [Accepted: 03/27/2020] [Indexed: 11/26/2022]
Abstract
Introduction The diagnosis of inclusion body myositis (IBM) can be challenging, and its presentation can be confused with other forms of myositis or neuromuscular disorders. In this study we evaluate the ability of quantitative muscle ultrasound to differentiate between IBM and mimicking diseases. Methods Patients 50 years of age and older were included from two specialty centers. Muscle echogenicity and muscle thickness of four characteristically involved muscles in IBM were measured and compared with polymyositis (PM)/dermatomyositis (DM), other neuromuscular disorders, and healthy controls. Results Echogenicity was higher and muscle thickness generally lower in all four muscles in IBM compared with PM/DM and normal controls. When comparing IBM with the comparator groups, the flexor digitorum profundus was the most discriminative muscle. Discussion Ultrasound appears to be a good test to differentiate established IBM from PM/DM and neuromuscular controls, with value as a diagnostic tool for IBM.
Collapse
|
14
|
Imaging in dermatomyositis in adults and children. J Ultrason 2020; 20:e36-e42. [PMID: 32320164 PMCID: PMC7266069 DOI: 10.15557/jou.2020.0007] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2019] [Accepted: 03/02/2020] [Indexed: 11/29/2022] Open
Abstract
Dermatomyositis is a rare autoimmune disorder in which an abnormal immune reaction against vascular endothelial antigens and endomysium leads to obstructive inflammatory changes of blood vessels within muscles, skin and other tissues. The disease is characterized by involvement of muscles, and less frequently of other systems, including the gastrointestinal tract, heart and lungs. Dermatomyositis may be diagnosed based on a detailed patient history, through clinical examination, detection of characteristic physical findings and certain specialized tests. Additional imaging studies may be performed to aid in the diagnosis. These include magnetic resonance imaging and ultrasound of the affected muscles. Magnetic resonance imaging is the modality of choice in the diagnostic work-up and monitoring of dermatomyositis affecting muscles, fasciae, and the subcutis. It may recognize acute inflammatory edematous changes in the affected muscles as well fatty replacement and atrophy. The role of ultrasound to diagnose and follow up muscle echogenicity, vascularity, elasticity and volume during treatment has increased over the last years in both adults and children. Ultrasound is used to discriminate between high and low disease activity, may show features of subclinical disease and may be used to confirm remission.
Collapse
|
15
|
Abstract
Inclusion body myositis (IBM) is often viewed as an enigmatic disease with uncertain pathogenic mechanisms and confusion around diagnosis, classification and prospects for treatment. Its clinical features (finger flexor and quadriceps weakness) and pathological features (invasion of myofibres by cytotoxic T cells) are unique among muscle diseases. Although IBM T cell autoimmunity has long been recognized, enormous attention has been focused for decades on several biomarkers of myofibre protein aggregates, which are present in <1% of myofibres in patients with IBM. This focus has given rise, together with the relative treatment refractoriness of IBM, to a competing view that IBM is not an autoimmune disease. Findings from the past decade that implicate autoimmunity in IBM include the identification of a circulating autoantibody (anti-cN1A); the absence of any statistically significant genetic risk factor other than the common autoimmune disease 8.1 MHC haplotype in whole-genome sequencing studies; the presence of a marked cytotoxic T cell signature in gene expression studies; and the identification in muscle and blood of large populations of clonal highly differentiated cytotoxic CD8+ T cells that are resistant to many immunotherapies. Mounting evidence that IBM is an autoimmune T cell-mediated disease provides hope that future therapies directed towards depleting these cells could be effective.
Collapse
|
16
|
Indications for neuromuscular ultrasound: Expert opinion and review of the literature. Clin Neurophysiol 2018; 129:2658-2679. [PMID: 30309740 DOI: 10.1016/j.clinph.2018.09.013] [Citation(s) in RCA: 49] [Impact Index Per Article: 8.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2018] [Revised: 08/10/2018] [Accepted: 09/02/2018] [Indexed: 12/11/2022]
Abstract
Over the last two decades, dozens of applications have emerged for ultrasonography in neuromuscular disorders. We wanted to measure its impact on practice in laboratories where the technique is in frequent use. After identifying experts in neuromuscular ultrasound and electrodiagnosis, we assessed their use of ultrasonography for different indications and their expectations for its future evolution. We then identified the earliest papers to provide convincing evidence of the utility of ultrasound for particular indications and analyzed the relationship of their date of publication with expert usage. We found that experts use ultrasonography often for inflammatory, hereditary, traumatic, compressive and neoplastic neuropathies, and somewhat less often for neuronopathies and myopathies. Usage significantly correlated with the timing of key publications in the field. We review these findings and the extensive evidence supporting the value of neuromuscular ultrasound. Advancement of the field of clinical neurophysiology depends on widespread translation of these findings.
Collapse
|
17
|
Local Texture Anisotropy as an Estimate of Muscle Quality in Ultrasound Imaging. ULTRASOUND IN MEDICINE & BIOLOGY 2018; 44:1133-1140. [PMID: 29428167 DOI: 10.1016/j.ultrasmedbio.2017.12.017] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/14/2017] [Revised: 12/12/2017] [Accepted: 12/21/2017] [Indexed: 06/08/2023]
Abstract
This study introduces local pattern texture anisotropy as a novel parameter to differentiate healthy and disordered muscle and to gauge the severity of muscle impairments based on B-mode ultrasound images. Preliminary human results are also presented. A local pattern texture anisotropy index (TAI) was computed in one region of interest in the short head of the biceps brachii. The effects of gain settings and box sizes required for TAI computation were investigated. Between-day reliability was studied in patients with sporadic inclusion body myositis (n = 26). The ability of the TAI to discriminate dystrophic from healthy muscle was evaluated in patients with Duchenne muscular dystrophy and healthy controls (n = 16). TAI values were compared with a gray-scale index (GSI). TAI values were less influenced by gain settings than were GSI values. TAI had lower between-day variability (typical error = 2.3%) compared with GSI (typical error = 2.3% vs. 8.3%, respectively). Patients with Duchenne muscular dystrophy had lower TAIs than controls (0.76 ± 0.06 vs. 0.87 ± 0.03, respectively, p <0.05). At 40% gain, TAI values correlated with percentage predicted elbow flexor strength in inclusion body myositis (R = 0.63, p <0.001). The TAI may be a promising addition to other texture-based approaches for quantitative muscle ultrasound imaging.
Collapse
|
18
|
|
19
|
Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methods. PLoS One 2017; 12:e0184059. [PMID: 28854220 PMCID: PMC5576677 DOI: 10.1371/journal.pone.0184059] [Citation(s) in RCA: 62] [Impact Index Per Article: 8.9] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2017] [Accepted: 08/17/2017] [Indexed: 12/12/2022] Open
Abstract
OBJECTIVE To evaluate the use of ultrasound coupled with machine learning (ML) and deep learning (DL) techniques for automated or semi-automated classification of myositis. METHODS Eighty subjects comprised of 19 with inclusion body myositis (IBM), 14 with polymyositis (PM), 14 with dermatomyositis (DM), and 33 normal (N) subjects were included in this study, where 3214 muscle ultrasound images of 7 muscles (observed bilaterally) were acquired. We considered three problems of classification including (A) normal vs. affected (DM, PM, IBM); (B) normal vs. IBM patients; and (C) IBM vs. other types of myositis (DM or PM). We studied the use of an automated DL method using deep convolutional neural networks (DL-DCNNs) for diagnostic classification and compared it with a semi-automated conventional ML method based on random forests (ML-RF) and "engineered" features. We used the known clinical diagnosis as the gold standard for evaluating performance of muscle classification. RESULTS The performance of the DL-DCNN method resulted in accuracies ± standard deviation of 76.2% ± 3.1% for problem (A), 86.6% ± 2.4% for (B) and 74.8% ± 3.9% for (C), while the ML-RF method led to accuracies of 72.3% ± 3.3% for problem (A), 84.3% ± 2.3% for (B) and 68.9% ± 2.5% for (C). CONCLUSIONS This study demonstrates the application of machine learning methods for automatically or semi-automatically classifying inflammatory muscle disease using muscle ultrasound. Compared to the conventional random forest machine learning method used here, which has the drawback of requiring manual delineation of muscle/fat boundaries, DCNN-based classification by and large improved the accuracies in all classification problems while providing a fully automated approach to classification.
Collapse
|
20
|
Neurogenic and Myogenic Diseases: Quantitative Texture Analysis of Muscle US Data for Differentiation. Radiology 2017; 283:492-498. [PMID: 28156201 DOI: 10.1148/radiol.2016160826] [Citation(s) in RCA: 33] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
Abstract
Purpose To assess the multiple texture features of skeletal muscles in neurogenic and myogenic diseases by using ultrasonography (US). Materials and Methods After institutional review board approval, muscle US studies of the medial head of the gastrocnemius were performed prospectively in patients with neurogenic diseases (n = 25 [18 men]; mean age, 66.0 years ± 12.3 [standard deviation]), in patients with myogenic diseases (n = 21 [12 men]; mean age, 68.3 years ± 11.5), and in healthy control subjects (n = 21 [11 men]; mean age, 70.5 years ± 8.4) between January 2013 and May 2016. Written informed consent was obtained. Muscle texture parameters were obtained, and five algorithms were used to classify the groups. Results The neurogenic and myogenic disease groups showed higher echo intensities than the control subjects. The histogram-derived texture parameters had overlaps between the neurogenic and myogenic groups and thus had a low discrimination rate. With assessment of more classes of texture parameters, three groups were correctly classified (100% correct, according to four of five classification algorithms). Tenfold cross validation showed 93.5%-95.7% correct classification between the neurogenic and myogenic groups. The run-length matrix, autoregressive model, and co-occurrence matrix were particularly useful in distinguishing the neurogenic and myogenic groups. Conclusion Texture analysis of muscle US data can enable differentiation between neurogenic and myogenic diseases and is useful in noninvasively assessing underlying disease mechanisms. © RSNA, 2017 Online supplemental material is available for this article.
Collapse
|
21
|
Preferential changes of skeletal muscle echogenicity in myotonic dystrophy type 1. Eur J Neurol 2016; 24:366-373. [PMID: 27933692 DOI: 10.1111/ene.13212] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2016] [Accepted: 10/25/2016] [Indexed: 11/28/2022]
Abstract
BACKGROUND AND PURPOSE In myotonic dystrophy type 1 (DM1), weakness of distal limb muscles affects quality of life. Non-invasive evaluation of muscular involvement by muscle sonography could be useful for characterizing muscle-specific involvement. METHODS Sonography of the lower leg and forearm was performed in 19 patients with DM1 and 10 control subjects. The mean echo intensities (EIs) of seven limb muscles were obtained by computer-assisted histogram analysis and compared within DM1 according to the overall clinical severity. RESULTS The EIs of the muscles were significantly higher in DM1 than in the controls (P < 0.01), except for the soleus (P = 0.4). Comparison of adjacent muscles showed the following: (i) greater EIs in flexor digitorum profundus than flexor carpi ulnaris (P < 0.01) and flexor digitorum superficialis (P = 0.02), and (ii) greater EIs in the medial head of the gastrocnemius than the soleus (P < 0.00001). In a subgroup analysis of DM1 according to the modified Rankin Scale (mRS), the more severe subgroup (mRS = 4-5) had lower mean EIs than the less severe subgroup (mRS from 1-3) (P = 0.01) in the flexor digitorum superficialis but not in other muscles. CONCLUSIONS Preferential high echogenicity in the medial gastrocnemius and deep finger flexors is suggestive of DM1. Muscle echogenicity is not generally related to functional dysfunction in DM1.
Collapse
|
22
|
Ultrasound estimates of muscle quality in older adults: reliability and comparison of Photoshop and ImageJ for the grayscale analysis of muscle echogenicity. PeerJ 2016; 4:e1721. [PMID: 26925339 PMCID: PMC4768702 DOI: 10.7717/peerj.1721] [Citation(s) in RCA: 52] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/09/2015] [Accepted: 01/31/2016] [Indexed: 12/25/2022] Open
Abstract
Background. Quantitative diagnostic ultrasound imaging has been proposed as a method of estimating muscle quality using measures of echogenicity. The Rectangular Marquee Tool (RMT) and the Free Hand Tool (FHT) are two types of editing features used in Photoshop and ImageJ for determining a region of interest (ROI) within an ultrasound image. The primary objective of this study is to determine the intrarater and interrater reliability of Photoshop and ImageJ for the estimate of muscle tissue echogenicity in older adults via grayscale histogram analysis. The secondary objective is to compare the mean grayscale values obtained using both the RMT and FHT methods across both image analysis platforms. Methods. This cross-sectional observational study features 18 community-dwelling men (age = 61.5 ± 2.32 years). Longitudinal views of the rectus femoris were captured using B-mode ultrasound. The ROI for each scan was selected by 2 examiners using the RMT and FHT methods from each software program. Their reliability is assessed using intraclass correlation coefficients (ICCs) and the standard error of the measurement (SEM). Measurement agreement for these values is depicted using Bland-Altman plots. A paired t-test is used to determine mean differences in echogenicity expressed as grayscale values using the RMT and FHT methods to select the post-image acquisition ROI. The degree of association among ROI selection methods and image analysis platforms is analyzed using the coefficient of determination (R (2)). Results. The raters demonstrated excellent intrarater and interrater reliability using the RMT and FHT methods across both platforms (lower bound 95% CI ICC = .97-.99, p < .001). Mean differences between the echogenicity estimates obtained with the RMT and FHT methods was .87 grayscale levels (95% CI [.54-1.21], p < .0001) using data obtained with both programs. The SEM for Photoshop was .97 and 1.05 grayscale levels when using the RMT and FHT ROI selection methods, respectively. Comparatively, the SEM values were .72 and .81 grayscale levels, respectively, when using the RMT and FHT ROI selection methods in ImageJ. Uniform coefficients of determination (R (2) = .96-.99, p < .001) indicate strong positive associations among the grayscale histogram analysis measurement conditions independent of the ROI selection methods and imaging platform. Conclusion. Our method for evaluating muscle echogenicity demonstrated a high degree of intrarater and interrater reliability using both the RMT and FHT methods across 2 common image analysis platforms. The minimal measurement error exhibited by the examiners demonstrates that the ROI selection methods used with Photoshop and ImageJ are suitable for the post-acquisition image analysis of tissue echogenicity in older adults.
Collapse
|