Development of an acquisition system to monitoring asynchronous tele-ultrasound for lung patients

Lung ultrasound imaging allows the detection and evaluation of the lung damage generated by COVID-19. However, several infrastructure and logistical limitations prevent them from being carried out in isolated and remote areas. In this work, a system for the acquisition of medical images through asynchronous tele-ultrasounds was developed. The system is based on a graphical user interface, which records the three video cameras, the ultrasound image and the accelerometer simultaneously. The interface was developed according to the Volume Sweep Imaging acquisition protocol. The translational and rotational movement of the transducer are tracked and monitored by the accelerometer and the position of the transducer is obtained from the images acquired by the three video cameras. The results show a correct functioning of the system overall, being viable to be implemented for data acquisition and calculation of error, although in order to validate the error calculation there is still more research to be done. © 2023 SPIE.

Photoacoustic Imaging of COVID-19 Vaccine Site Inflammation of Autoimmune Disease Patients.

Based on the observations made in rheumatology clinics, autoimmune disease (AD) patients on immunosuppressive (IS) medications have variable vaccine site inflammation responses, whose study may help predict the long-term efficacy of the vaccine in this at-risk population. However, the quantitative assessment of the inflammation of the vaccine site is technically challenging. In this study analyzing AD patients on IS medications and normal control subjects, we imaged the inflammation of the vaccine site 24 h after mRNA COVID-19 vaccinations were administered using both the emerging photoacoustic imaging (PAI) method and the established Doppler ultrasound (US) method. A total of 15 subjects were involved, including 6 AD patients on IS and 9 normal control subjects, and the results from the two groups were compared. Compared to the results obtained from the control subjects, the AD patients on IS medications showed statistically significant reductions in vaccine site inflammation, indicating that immunosuppressed AD patients also experience local inflammation after mRNA vaccination but not in as clinically apparent of a manner when compared to non-immunosuppressed non-AD individuals. Both PAI and Doppler US were able to detect mRNA COVID-19 vaccine-induced local inflammation. PAI, based on the optical absorption contrast, shows better sensitivity in assessing and quantifying the spatially distributed inflammation in soft tissues at the vaccine site.

Using Ultrasound Image Augmentation and Ensemble Predictions to Prevent Machine-Learning Model Overfitting.

Deep learning predictive models have the potential to simplify and automate medical imaging diagnostics by lowering the skill threshold for image interpretation. However, this requires predictive models that are generalized to handle subject variability as seen clinically. Here, we highlight methods to improve test accuracy of an image classifier model for shrapnel identification using tissue phantom image sets. Using a previously developed image classifier neural network-termed ShrapML-blind test accuracy was less than 70% and was variable depending on the training/test data setup, as determined by a leave one subject out (LOSO) holdout methodology. Introduction of affine transformations for image augmentation or MixUp methodologies to generate additional training sets improved model performance and overall accuracy improved to 75%. Further improvements were made by aggregating predictions across five LOSO holdouts. This was done by bagging confidences or predictions from all LOSOs or the top-3 LOSO confidence models for each image prediction. Top-3 LOSO confidence bagging performed best, with test accuracy improved to greater than 85% accuracy for two different blind tissue phantoms. This was confirmed by gradient-weighted class activation mapping to highlight that the image classifier was tracking shrapnel in the image sets. Overall, data augmentation and ensemble prediction approaches were suitable for creating more generalized predictive models for ultrasound image analysis, a critical step for real-time diagnostic deployment.

