Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 168
Filter
Add filters

Document Type
Year range
1.
IEEE Rev Biomed Eng ; 14: 16-29, 2021.
Article in English | MEDLINE | ID: covidwho-1501334

ABSTRACT

Coronavirus disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is spreading rapidly around the world, resulting in a massive death toll. Lung infection or pneumonia is the common complication of COVID-19, and imaging techniques, especially computed tomography (CT), have played an important role in diagnosis and treatment assessment of the disease. Herein, we review the imaging characteristics and computing models that have been applied for the management of COVID-19. CT, positron emission tomography - CT (PET/CT), lung ultrasound, and magnetic resonance imaging (MRI) have been used for detection, treatment, and follow-up. The quantitative analysis of imaging data using artificial intelligence (AI) is also explored. Our findings indicate that typical imaging characteristics and their changes can play crucial roles in the detection and management of COVID-19. In addition, AI or other quantitative image analysis methods are urgently needed to maximize the value of imaging in the management of COVID-19.


Subject(s)
COVID-19/diagnosis , Artificial Intelligence , COVID-19/diagnostic imaging , Humans , Lung/diagnostic imaging , Lung/virology , Positron Emission Tomography Computed Tomography/methods , SARS-CoV-2/pathogenicity , Tomography, X-Ray Computed/methods , Ultrasonography/methods
2.
Pediatr Ann ; 50(10): e404-e410, 2021 Oct.
Article in English | MEDLINE | ID: covidwho-1456368

ABSTRACT

Point-of-care ultrasound (POCUS) is a noninvasive imaging tool with both diagnostic and therapeutic applications. In this article, the author will review the role of POCUS for vascular access, endotracheal intubation, lumbar puncture, chest tube, and diagnosing coronavirus disease 2019 lung pathology. This will include a review of the evidence, technique, and strategies for optimizing performance of these procedures. [Pediatr Ann. 2021;50(10):e404-e410.].


Subject(s)
COVID-19 , Pediatrics , Point-of-Care Systems , Ultrasonography/methods , Child , Humans , SARS-CoV-2
4.
Clin Otolaryngol ; 46(6): 1304-1309, 2021 11.
Article in English | MEDLINE | ID: covidwho-1429583

ABSTRACT

INTRODUCTION: Unilateral vocal cord paralysis (UVCP) is a known complication of thyroid surgery, due to iatrogenic recurrent laryngeal nerve injury, with reported rates of 2%-5% in children. The gold standard for assessing vocal cord function in flexible nasendoscopy (FNE) examination, which is considered high-risk for contraction of the COVID-19 virus. Intraoperative ultrasonographic assessment (IUA) of vocal cord function is a non-invasive and relatively simple procedure performed in a supine position, performed during spontaneous breathing, following reversed anaesthesia, while the patient is still sedated. OBJECTIVES: To evaluate the validity of IUA modality in children undergoing thyroidectomy and to compare it to the standard FNE. DESIGN: A prospective double-blind study covering 24 months (March 2019-March 2021). Twenty thyroid lobectomies were performed, during 15 surgeries. Vocal cord function was assessed three times: Pre-operatively by FNE, intraoperative (IUA) following extubation, and a second FNE on the first post-operative day. SETTINGS: A tertiary paediatric hospital. RESULTS: The overall accuracy of IUA results in our study was 92%. IUA sensitivity, specificity, positive and negative predictive values were 100%, 89%, 33% and 100%, respectively. Patient's age demonstrated borderline significance (p = .08). The resident's experience was associated with a better correlation between IUA and FNE results (p < .05). CONCLUSIONS: IUA of vocal cord motion has a high accuracy rate for detection of iatrogenic vocal cord paralysis, similar to FNE. It is easily learned by residents, well-tolerated by children, and it provides a safe and valid alternative modality while ensuring the safety of the medical staff in treating patients, especially in times of COVID-19 pandemic.


