Lung ultrasound: an additional tool in COVID-19

Oliveira, Rodrigo Ribeiro de; Rodrigues, Thiago Potrich; Silva, Paulo Savoia Dias da; Gomes, Andreia; Chammas, M.C.

doi:10.1590/0100-3984.2020.0051

Cited by 19 publications

(20 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, they have a longer acoustic wavelength and provide better penetration and visualization of deeper structures. This type of transducer is, therefore, best suited for evaluating consolidations and pleural effusions [ 27 , 130 ]. On the other hand, high-frequency transducers have a high resolution compared to low-frequency transducers and are more suitable for evaluating the pleural region.…”

Section: Methodsmentioning

confidence: 99%

“…Lung ultrasound (LUS) has good sensitivity in detecting lung pathology (bacterial or viral) [ 25 , 26 ]. Regarding COVID-19, studies report a high correlation between the clinical findings of the LUS and the chest CT examination [ 27 , 28 , 29 , 30 , 31 , 32 ]. In this sense, some studies suggest the use of ultrasound as an alternative to auscultation and auxiliary XR and CT exams [ 33 , 34 , 35 , 36 , 37 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pulmonary COVID-19: Learning Spatiotemporal Features Combining CNN and LSTM Networks for Lung Ultrasound Video Classification

Barros

Lacerda

Albuquerque

et al. 2021

Sensors

View full text Add to dashboard Cite

Deep Learning is a very active and important area for building Computer-Aided Diagnosis (CAD) applications. This work aims to present a hybrid model to classify lung ultrasound (LUS) videos captured by convex transducers to diagnose COVID-19. A Convolutional Neural Network (CNN) performed the extraction of spatial features, and the temporal dependence was learned using a Long Short-Term Memory (LSTM). Different types of convolutional architectures were used for feature extraction. The hybrid model (CNN-LSTM) hyperparameters were optimized using the Optuna framework. The best hybrid model was composed of an Xception pre-trained on ImageNet and an LSTM containing 512 units, configured with a dropout rate of 0.4, two fully connected layers containing 1024 neurons each, and a sequence of 20 frames in the input layer (20×2018). The model presented an average accuracy of 93% and sensitivity of 97% for COVID-19, outperforming models based purely on spatial approaches. Furthermore, feature extraction using transfer learning with models pre-trained on ImageNet provided comparable results to models pre-trained on LUS images. The results corroborate with other studies showing that this model for LUS classification can be an important tool in the fight against COVID-19 and other lung diseases.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Pulmonary COVID-19: Learning Spatiotemporal Features Combining CNN and LSTM Networks for Lung Ultrasound Video Classification

Barros

Lacerda

Albuquerque

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Some protocols evaluate 14 areas (two anterior, two lateral and three posterior areas in each hemithorax) and constitute a scoring system based on findings. 48 It was reported that scoring systems based on B-line were correlated with oxygen parameters, and thus, LUS can be used for COVID-19 pneumonia severity estimation. 49 To determine disease severity, a scoring system to avoid subjectivity and the operator-dependence of the exam was suggested by Soldati et al According to this system, normal LUS pattern characterized by regular pleural line and A-lines is score 0 vertical artifacts are described.…”

Section: Of Lus In Covid-19 Pneumoniamentioning

confidence: 99%

The role of lung ultrasonography in evaluation of COVID-19 pneumonia

2021

View full text Add to dashboard Cite

After a few months it emerged in Wuhan (China), Coronavirus Disease 2019 (COVID-19) caused by 2019 novel coronavirus (2019-nCoV) was declared as a pandemic by the World Health Organization (WHO). Diagnosis of the disease is mainly based on real time polymerase chain reaction (PCR) test by nasopharyngeal swab. However, due to excess of numbers of false-negative PCR test results, chest computed tomography (CT) is commonly used as a supplementary modality. However, CT has some disadvantages. Firstly, a normal chest CT scan does not exclude the diagnosis of COVID-19 pneumonia. Additionally, the radiation exposure and a weak diagnostic value are other challenges. When the infection is limited to upper respiratory system or performed in the early stage, false-negative results may be obtained on CT scan. Recently lung ultrasonography (LUS) has emerged as a easy-to-use, cost-effective and radiation-free tool in diagnosis, management and follow-up of COVID-19 pneumonia. In this narrative review, our aim is to clarify the utility of LUS in COVID-19 pneumonia with its advantages and disadvantages. We also aimed to guide clinicians to use LUS as a practical tool.

show abstract

“…In the previous issue of the Radiologia Brasileira, the text “Pulmonary ultrasound: an additional tool in COVID-19” ( 15 ) was published as a special article on the use of chest ultrasound in COVID-19, presenting the technique, normal findings, disinfection, main findings, and limitations as a screening method. Chest ultrasound is an additional tool in emergency care.…”

mentioning

confidence: 99%

“…The use of imaging methods to diagnose and control treatment in COVID-19 illustrates the central role of imagology in medicine. The special article by Oliveira et al ( 15 ) improves the knowledge of the several ultrasound uses in the fight against COVID-19 .This method, as a medical act, should be thought of as a foundation by the general radiologist.…”

mentioning

confidence: 99%