Graph and Capsule Convolutional Neural Network Based Classification of Lung Cancer, Pneumonia, COVID-19 using Lung CT and Ultrasound Radiography Imaging

Pulmonary / Lung nodules are a sign of lung cancer. Pneumonia, Lung nodules show up on imaging scans like X-rays, CT or ultrasound scans. The healthcare team may refer to the growth as a spot on the lung, coin lesion, or shadow. Coronavirus (COVID-19) has been identified as a worldwide epidemic, affecting individuals all over the nation. It is vital to identify COVID-19-affected persons to limit the virus's spread. According to the latest study, radiographic approaches can be used to diagnose contamination utilizing deep learning (DL) methods. Considering that DL is a valuable approach and methodology for image analysis, various studies on COVID-19 case detection utilizing radiographs to train DL networks have been conducted. Although just a handful of studies presume to have excellent prediction results, their proposed systems may suffer from a restricted amount of data. Employing graph and capsule, Convolutional Neural Network (CNN) can overcome the shortcomings by predicting multiple disorders using a single network implemented in a hospital. We present a novel comparative method that has paved the way for an open-source COVID-19 case classification approach based on graph and capsule images with CT and ultrasound. Experimental results show that the Capsule network attained the best 98.93% AUC, 99.2% accuracy, 98.4% Fl-score, 98.40% sensitivity, 98.40% specificity, 9S.4l% precision using CT labels. Whereas the ultrasound test set the graph network performed well with 96.93% AUC, 97.26% accuracy, 95.92% Fl-score, 95.90% sensitivity, 97.94% specificity, 96.08% precision. © 2022 IEEE.

COVID-19 feature detection with deep neural networks trained on simulated lung ultrasound B-mode images

Deep learning has been implemented to detect COVID-19 features in lung ultrasound B-mode images. However, previous work primarily relied on in vivo images as the training data, which suffers from limited access to required manual labeling of thousands of training image examples. To avoid this manual labeling, which is tedious and time consuming, we propose the detection of in vivo COVID-19 features (i.e., A-line, B-line, consolidation) with deep neural networks (DNNs) trained on simulated B-mode images. The simulation-trained DNNs were tested on in vivo B-mode images from healthy subjects and COVID-19 patients. With data augmentation included during the training process, Dice similarity coefficients (DSCs) between ground truth and DNN predictions were maximized, producing mean ± standard deviatio values as high as 0.48 ± 0.29, 0.45 ± 0.25, and 0.46 ± 0.35 when segmenting in vivo A-line, B-line, and consolidation features, respectively. Results demonstrate that simulation-trained DNNs are a promising alternative to training with real patient data when segmenting in vivo COVID-19 features. © 2022 IEEE.

Automatically Scoring Lung Ultrasound Videos of COVID-19 and post-COVID-19 Patients

Lung ultrasound (LUS) imaging is playing an important role in the current pandemic, allowing the evaluation of patients affected by COVID-19 pneumonia. However, LUS is limited to the visual inspection of ultrasound data, which negatively affects the reproducibility and reliability of the findings. For these reasons, we were the first to propose a standardized imaging protocol and a scoring system, from which we developed the first artificial intelligence (AI) models able to evaluate LUS videos. Furthermore, we demonstrated prognostic value of our approach and its utility for patients' stratification. In this study, we report on the level of agreement between AI and LUS clinical experts (MD) on LUS data acquired from both COVID-19 patients and post-COVID-19 patients. © 2022 IEEE.

RL Based Unsupervised Video Summarization Framework for Ultrasound Imaging

The need for summarizing long medical scan videos for automatic triage in Emergency Departments and transmission of the summarized videos for telemedicine has gained significance during the COVID-19 pandemic. However, supervised learning schemes for summarizing videos are infeasible as manual labeling of scans for large datasets is impractical by frontline clinicians. This work presents a methodology to summarize ultrasound videos using completely unsupervised learning schemes and is validated on Lung Ultrasound videos. A Convolutional Autoencoder and a Transformer decoder is trained in an unsupervised reinforcement learning setup i.e., without supervised labels in the whole workflow. Novel precision and recall computation for ultrasound videos is also presented employing which high Precision and F1 scores of 64.36% and 35.87% with an average video compression rate of 78% is obtained when validated against clinically annotated cases. Even though demonstrated using lung ultrasound videos, our approach can be readily extended to other imaging modalities. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Rapid Lung Ultrasound COVID-19 Severity Scoring with Resource-Efficient Deep Feature Extraction

