Shear Wave Elastography of the Diaphragm: Good Vibrations?

Deep learning radiomics on shear wave elastography and b-mode ultrasound videos of diaphragm for weaning outcome prediction

PURPOSE

We proposed an automatic method based on deep learning radiomics (DLR) on shear wave elastography (SWE) and B-mode ultrasound videos of diaphragm for two classification tasks, one for differentiation between the control and patient groups, and the other for weaning outcome prediction.

MATERIALS AND METHODS

We included a total of 581 SWE and B-mode ultrasound videos, of which 466 were from the control group of 179 normal subjects, and 115 were from the patient group of 35 mechanically ventilated subjects in the intensive care unit (ICU). Among the patient group, 17 subjects successfully weaned and 18 failed. The deep neural network of U-Net was utilized to automatically segment diaphragm regions in dual-modal videos of SWE and B-mode. High-throughput radiomics features were then extracted, the statistical test and least absolute shrinkage and selection operator (LASSO) were applied for feature dimension reduction. The optimal classification models for the two tasks were established using the support vector machine (SVM).

RESULTS

The automatic segmentation model achieved Dice score of 87.89 %. A total of 4524 radiomics features were extracted, 10 and 20 important features were left after feature dimension reduction for constructing the two classification models. The best areas under receiver operating characteristic curves of the two models reached 84.01 % and 94.37 %, respectively.

CONCLUSIONS

Our proposed DLR methods are innovative for automatic segmentation of diaphragm regions in SWE and B-mode videos and deep mining of high-throughput radiomics features from dual-modal images. The approaches have been proved to be effective for prediction of weaning outcomes.

Electrodiagnostic and ultrasound evaluation of respiratory weakness

Phrenic nerve conduction studies (NCSs) and needle electromyography (EMG) can provide important information on the underlying pathophysiology in patients presenting with unexplained shortness of breath, failure to wean from the ventilator, or consideration of phrenic nerve pacemaker implantation. However, these techniques are often technically challenging, require experience, can lack sensitivity and specificity, and, in the case of diaphragm EMG, involve some degree of risk. Diagnostic high-resolution ultrasound has been introduced in recent years as an adjuvant technique readily available at the bedside that can increase the overall sensitivity and specificity of the neurophysiologic evaluation of respiratory symptoms. Two-dimensional ultrasound in the zone of apposition can identify atrophy and evaluate contractility of the diaphragm, in addition to localizing a safe zone for needle EMG. M-mode ultrasound can identify decreased excursion or paradoxical motion of the diaphragm and can increase the reliability of phrenic NCSs. When used in combination, ultrasound, phrenic NCSs and EMG of the diaphragm can differentiate neuropathic, myopathic, and central disorders, and can offer aid in prognosis that is difficult to arrive at solely from clinical examination. This article will review techniques to successfully perform phrenic NCSs, needle EMG of the diaphragm, and ultrasound of the diaphragm. The discussion will include technical pitfalls and clinical pearls as well as future directions and clinical indications.

Reliability and validity of ultrasonography in evaluating the thickness, excursion, stiffness, and strain rate of respiratory muscles in non-hospitalized individuals: a systematic review

OBJECTIVE

To summarize the reliability and validity of ultrasonography in evaluating the stiffness, excursion, stiffness, or strain rate of diaphragm, intercostals and abdominal muscles in healthy or non-hospitalized individuals.

LITERATURE SEARCH

PubMed, Embase, SPORTDiscus, CINAHL and Cochrane Library were searched from inception to May 30, 2022.

STUDY SELECTION CRITERIA

Case-control, cross-sectional, and longitudinal studies were included if they investigated the reliability or validity of various ultrasonography technologies (e.g., brightness-mode, motion-mode, shear wave elastography) in measuring the thickness, excursion, stiffness, or strain rate of any respiratory muscles.