Subject(s)
COVID-19/epidemiology , Postoperative Complications/diagnostic imaging , Thyroidectomy , Ultrasonography/methods , Vocal Cord Paralysis/diagnostic imaging , Adolescent , Child , Double-Blind Method , Female , Humans , Iatrogenic Disease , Male , Monitoring, Intraoperative , Pandemics , Prospective Studies , SARS-CoV-2
5.
Ultrasound Q ; 37(3): 261-266, 2021 Mar 03.
Article in English | MEDLINE | ID: covidwho-1413343

ABSTRACT

OBJECTIVE: The aim of this study was to identify the sensitivity and specificity of lung ultrasound (LUS) and show its place in diagnosing patients with known coronavirus disease 2019 (COVID-19) pneumonia, according to chest computed tomography and the COVID-19 reporting and data system (CO-RADS). METHODS: Nineteen patients who admitted to a single university hospital emergency department between March 5, 2020, and April 27, 2020, describing dyspnea were included in the study and underwent LUS by a single emergency specialist. The patient population was divided into 2 groups, COVID-19 positive and negative, and the sensitivity and specificity of LUS according to chest computed tomography were calculated for COVID-19 pneumonia diagnosis. In the subgroup analysis, the patient group was divided into real-time reverse transcription-polymerase chain reaction positive (n = 7) and negative (n = 12), and sensitivity and specificity were calculated according to the CO-RADS. RESULTS: According to the CO-RADS, significant differences were detected between the LUS positive and negative groups in terms of COVID-19 pneumonia presence. Only 1 patient was evaluated as CO-RADS 2 in the LUS positive group, and 2 patients were evaluated as CO-RADS 4 in the LUS negative group (P = 0.04). The sensitivity of LUS according to the CO-RADS for COVID-19 pneumonia diagnosis was measured to be 77.78% (95% confidence interval [CI], 39.9%-97.1%), specificity was 90% (95% CI, 55.5%-99.75%), positive predictive value was 87.5% (95% CI, 51.35%-97.8%), and accuracy was 84.21% (95% CI, 60.4%-96.62%; P = 0.004). CONCLUSIONS: In conclusion, LUS is easily used in the diagnosis of COVID-19 pneumonia because it has bedside application and is fast, easy to apply, reproducible, radiation free, safe for pregnant women, and cheap.


Subject(s)
COVID-19/diagnosis , Emergency Service, Hospital/statistics & numerical data , Lung/diagnostic imaging , Pandemics , SARS-CoV-2 , Ultrasonography/methods , COVID-19/epidemiology , Female , Humans , Male , Middle Aged , Predictive Value of Tests , Retrospective Studies
6.
Ultrasound Med Biol ; 47(11): 3034-3040, 2021 11.
Article in English | MEDLINE | ID: covidwho-1376111

ABSTRACT

Chest computed tomography has been frequently used to evaluate patients with potential coronavirus disease 2019 (COVID-19) infection. However, this may be particularly risky for pediatric patients owing to high doses of ionizing radiation. We sought to evaluate COVID-19 imaging options in pediatric patients based on the published literature. We performed an exhaustive literature review focusing on COVID-19 imaging in pediatric patients. We used the search terms "COVID-19," "SARS-CoV2," "coronavirus," "2019-nCoV," "Wuhan virus," "lung ultrasound (LUS)," "sonography," "lung HRCT," "children," "childhood" and "newborn" to query the online databases PubMed, Medical Subject Headings (MeSH), Embase, LitCovid, the World Health Organization COVID-19 database and Medline Bireme. Articles meeting the inclusion criteria were included in the analysis and review. We identified only seven studies using lung ultrasound (LUS) to diagnose severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection in newborns and children. The studies evaluated small numbers of patients, and only 6% had severe or critical illness associated with COVID-19. LUS showed the presence of B-lines in 50% of patients, sub-pleural consolidation in 43.18%, pleural irregularities in 34.09%, coalescent B-lines and white lung in 25%, pleural effusion in 6.82% and thickening of the pleural line in 4.55%. We found 117 studies describing the use of chest X-ray or chest computed tomography in pediatric patients with COVID-19. The proportion of those who were severely or critically ill was similar to that in the LUS study population. Our review indicates that use of LUS should be encouraged in pediatric patients, who are at highest risk of complications from medical ionizing radiation. Increased use of LUS may be of particularly high impact in under-resourced areas, where access to chest computed tomography may be limited.


Subject(s)
COVID-19/diagnostic imaging , Radiography/methods , Ultrasonography/methods , Adolescent , Child , Child, Preschool , Humans , Infant , Infant, Newborn , Lung/diagnostic imaging , SARS-CoV-2 , Tomography, X-Ray Computed/methods
7.
PLoS One ; 16(8): e0256359, 2021.
Article in English | MEDLINE | ID: covidwho-1372011

ABSTRACT

PURPOSE: To evaluate whether there is a change in findings of coronavirus disease 2019 patients in follow up lung ultrasound and to determine whether these findings can predict the development of severe disease. MATERIALS AND METHODS: In this prospective monocentric study COVID-19 patients had standardized lung ultrasound (12 area evaluation) at day 1, 3 and 5. The primary end point was detection of pathologies and their change over time. The secondary end point was relationship between change in sonographic results and clinical outcome. Clinical outcome was assessed on development of severe disease defined as need for intensive care unit. RESULTS: Data of 30 patients were analyzed, 26 patients with follow-up lung ultrasound. All of them showed lung pathologies with dynamic patterns. 26,7% developed severe disease tending to have an ubiquitous lung involvement in lung ultrasound. In patients with need for intensive care unit a previously developed increase in B-lines, subpleural consolidations and pleural line irregularities was more common. A statistically significant association between change in B-lines as well as change in pleural line irregularities and development of severe disease was observed (p<0,01). CONCLUSION: The present study demonstrates that follow up lung ultrasound can be a powerful tool to track the evolution of disease and suggests that lung ultrasound is able to indicate an impending development of severe disease in COVID-19 patients.


Subject(s)
COVID-19/pathology , Lung/diagnostic imaging , Ultrasonography/methods , Aged , Aged, 80 and over , COVID-19/complications , COVID-19/diagnostic imaging , COVID-19/virology , Female , Follow-Up Studies , Humans , Intensive Care Units , Male , Middle Aged , Pleural Effusion/etiology , Prospective Studies , SARS-CoV-2/isolation & purification
9.
G Ital Cardiol (Rome) ; 22(8): 638-647, 2021 Aug.
Article in Italian | MEDLINE | ID: covidwho-1365476

ABSTRACT

In recent years, lung ultrasonography has acquired an important role as a valuable diagnostic tool in clinical practice. The lung is usually poorly explorable, but it provides more acoustic information in pathological conditions that modify the relationship between air, water and tissues. The different acoustic impedance of all these components makes the chest wall a powerful ultrasound reflector: this is responsible for the creation of several artifacts providing valuable information about lung pathophysiology. Lung ultrasonography helps in the diagnostic process of parenchymal and pleural pathologies, in the differential diagnosis of dyspnea and in the clinical and prognostic evaluation of the SARS-CoV-2 infection.


Subject(s)
COVID-19/diagnostic imaging , Lung/diagnostic imaging , Ultrasonography/methods , Cardiologists , Diagnosis, Differential , Dyspnea/diagnostic imaging , Humans , Lung/virology , Lung Diseases/diagnostic imaging , Lung Diseases/physiopathology , Prognosis
10.
PLoS One ; 16(8): e0255886, 2021.
Article in English | MEDLINE | ID: covidwho-1357433

ABSTRACT

BACKGROUND: The COVID-19 pandemic has exposed the vulnerability of healthcare services worldwide, especially in underdeveloped countries. There is a clear need to develop novel computer-assisted diagnosis tools to provide rapid and cost-effective screening in places where massive traditional testing is not feasible. Lung ultrasound is a portable, easy to disinfect, low cost and non-invasive tool that can be used to identify lung diseases. Computer-assisted analysis of lung ultrasound imagery is a relatively recent approach that has shown great potential for diagnosing pulmonary conditions, being a viable alternative for screening and diagnosing COVID-19. OBJECTIVE: To evaluate and compare the performance of deep-learning techniques for detecting COVID-19 infections from lung ultrasound imagery. METHODS: We adapted different pre-trained deep learning architectures, including VGG19, InceptionV3, Xception, and ResNet50. We used the publicly available POCUS dataset comprising 3326 lung ultrasound frames of healthy, COVID-19, and pneumonia patients for training and fine-tuning. We conducted two experiments considering three classes (COVID-19, pneumonia, and healthy) and two classes (COVID-19 versus pneumonia and COVID-19 versus non-COVID-19) of predictive models. The obtained results were also compared with the POCOVID-net model. For performance evaluation, we calculated per-class classification metrics (Precision, Recall, and F1-score) and overall metrics (Accuracy, Balanced Accuracy, and Area Under the Receiver Operating Characteristic Curve). Lastly, we performed a statistical analysis of performance results using ANOVA and Friedman tests followed by post-hoc analysis using the Wilcoxon signed-rank test with the Holm's step-down correction. RESULTS: InceptionV3 network achieved the best average accuracy (89.1%), balanced accuracy (89.3%), and area under the receiver operating curve (97.1%) for COVID-19 detection from bacterial pneumonia and healthy lung ultrasound data. The ANOVA and Friedman tests found statistically significant performance differences between models for accuracy, balanced accuracy and area under the receiver operating curve. Post-hoc analysis showed statistically significant differences between the performance obtained with the InceptionV3-based model and POCOVID-net, VGG19-, and ResNet50-based models. No statistically significant differences were found in the performance obtained with InceptionV3- and Xception-based models. CONCLUSIONS: Deep learning techniques for computer-assisted analysis of lung ultrasound imagery provide a promising avenue for COVID-19 screening and diagnosis. Particularly, we found that the InceptionV3 network provides the most promising predictive results from all AI-based techniques evaluated in this work. InceptionV3- and Xception-based models can be used to further develop a viable computer-assisted screening tool for COVID-19 based on ultrasound imagery.


Subject(s)
COVID-19/diagnostic imaging , Deep Learning , Image Processing, Computer-Assisted/methods , Lung/diagnostic imaging , Ultrasonography/methods , Humans
11.
Shock ; 56(2): 200-205, 2021 08 01.
Article in English | MEDLINE | ID: covidwho-1316852

ABSTRACT

PURPOSE: We used lung ultrasonography to identify features of COVID-19 pneumonia and to evaluate the prognostic value. PATIENTS AND METHODS: We performed lung ultrasonography on 48 COVID-19 patients in an intensive care unit (ICU) (Wuhan, China) using a 12-zone method. The associations between lung ultrasonography score, PaO2/FiO2, APACHE II, SOFA, and PaCO2 with 28-day mortality were analyzed and the receiver operator characteristic curve was plotted. RESULTS: 25.9% areas in all scanning zones presented with B7 lines and 23.5% with B3 lines (B-pattern) on lung ultrasonography; 13% areas with confluent B lines (B-pattern), 24.9% in areas with consolidations, and 9.9% in areas with A lines. Pleural effusion was observed in 2.8% of areas. Lung ultrasonography score was negatively correlated with PaO2/FiO2 (n = 48, r = -0.498, P < 0.05) and positively correlated with APACHE II (n = 48, r = 0.435, P < 0.05). Lung ultrasonography score was independently associated with 28-day mortality. The areas under receiver operator characteristic curves of lung ultrasonography score were 0.735 (95% CI: 0.586-0.844). The sensitivity, specificity, and cutoff values were 0.833, 0.722, and 22.5, respectively. CONCLUSIONS: Lung ultrasonography could be used to assess the severity of COVID-19 pneumonia, and it could also reveal the pathological signs of the disease. The lung ultrasonography score on ICU admission was independently related to the ICU 28-day mortality.


Subject(s)
COVID-19/diagnosis , Lung/diagnostic imaging , Ultrasonography/methods , Aged , COVID-19/epidemiology , Female , Follow-Up Studies , Humans , Male , Middle Aged , Pandemics , Prognosis , Prospective Studies , ROC Curve , SARS-CoV-2
13.
Ann Clin Transl Neurol ; 8(8): 1745-1749, 2021 08.
Article in English | MEDLINE | ID: covidwho-1303224

ABSTRACT

Many survivors from severe coronavirus disease 2019 (COVID-19) suffer from persistent dyspnea and fatigue long after resolution of the active infection. In a cohort of 21 consecutive severe post-COVID-19 survivors admitted to an inpatient rehabilitation hospital, 16 (76%) of them had at least one sonographic abnormality of diaphragm muscle structure or function. This corresponded to a significant reduction in diaphragm muscle contractility as represented by thickening ratio (muscle thickness at maximal inspiration/end-expiration) for the post-COVID-19 compared to non-COVID-19 cohorts. These findings may shed new light on neuromuscular respiratory dysfunction as a contributor to prolonged functional impairments after hospitalization for post-COVID-19.


Subject(s)
COVID-19/complications , Diaphragm , Ultrasonography/methods , Adult , Aged , Aged, 80 and over , COVID-19/diagnostic imaging , COVID-19/pathology , COVID-19/physiopathology , Diaphragm/diagnostic imaging , Diaphragm/pathology , Diaphragm/physiopathology , Female , Hospitals, Rehabilitation , Humans , Inpatients , Male , Middle Aged
14.
IEEE Trans Ultrason Ferroelectr Freq Control ; 68(7): 2507-2515, 2021 07.
Article in English | MEDLINE | ID: covidwho-1288239

ABSTRACT

As being radiation-free, portable, and capable of repetitive use, ultrasonography is playing an important role in diagnosing and evaluating the COVID-19 Pneumonia (PN) in this epidemic. By virtue of lung ultrasound scores (LUSS), lung ultrasound (LUS) was used to estimate the excessive lung fluid that is an important clinical manifestation of COVID-19 PN, with high sensitivity and specificity. However, as a qualitative method, LUSS suffered from large interobserver variations and requirement for experienced clinicians. Considering this limitation, we developed a quantitative and automatic lung ultrasound scoring system for evaluating the COVID-19 PN. A total of 1527 ultrasound images prospectively collected from 31 COVID-19 PN patients with different clinical conditions were evaluated and scored with LUSS by experienced clinicians. All images were processed via a series of computer-aided analysis, including curve-to-linear conversion, pleural line detection, region-of-interest (ROI) selection, and feature extraction. A collection of 28 features extracted from the ROI was specifically defined for mimicking the LUSS. Multilayer fully connected neural networks, support vector machines, and decision trees were developed for scoring LUS images using the fivefold cross validation. The model with 128×256 two fully connected layers gave the best accuracy of 87%. It is concluded that the proposed method could assess the ultrasound images by assigning LUSS automatically with high accuracy, potentially applicable to the clinics.


Subject(s)
COVID-19/diagnostic imaging , Image Interpretation, Computer-Assisted/methods , Lung/diagnostic imaging , Neural Networks, Computer , Ultrasonography/methods , Adult , Aged , Female , Humans , Male , Middle Aged , SARS-CoV-2
15.
BMC Anesthesiol ; 21(1): 178, 2021 06 28.
Article in English | MEDLINE | ID: covidwho-1286811

ABSTRACT

BACKGROUND: Point-of-care lung ultrasound (LU) is an established tool in the first assessment of patients with coronavirus disease (COVID-19). Purpose of this study was to evaluate the value of lung ultrasound in COVID-19 intensive care unit (ICU) patients in predicting clinical course and outcome. METHODS: We analyzed lung ultrasound score (LUS) of all COVID-19 patients admitted from March 2020 to December 2020 to the Internal Intensive Care Unit, Ludwig-Maximilians-University (LMU) of Munich. LU was performed according to a standardized protocol at ICU admission and in case of clinical deterioration with the need for intubation. A normal lung scores 0 points, the worst LUS has 24 points. Patients were stratified in a low (0-12 points) and a high (13-24 points) lung ultrasound score group. RESULTS: The study included 42 patients, 69% of them male. The most common comorbidities were hypertension (81%) and obesity (57%). The values of pH (7.42 ± 0.09 vs 7.35 ± 0.1; p = 0.047) and paO2 (107 [80-130] vs 80 [66-93] mmHg; p = 0.034) were significantly reduced in patients of the high LUS group. Furthermore, the duration of ventilation (12.5 [8.3-25] vs 36.5 [9.8-70] days; p = 0.029) was significantly prolonged in this group. Patchy subpleural thickening (n = 38; 90.5%) and subpleural consolidations (n = 23; 54.8%) were present in most patients. Pleural effusion was rare (n = 4; 9.5%). The median total LUS was 11.9 ± 3.9 points. In case of clinical deterioration with the need for intubation, LUS worsened significantly compared to baseline LU. Twelve patients died during the ICU stay (29%). There was no difference in survival in both LUS groups (75% vs 66.7%, p = 0.559). CONCLUSIONS: LU can be a useful monitoring tool to predict clinical course but not outcome of COVID-19 ICU patients and can early recognize possible deteriorations.


Subject(s)
COVID-19/diagnosis , COVID-19/epidemiology , Critical Care/methods , Lung/diagnostic imaging , SARS-CoV-2 , Ultrasonography/methods , Aged , COVID-19/pathology , Female , Germany/epidemiology , Humans , Male , Middle Aged , Point-of-Care Testing , Predictive Value of Tests , Prognosis , Retrospective Studies
16.
Ultrasound Med Biol ; 47(8): 1997-2005, 2021 08.
Article in English | MEDLINE | ID: covidwho-1286382

ABSTRACT

The goal of this review was to systematize the evidence on pulmonary ultrasound (PU) use in diagnosis, monitorization or hospital discharge criteria for patients with coronavirus disease 2019 (COVID-19). Evidence on the use of PU for diagnosis and monitorization of or as hospital discharge criteria for COVID-19 patients confirmed to have COVID-19 by reverse transcription polymerase chain reaction (RT-PCR) between December 1, 2019 and July 5, 2020 was compared with evidence obtained with thoracic radiography (TR), chest computed tomography (CT) and RT-PCR. The type of study, motives for use of PU, population, type of transducer and protocol, results of PU and quantitative or qualitative correlation with TR and/or chest CT and/or RT-PCR were evaluated. A total of 28 articles comprising 418 patients were involved. The average age was 50 y (standard deviation: 25.1 y), and there were 395 adults and 23 children. One hundred forty-three were women, 13 of whom were pregnant. The most frequent result was diffuse, coalescent and confluent B-lines. The plural line was irregular, interrupted or thickened. The presence of subpleural consolidation was noduliform, lobar or multilobar. There was good qualitative correlation between TR and chest CT and a quantitative correlation with chest CT of r = 0.65 (p < 0.001). Forty-four patients were evaluated only with PU. PU is a useful tool for diagnosis and monitorization and as criteria for hospital discharge for patients with COVID-19.


Subject(s)
COVID-19 Testing/methods , COVID-19/diagnosis , Lung/diagnostic imaging , Ultrasonography/methods , Humans , SARS-CoV-2
17.
IEEE Trans Ultrason Ferroelectr Freq Control ; 67(11): 2258-2264, 2020 11.
Article in English | MEDLINE | ID: covidwho-1284995

ABSTRACT

Lung ultrasound (LUS) is a practical tool for lung diagnosis when computer tomography (CT) is not available. Recent findings suggest that LUS diagnosis is highly advantageous because of its mobility and correlation with radiological findings for viral pneumonia. Simple models for both educational evaluation and technical evaluation are needed. Therefore, this work investigates the usability of a large animal model under aspects of LUS features of viral pneumonia using saline one lung flooding. Six pigs were intubated with a double-lumen tube, and the left lung was instilled with saline. During the instillation of up to 12.5 ml/kg, the sonographic features were assessed. All features present during viral pneumonia were found, such as B-lines, white lung syndrome, pleural thickening, and the formation of pleural consolidations. Sonographic findings correlate well with current LUS scores for COVID19. The scores of 1, 2, and 3 were dominantly present at 1-4-, 4-8-, and 8-12-ml/kg saline instillation, respectively. The noninfective animal model can be used for further investigation of the LUS features and can serve in education, by helping with the appropriate handling of LUS in clinical practice during management of viral pneumonia.


Subject(s)
Image Interpretation, Computer-Assisted/methods , Lung , Pneumonia, Viral , Ultrasonography/methods , Animals , COVID-19 , Female , Lung/diagnostic imaging , Lung/pathology , Pneumonia, Viral/diagnostic imaging , Pneumonia, Viral/pathology , Swine
19.
Ultrasound Med Biol ; 47(8): 2080-2089, 2021 08.
Article in English | MEDLINE | ID: covidwho-1258503

ABSTRACT

Severe acute respiratory syndrome coronavirus 2 causes coronavirus disease 2019 (Covid-19), which has been declared as a pandemic by the World Health Organization. The aim of the study described here was to determine the severity of pneumonia and the clinical parameters related to a modified lung ultrasound score (mLUS) in patients with COVID-19 pneumonia. The study included 44 patients with proven COVID-19 pneumonia. Patients were divided into three groups on the basis of pneumonia severity: mild/moderate pneumonia (group I), severe pneumonia (group II) and critically ill patients (group III). It was determined that mLUS values in groups I-III were 6.51 ± 4.12, 23.5 ± 5.9 and 24.7 ± 3.9, respectively. mLUS values were significantly higher in group II and III patients than in group I patients. There was a positive relationship between mLUS and age and N-terminal pro-brain natriuretic peptide level and a negative relationship with PaO2/FiO2 (p = 0.032, ß = 0.275 vs. p = 0.012, ß = 0.315 vs. p = 0.001, ß = -0.520, respectively). In patients with COVID-19 pneumonia, mLUS increases significantly with the severity of the disease.


Subject(s)
COVID-19/diagnosis , Lung/diagnostic imaging , SARS-CoV-2 , Ultrasonography/methods , Aged , Cross-Sectional Studies , Female , