Muscle B mode ultrasound and shear-wave elastography in idiopathic inflammatory myopathies (SWIM): criterion validation against MRI and muscle biopsy findings in an incident patient cohort

[Sonography of muscles : Rheumatology-Neurology-Geriatrics-Sports medicine-Orthopedics]

Muscle sonography is used in rheumatology, neurology, geriatrics, sports medicine and orthopedics. Muscular atrophy with fatty and connective tissue degeneration can be visualized and must be interpreted in conjunction with the sonographic findings of the supplying nerves. Sonography is becoming increasingly more important for the early diagnosis of sarcopenia in rheumatology, geriatrics and osteology. Even if its significance has not yet been conclusively clarified, many publications confirm the high reliability of the method. Sonography can ideally be used in addition to magnetic resonance imaging (MRI) in the diagnostics of myositis as it can speed up the diagnosis, muscle groups that were not imaged by MRI can also be assessed sonographically and all muscle groups can be examined during the course of the procedure. Sonography also helps to make a quick and uncomplicated diagnosis of many sports injuries in addition to MRI and is therefore the basis for a targeted therapeutic approach.

Muscle ultrasound in myopathies

PURPOSE OF REVIEW

This review highlights recent developments in the field of muscle ultrasound (MUS) for the diagnosis and follow up of muscle disorders.

RECENT FINDINGS

The diagnostic screening capacity of quantitative grayscale analysis is still sufficient to assess children suspected of a neuromuscular disorder. A combination of visual and quantitative assessment is advised for optimal interpretation. MUS was more sensitive but less specific than MRI for detecting pathology in limb girdle dystrophies and inflammatory myopathies. New techniques such as shearwave elastography and artificial intelligence algorithms for automated image segmentation show promise but need further development for use in everyday practice.Muscle ultrasound has high correlations with clinical measures of function in skeletal and respiratory muscles and the orofacial region, in most of the myopathies and dystrophies studied. Over time, imaging changes precede changes in clinical status, making them attractive for biomarker use in trials. In Duchenne muscular dystrophy MUS was also responsive to the effects of steroid treatment.

SUMMARY

Muscle ultrasound is a sensitive technique to diagnose and follow up of skeletal, facial and respiratory muscles in neuromuscular disorders. Its role is both complementary to and partially overlapping with that of MRI.

MGB-Unet: An Improved Multiscale Unet with Bottleneck Transformer for Myositis Segmentation from Ultrasound Images

Myositis is the inflammation of the muscles that can arise from various sources with diverse symptoms and require different treatments. For treatment to achieve optimal results, it is essential to obtain an accurate diagnosis promptly. This paper presents a new supervised segmentation architecture that can efficiently perform precise segmentation and classification of myositis from ultrasound images with few computational resources. The architecture of our model includes a unique encoder-decoder structure that integrates the Bottleneck Transformer (BOT) with a newly developed Residual block named Multi-Conv Ghost switchable bottleneck Residual Block (MCG_RB). This block effectively captures and analyzes ultrasound image input inside the encoder segment at several resolutions. Moreover, the BOT module is a transformer-style attention module designed to bridge the feature gap between the encoding and decoding stages. Furthermore, multi-level features are retrieved using the MCG-RB module, which combines multi-convolution with ghost switchable residual connections of convolutions for both the encoding and decoding stages. The suggested method attains state-of-the-art performance on a benchmark set of myositis ultrasound images across all parameters, including accuracy, precision, recall, dice coefficient, and Jaccard index. Despite its limited training data, the suggested approach demonstrates remarkable generalizability by yielding exceptional results. The proposed model showed a substantial enhancement in accuracy when compared to segmentation state-of-the-art methods such as Unet++, DeepLabV3, and the Duck-Net. The dice coefficient and Jaccard index obtained improvements of up to 3%, 6%, and 7%, respectively, surpassing the other methods.

MyoVision-US: an Artificial Intelligence-Powered Software for Automated Analysis of Skeletal Muscle Ultrasonography

Introduction/Aims

Muscle ultrasound has high utility in clinical practice and research; however, the main challenges are the training and time required for manual analysis to achieve objective quantification of morphometry. This study aimed to develop and validate a software tool powered by artificial intelligence (AI) by measuring its consistency and predictability of expert manual analysis quantifying lower limb muscle ultrasound images across healthy, acute, and chronic illness subjects.

Methods

Quadriceps complex (QC [rectus femoris and vastus intermedius]) and tibialis anterior (TA) muscle ultrasound images of healthy, intensive care unit, and/or lung cancer subjects were captured with portable devices. Automated analyses of muscle morphometry were performed using a custom-built deep-learning model (MyoVision-US), while manual analyses were performed by experts. Consistency between manual and automated analyses was determined using intraclass correlation coefficients (ICC), while predictability of MyoVision -US was calculated using adjusted linear regression (adj.R 2 ).

Results

Manual analysis took approximately 24 hours to analyze all 180 images, while MyoVision - US took 247 seconds, saving roughly 99.8%. Consistency between the manual and automated analyses by ICC was good to excellent for all QC (ICC:0.85-0.99) and TA (ICC:0.93-0.99) measurements, even for critically ill (ICC:0.91-0.98) and lung cancer (ICC:0.85-0.99) images. The predictability of MyoVision-US was moderate to strong for QC (adj.R 2 :0.56-0.94) and TA parameters (adj.R 2 :0.81-0.97).

Discussion

The application of AI automating lower limb muscle ultrasound analyses showed excellent consistency and strong predictability compared with human analysis. Future work needs to explore AI-powered models for the evaluation of other skeletal muscle groups.

The longitudinal study of muscle changes with ultrasound: differential changes in idiopathic inflammatory myopathy subgroups

OBJECTIVES

We investigated shear wave elastography (SWE), B mode US and power Doppler (PDUS) as imaging biomarkers for longitudinal follow-up in idiopathic inflammatory myopathy (IIM), with a particular focus on immune-mediated necrotizing myopathy (IMNM) and DM.

METHODS

Participants had serial SWE, PDUS on the deltoid (D) and vastus lateralis (VL) muscles on four occasions at intervals of 3-6 months. Clinical assessments included manual muscle testing, and patient- and physician-reported outcome scales.

RESULTS

Thirty-three participants were included: IMNM = 17, DM = 12, overlap myositis = 3, PM = 1. Twenty were in a prevalent clinic group, and 13 were recently treated cases in an incident group. Differential changes in SWS and US domains occurred with time in both the prevalent and incident groups. In the VL-prevalent subgroup, echogenicity increased over time (P = 0.040), while in the incident cases there was a trend for reduction to normal over time (P = 0.097) with treatment. Muscle bulk reduced in the D-prevalent subgroup over time (P = 0.096), suggesting atrophy. SWS also reduced in the VL-incident subgroup over time (P = 0.096), suggesting a trend towards improvement in muscle stiffness with treatment.

CONCLUSION

SWE and US appear promising as imaging biomarkers for patient follow-up in IIM and indicate changes over time, especially with echogenicity, muscle bulk and SWS in the VL. Due to the limitations of the participant numbers, additional studies with a larger cohort are needed to help evaluate these US domains further and outline specific characteristics within the IIM subgroups.

Imaging biomarkers in the idiopathic inflammatory myopathies

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.