Artificial intelligence-based analysis of lung ultrasound imaging has been demonstrated as an effective technique for rapid diagnostic decision support throughout the COVID-19 pandemic. However, such techniques can require days- or weeks-long training processes and hyper-parameter tuning to develop intelligent deep learning image analysis models. This work focuses on leveraging ‘off-the-shelf’ pre-trained models as deep feature extractors for scoring disease severity with minimal training time. We propose using pre-trained initializations of existing methods ahead of simple and compact neural networks to reduce reliance on computational capacity. This reduction of computational capacity is of critical importance in time-limited or resource-constrained circumstances, such as the early stages of a pandemic. On a dataset of 49 patients, comprising over 20,000 images, we demonstrate that the use of existing methods as feature extractors results in the effective classification of COVID-19-related pneumonia severity while requiring only minutes of training time. Our methods can achieve an accuracy of over 0.93 on a 4-level severity score scale and provides comparable per-patient region and global scores compared to expert annotated ground truths. These results demonstrate the capability for rapid deployment and use of such minimally-adapted methods for progress monitoring, patient stratification and management in clinical practice for COVID-19 patients, and potentially in other respiratory diseases. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

COVIDx-US: An Open-Access Benchmark Dataset of Ultrasound Imaging Data for AI-Driven COVID-19 Analytics.

BACKGROUND: The Coronavirus Disease 2019 (COVID-19) pandemic continues to have a devastating effect on the health and well-being of the global population. Apart from the global health crises, the pandemic has also caused significant economic and financial difficulties and socio-physiological implications. Effective screening, triage, treatment planning, and prognostication of outcome play a key role in controlling the pandemic. Recent studies have highlighted the role of point-of-care ultrasound imaging for COVID-19 screening and prognosis, particularly given that it is non-invasive, globally available, and easy-to-sanitize. COVIDx-US Dataset: Motivated by these attributes and the promise of artificial intelligence tools to aid clinicians, we introduce COVIDx-US, an open-access benchmark dataset of COVID-19 related ultrasound imaging data. The COVIDx-US dataset was curated from multiple data sources and its current version, i.e., v1.5., consists of 173 ultrasound videos and 21,570 processed images across 147 patients with COVID-19 infection, non-COVID-19 infection, other lung diseases/conditions, as well as normal control cases. CONCLUSIONS: The COVIDx-US dataset was released as part of a large open-source initiative, the COVID-Net initiative, and will be continuously growing, as more data sources become available. To the best of the authors' knowledge, COVIDx-US is the first and largest open-access fully-curated benchmark lung ultrasound imaging dataset that contains a standardized and unified lung ultrasound score per video file, providing better interpretation while enabling other research avenues such as severity assessment. In addition, the dataset is reproducible, easy-to-use, and easy-to-scale thanks to the well-documented modular design.

Multi-stage investigation of deep neural networks for COVID-19 B-line feature detection in simulated and in vivo ultrasound images

COVID-19 is a highly infectious disease with high morbidity and mortality, requiring tools to support rapid triage and risk stratification. In response, deep learning has demonstrated great potential to quicklyand autonomously detect COVID-19 features in lung ultrasound B-mode images. However, no previous work considers the application of these deep learning models to signal processing stages that occur prior to traditional ultrasound B-mode image formation. Considering the multiple signal processing stages required to achieve ultrasound B-mode images, our research objective is to investigate the most appropriate stage for our deep learning approach to COVID-19 B-line feature detection, starting with raw channel data received by an ultrasound transducer. Results demonstrate that for our given training and testing configuration, the maximum Dice similarity coefficient (DSC) was produced by B-mode images (DSC = 0.996) when compared with three alternative image formation stages that can serve as network inputs: (1) raw in-phase and quadrature (IQ) data before beamforming, (2) beamformed IQ data, (3) envelope detected IQ data. The best-performing simulation-trained network was tested on in vivo B-mode images of COVID-19 patients, ultimately achieving 76% accuracy to detect the same (82% of cases) or more (18% of cases) B-line features when compared to B-line feature detection by human observers interpreting B-mode images. Results are promising to proceed with future COVID-19 B-line feature detection using ultrasound B-mode images as the input to deep learning models. © 2022 SPIE.

