Point-of-care lung ultrasound in the assessment of patients with COVID-19: A tutorial

Transthoracic sonographic scores in evaluating the success of different scelerosing modalities in patients with malignant pleural effusion

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

SpecMEn-DL: spectral mask enhancement with deep learning models to predict COVID-19 from lung ultrasound videos

Lung Ultrasound (LUS) images are considered to be effective for detecting Coronavirus Disease (COVID-19) as an alternative to the existing reverse transcription-polymerase chain reaction (RT-PCR)-based detection scheme. However, the recent literature exhibits a shortage of works dealing with LUS image-based COVID-19 detection. In this paper, a spectral mask enhancement (SpecMEn) scheme is introduced along with a histogram equalization pre-processing stage to reduce the noise effect in LUS images prior to utilizing them for feature extraction. In order to detect the COVID-19 cases, we propose to utilize the SpecMEn pre-processed LUS images in the deep learning (DL) models (namely the SpecMEn-DL method), which offers a better representation of some characteristics features in LUS images and results in very satisfactory classification performance. The performance of the proposed SpecMEn-DL technique is appraised by implementing some state-of-the-art DL models and comparing the results with related studies. It is found that the use of the SpecMEn scheme in DL techniques offers an average increase in accuracy and F 1 score of 11 % and 11.75 % , respectively, at the video-level. Comprehensive analysis and visualization of the intermediate steps manifest a very satisfactory detection performance creating a flexible and safe alternative option for the clinicians to get assistance while obtaining the immediate evaluation of the patients.

An integrated autoencoder-based hybrid CNN-LSTM model for COVID-19 severity prediction from lung ultrasound

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 7-12%, which is approximately 17% 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.