DATA SYNTHESIS

Relevant data were summarized based on healthy and different patient populations. The methodological quality by different checklist depending on study design. The quality of evidence of each psychometric property was graded by the Grading of Recommendations, Assessment, Development and Evaluations, respectively.

RESULTS

This review included 24 studies with 787 healthy or non-hospitalized individuals (e.g., lower back pain (LBP), adolescent idiopathic scoliosis (AIS), and chronic obstructive pulmonary disease (COPD)). Both inspiratory (diaphragm and intercostal muscles) and expiratory muscles (abdominal muscles) were investigated. Moderate-quality evidence supported sufficient (intra-class correlation coefficient > 0.7) within-day intra-rater reliability of B-mode ultrasonography in measuring right diaphragmatic thickness among people with LBP, sufficient between-day intra-rater reliability of M-mode ultrasonography in measuring right diaphragmatic excursion in non-hospitalized individuals. The quality of evidence for all other measurement properties in various populations was low or very low. High-quality evidence supported sufficient positive correlations between diaphragm excursion and forced expiratory volume in the first second or forced vital capacity (r >  = 0.3) in healthy individuals.

CONCLUSIONS

Despite the reported sufficient reliability and validity of using ultrasonography to assess the thickness, excursion, stiffness, and strain rate of respiratory muscles in non-hospitalized individuals, further large-scale studies are warranted to improve the quality of evidence regarding using ultrasonography for these measurements in clinical practice. Researchers should establish their own reliability before using various types of ultrasonography to evaluate respiratory muscle functions.

TRIAL REGISTRATION

PROSPERO NO. CRD42022322945.

Diaphragm Ultrasound in Critically Ill Patients on Mechanical Ventilation—Evolving Concepts

Mechanical ventilation (MV) is a life-saving respiratory support therapy, but MV can lead to diaphragm muscle injury (myotrauma) and induce diaphragmatic dysfunction (DD). DD is relevant because it is highly prevalent and associated with significant adverse outcomes, including prolonged ventilation, weaning failures, and mortality. The main mechanisms involved in the occurrence of myotrauma are associated with inadequate MV support in adapting to the patient’s respiratory effort (over- and under-assistance) and as a result of patient-ventilator asynchrony (PVA). The recognition of these mechanisms associated with myotrauma forced the development of myotrauma prevention strategies (MV with diaphragm protection), mainly based on titration of appropriate levels of inspiratory effort (to avoid over- and under-assistance) and to avoid PVA. Protecting the diaphragm during MV therefore requires the use of tools to monitor diaphragmatic effort and detect PVA. Diaphragm ultrasound is a non-invasive technique that can be used to monitor diaphragm function, to assess PVA, and potentially help to define diaphragmatic effort with protective ventilation. This review aims to provide clinicians with an overview of the relevance of DD and the main mechanisms underlying myotrauma, as well as the most current strategies aimed at minimizing the occurrence of myotrauma with special emphasis on the role of ultrasound in monitoring diaphragm function.

The Possible Impact of COVID-19 on Respiratory Muscles Structure and Functions: A Literature Review

The impact of SARS-CoV-2 infection on respiratory muscle functions is an important area of recent enquiry. COVID-19 has effects on the respiratory muscles. The diaphragm muscle is perturbed indirectly due to the mechanical-ventilation-induced-disuse, but also by direct mechanisms linked with SARS-CoV-2 viral infection. In this sense, a deeper understanding of the possible links between COVID-19 and alterations in structure and functions of the respiratory muscles may increase the success rate of preventive and supportive strategies. Ultrasound imaging alongside respiratory muscle strength tests and pulmonary function assessment are valid approaches to the screening and monitoring of disease, for mild to severe patients. The aim of the present review is to highlight the current literature regarding the links between COVID-19 and respiratory muscle functions. We examine from the pathophysiological aspects of disease, up to approaches taken to monitor and rehabilitate diseased muscle. We hope this work will add to a greater understanding of the pathophysiology and disease management of respiratory muscle pathology subsequent to SARS-CoV-2 infection.