Dual Mode pHRI-teleHRI Control System with a Hybrid Admittance-Force Controller for Ultrasound Imaging.

The COVID-19 pandemic has brought unprecedented extreme pressure on the medical system due to the physical distance policy, especially for procedures such as ultrasound (US) imaging, which are usually carried out in person. Tele-operation systems are a promising way to avoid physical human-robot interaction (pHRI). However, the system usually requires another robot on the remote doctor side to provide haptic feedback, which makes it expensive and complex. To reduce the cost and system complexity, in this paper, we present a low-cost, easy-to-use, dual-mode pHRI-teleHRI control system with a custom-designed hybrid admittance-force controller for US imaging. The proposed system requires only a tracking camera rather than a sophisticated robot on the remote side. An audio feedback is designed for replacing haptic feedback on the remote side, and its sufficiency is experimentally verified. The experimental results indicate that the designed hybrid controller can significantly improve the task performance in both modes. Furthermore, the proposed system enables the user to conduct US imaging while complying with the physical distance policy, and allows them to seamlessly switch modes from one to another in an online manner. The novel system can be easily adapted to other medical applications beyond the pandemic, such as tele-healthcare, palpation, and auscultation.

What Is COVID 19 Teaching Us about Pulmonary Ultrasound?

In lung ultrasound (LUS), the interactions between the acoustic pulse and the lung surface (including the pleura and a small subpleural layer of tissue) are crucial. Variations of the peripheral lung density and the subpleural alveolar shape and its configuration are typically connected to the presence of ultrasound artifacts and consolidations. COVID-19 pneumonia can give rise to a variety of pathological pulmonary changes ranging from mild diffuse alveolar damage (DAD) to severe acute respiratory distress syndrome (ARDS), characterized by peripheral bilateral patchy lung involvement. These findings are well described in CT imaging and in anatomopathological cases. Ultrasound artifacts and consolidations are therefore expected signs in COVID-19 pneumonia because edema, DAD, lung hemorrhage, interstitial thickening, hyaline membranes, and infiltrative lung diseases when they arise in a subpleural position, generate ultrasound findings. This review analyzes the structure of the ultrasound images in the normal and pathological lung given our current knowledge, and the role of LUS in the diagnosis and monitoring of patients with COVID-19 lung involvement.

Challenges with tunneled dialysis catheter placement with subcutaneous emphysema.

Central vein catheter is a convenient and preferred vascular access for blood purification therapy in intensive care unit. Utilizing ultrasound to access the central vein is considered standard of care. However, critically ill patients can pose challenges while acquiring an optimal ultrasound image. The presence of subcutaneous air pockets, concerns for air embolism, and excessive bleeding from the exit site is one such clinical situation. We describe our experience with a unique situation while placing a tunneled dialysis catheter in a COVID-19 patient with acute respiratory failure and subcutaneous emphysema.

Adaptive Few-Shot Learning PoC Ultrasound COVID-19 Diagnostic System

This paper presents a novel ultrasound imaging point-of-care (PoC) COVID-19 diagnostic system. The adaptive visual diagnostics utilize few-shot learning (FSL) to generate encoded disease state models that are stored and classified using a dictionary of knowns. The novel vocabulary based feature processing of the pipeline adapts the knowledge of a pretrained deep neural network to compress the ultrasound images into discrimative descriptions. The computational efficiency of the FSL approach enables high diagnostic deep learning performance in PoC settings, where training data is limited and the annotation process is not strictly controlled. The algorithm performance is evaluated on the open source COVID-19 POCUS Dataset to validate the system's ability to distinguish COVID-19, pneumonia, and healthy disease states. The results of the empirical analyses demonstrate the appropriate efficiency and accuracy for scalable PoC use. The code for this work will be made publicly available on GitHub upon acceptance. © 2021 IEEE.

The Role of Rehabilitative Ultrasound Imaging Technique in the Lumbopelvic Region as a Diagnosis and Treatment Tool in Physiotherapy: Systematic Review, Meta-Analysis and Meta-Regression.

Rehabilitative ultrasound imaging (RUSI) technique seems to be a valid and reliable tool for diagnosis and treatment in physiotherapy and has been widely studied in the lumbopelvic region the last three decades. The aims for this utility in clinical settings must be review through a systematic review, meta-analysis and meta-regression. A systematic review was designed following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines with PROSPERO registration and per review in all phases of the process using COVIDENCE, analysis of risk of bias and meta-analysis using REVMAN, and meta-regression calculation using STATA. Database screening provided 6544 references, out of which 321 reported narrative synthesis, and 21 reported quantitative synthesis, while only 7 of them provided comparable data to meta-analyze the variables pain and muscle thickness. In most cases, the forest plots showed considerable I2 heterogeneity indexes for multifidus muscle thickness (I2 = 95%), low back pain (I2 = 92%) and abdominal pain (I2 = 95%), not important for transversus abdominis muscle thickness (I2 = 22%), significant heterogenity (I2 = 69%) depending on the subgroup and not important internal oblique muscle thickness (I2 = 0%) and external oblique muscle thickness (I2 = 0%). Meta-regression did not provide significant data for the correlations between the variables analyzed and the intervention, age, and BMI (Body Mass Index). This review reveals that RUSI could contribute to a high reliability of the measurements in the lumbopelvic region with validity and reliability for the assessments, as well as showing promising results for diagnosis and intervention assessment in physiotherapy compared to the traditional model, allowing for future lines of research in this area.

Virtual neuromuscular ultrasound courses during COVID-19 pandemic: Leveraging technology to enhance learning opportunities.

INTRODUCTION/AIMS: Hands-on supervised training is essential for learning diagnostic ultrasound. Unfortunately, the coronavirus disease 2019 (COVID-19) pandemic led to suspension of in-person training courses. As a result, many hands-on training courses were converted into virtual courses during the pandemic. Several reports regarding virtual ultrasound courses exist, but none has addressed virtual neuromuscular ultrasound courses, their design, or participants' views of this form of training. Therefore, the aims of this study were: (1) to determine the feasibility of conducting virtual neuromuscular ultrasound courses during the COVID-19 pandemic; and (2) to report the positive and negative aspects of the courses through the analyses of the responses of post-course surveys. METHODS: Two virtual neuromuscular ultrasound courses, basic and intermediate level, were conducted by the Egyptian Neuromuscular Ultrasound society during August 2020. Post-course, the attendees were directed to an electronic survey that consisted of eight questions. Ninety-three responses (23.8%) were obtained from the survey of the basic course and 156 responses (44.4%) were obtained from the survey of the intermediate course. RESULTS: Ninety-eight percent of the respondents to basic course surveys, and 100% of the respondents to the intermediate course survey found the courses useful or very useful. DISCUSSION: This report demonstrates the utility of virtual neuromuscular ultrasound courses for those participants willing to respond to a survey and describes a proposed design for such courses. Although hands-on supervised ultrasound training is ideal, virtual courses can be useful alternatives to in-person training when in-person interaction is restricted.

Ultrasound Imaging Findings of Acute Testicular Infection in Patients With Coronavirus Disease 2019: A Single-Center-Based Study in Wuhan, China.

OBJECTIVES: Coronavirus disease 2019 (COVID-19), caused by the novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has become a global pandemic, raising widespread public health concerns. Our team treated hospitalized patients with COVID-19 in Wuhan, where the outbreak first began, and we suspected that SARS-CoV-2 may cause testicular infection in male patients. We conducted this study to explore that observation. METHODS: We enrolled male patients with a confirmed diagnosis of COVID-19 and performed a bedside ultrasound (US) examination of the scrotum, focused on findings of acute inflammation such as tunica albuginea thickening, enlargement and heterogeneous echogenicity of the testis, epididymis, or both, an abscess, scrotal wall edema, and hydrocele. Then we compared the proportions of observed epididymo-orchitis in patients from different age groups and COVID-19 severity groups. RESULTS: A total of 142 patients with COVID-19 were enrolled in our study, and 32 (22.5%) patients had acute orchitis, epididymitis, or epididymo-orchitis on scrotal US imaging, according to the diagnosis criteria. The observed risk of acute scrotal infection increased with age, with the incidence reaching 53.3% in men older than 80 years. We also observed that men with severe COVID-19 had a significantly higher possibility of epididymo-orchitis compared to the nonsevere COVID-19 group (P = .037). CONCLUSIONS: This study shows US imaging evidence that SARS-CoV-2 may cause infection of the testis or epididymis, and the risk is worthy of the attention of clinicians.

Diagnosis of COVID-19 Using Machine Learning and Deep Learning: A Review.

BACKGROUND: This paper provides a systematic review of the application of Artificial Intelligence (AI) in the form of Machine Learning (ML) and Deep Learning (DL) techniques in fighting against the effects of novel coronavirus disease (COVID-19). OBJECTIVE & METHODS: The objective is to perform a scoping review on AI for COVID-19 using preferred reporting items of systematic reviews and meta-analysis (PRISMA) guidelines. A literature search was performed for relevant studies published from 1 January 2020 till 27 March 2021. Out of 4050 research papers available in reputed publishers, a full-text review of 440 articles was done based on the keywords of AI, COVID-19, ML, forecasting, DL, X-ray, and Computed Tomography (CT). Finally, 52 articles were included in the result synthesis of this paper. As part of the review, different ML regression methods were reviewed first in predicting the number of confirmed and death cases. Secondly, a comprehensive survey was carried out on the use of ML in classifying COVID-19 patients. Thirdly, different datasets on medical imaging were compared in terms of the number of images, number of positive samples and number of classes in the datasets. The different stages of the diagnosis, including preprocessing, segmentation and feature extraction were also reviewed. Fourthly, the performance results of different research papers were compared to evaluate the effectiveness of DL methods on different datasets. RESULTS: Results show that residual neural network (ResNet-18) and densely connected convolutional network (DenseNet 169) exhibit excellent classification accuracy for X-ray images, while DenseNet-201 has the maximum accuracy in classifying CT scan images. This indicates that ML and DL are useful tools in assisting researchers and medical professionals in predicting, screening and detecting COVID-19. CONCLUSION: Finally, this review highlights the existing challenges, including regulations, noisy data, data privacy, and the lack of reliable large datasets, then provides future research directions in applying AI in managing COVID-19.

On the Impact of Different Lung Ultrasound Imaging Protocols in the Evaluation of Patients Affected by Coronavirus Disease 2019: How Many Acquisitions Are Needed?

Lung ultrasound (LUS) is currently being extensively used for the evaluation of patients affected by coronavirus disease 2019. In the past months, several imaging protocols have been proposed in the literature. However, how the different protocols would compare when applied to the same patients had not been investigated yet. To this end, in this multicenter study, we analyzed the outcomes of 4 different LUS imaging protocols, respectively based on 4, 8, 12, and 14 LUS acquisitions, on data from 88 patients. Results show how a 12-area acquisition system seems to be a good tradeoff between the acquisition time and accuracy.