Abstract:The adoption of point-of-care lung ultrasound for both suspected and confirmed COVID-19 patients highlights the issues of accessibility to ultrasound training and equipment. Lung ultrasound is more sensitive than chest radiography in detecting viral pneumonitis and preferred over computed tomography for reasons including its portability, reduced healthcare worker exposure and repeatability. The main lung ultrasound findings in COVID-19 patients are interstitial syndrome, irregular pleural line and subpleural c… Show more
“…Hence, in this case, the focus of the Grad-CAM algorithm has been spread over a comparatively larger region. As the score rises up to 3, the model activates in a more indicative manner as patchy areas of B-lines, irregular pleural lines, and consolidations in the subpleural region, i.e., symptoms for an unhealthy lung [ 35 ] are prevalent there. Figure 6 The heatmaps indicate which portions instigated the classification decision in the frames acquired from both convex and linear probes.…”
The COVID-19 pandemic has become one of the biggest threats to the global healthcare system, creating an unprecedented condition worldwide. The necessity of rapid diagnosis calls for alternative methods to predict the condition of the patient, for which disease severity estimation on the basis of Lung Ultrasound (LUS) can be a safe, radiation-free, flexible, and favorable option. In this paper, a frame-based 4-score disease severity prediction architecture is proposed with the integration of deep convolutional and recurrent neural networks to consider both spatial and temporal features of the LUS frames. The proposed convolutional neural network (CNN) architecture implements an autoencoder network and separable convolutional branches fused with a modified DenseNet-201 network to build a vigorous, noise-free classification model. A five-fold cross-validation scheme is performed to affirm the efficacy of the proposed network. In-depth result analysis shows a promising improvement in the classification performance by introducing the Long Short-Term Memory (LSTM) layers after the proposed CNN architecture by an average of
, which is approximately
more than the traditional DenseNet architecture alone. From an extensive analysis, it is found that the proposed end-to-end scheme is very effective in detecting COVID-19 severity scores from LUS images.
“…Hence, in this case, the focus of the Grad-CAM algorithm has been spread over a comparatively larger region. As the score rises up to 3, the model activates in a more indicative manner as patchy areas of B-lines, irregular pleural lines, and consolidations in the subpleural region, i.e., symptoms for an unhealthy lung [ 35 ] are prevalent there. Figure 6 The heatmaps indicate which portions instigated the classification decision in the frames acquired from both convex and linear probes.…”
The COVID-19 pandemic has become one of the biggest threats to the global healthcare system, creating an unprecedented condition worldwide. The necessity of rapid diagnosis calls for alternative methods to predict the condition of the patient, for which disease severity estimation on the basis of Lung Ultrasound (LUS) can be a safe, radiation-free, flexible, and favorable option. In this paper, a frame-based 4-score disease severity prediction architecture is proposed with the integration of deep convolutional and recurrent neural networks to consider both spatial and temporal features of the LUS frames. The proposed convolutional neural network (CNN) architecture implements an autoencoder network and separable convolutional branches fused with a modified DenseNet-201 network to build a vigorous, noise-free classification model. A five-fold cross-validation scheme is performed to affirm the efficacy of the proposed network. In-depth result analysis shows a promising improvement in the classification performance by introducing the Long Short-Term Memory (LSTM) layers after the proposed CNN architecture by an average of
, which is approximately
more than the traditional DenseNet architecture alone. From an extensive analysis, it is found that the proposed end-to-end scheme is very effective in detecting COVID-19 severity scores from LUS images.
“…ML methodology with chest CT scans to diagnose Covid-19 disease, COVID-19-related pneumonia, or aid in image segmentation of the lungs. Pulmonary ultrasound can be used to triage patients who may have pneumonitis (21) . The results show a high to nearly perfect ability to identify covid-19, although this model and its evaluation also carry a high risk of bias, mainly due to poorly reported reporting (13) .…”
Section: Figure 4: Display On Smartphone Room Temperature Resultsmentioning
Technology development triggers the development of human thought to be able to create innovations to improve performance. The increasing cases of COVID-19 infection mean that you should seek to break the chain of this virus by self-isolation. However, the purpose of self-isolation rooms should be considered especially at rooms without air conditioning. These technological innovations are needed to provide comfort for patients and families. The goal of this study is to give families of COVID-19 positive patients easy access to their loved ones' rooms without having to physically enter the room. The procedure is artificial intelligence with Arduino programming using Arduino IDE that is part of the micro controller board. Microcontrolled systems can be thought of as being like an integrated computer system packaged in a single chip. The result showed the temperature control system tool was able to work well with a temperature error rate of 1.13%. It is known that in COVID-19-positive patients it is very helpful for families to monitor room temperature and for patients to rest comfortably.
“…The anterior chest wall extended from the para sternal to the anterior axillary line and was subdivided into three areas [from clavicle to second intercostal space; infraclavicular, between fifth and sixth intercostal spaces; infra mammary, and between third and fourth intercostal spaces; mammary]. The lateral zone extended between the anterior and the posterior axillary line and was furtherly subdivided into upper and basal halves by the oblique fissure, which can be estimated with a line from the sixth costochondral junction to the tip of the scapular spine at the mid axillary line [16]. While the back "between the spine and medial border of the scapula" was divided into three zones; supra scapular: at second intercostal space; interscapular: at the level of fifth to seventh intercostal space; and infrascapular: at ninth intercostal space [17].…”
Background
Malignant pleural effusions (MPE) mostly arises from metastases to the pleura from other sites. Management of malignant effusions aims to palliate dyspnea and prevent the reaccumulation of pleural fluid to improve patients’ quality of life. Pleurodesis is the most common palliative treatment for patients with refractory MPE. This study was carried out to evaluate the performance of transthoracic sonographic (TUS) scores (pleural sliding and pleural adherence score) in predicting the success of pleurodesis by different modalities in patients with malignant pleural effusion. One hundred malignant pleural effusion patients were enrolled to an interventional clinical trial from September 2019 to April 2021 for palliative management of dyspnea. Pleurodesis for palliative treatment of dyspnea was done either spontaneously by the intercostal chest tube or by a sclerosing agent such as tetracycline solution or tetracycline poudrage or iodopovidine. Patients were randomly allocated to one of these four groups where each group included 25 patients. Transthoracic ultrasound was performed at baseline, and 1 month after pleurodesis and the lung sliding score and pleural adherence score were evaluated.
Results
Majority of patients (78%) had high baseline lung sliding score (7-8). Post pleurodesis only 11.4% had high scores (p<0.001), also the mean lung sliding score decreased significantly in comparison to the baseline values (p˂ 0.001) in the spontaneous, tetracycline solution, tetracycline poudrage, and iodopovidine groups (7.04 ± 1.02 vs. 4.85 ± 1.60, 7.28± 0.98 vs. 4.48± 1.75, 7.20±0.96 vs. 4.44 ± 1.45, 7.04±0.93 vs. 3.35±1.81, respectively). Iodopovidine pleurodesis group in comparison to the other modalities showed the highest pleural adherence score (12.64 ± 2.98) and absent lung sliding in 72.7% of cases and 70 % success rate. Pleural adherence score at cut off ≥ 12 showed 92.75% sensitivity, 89.47% specificity, 92.1 accuracy, and 0.911 area under the curve (AUC) for predicting successful pleurodesis.
Conclusion
TUS scores is a feasible, bedside, and accurate method to detect the outcome of pleurodesis. Iodopovidone was more effective than tetracycline solution, tetracycline poudrage, and spontaneous pleurodesis.
Trial registration
ClinicalTrials.gov. NCT04074902. Registered on 29 August 2019
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
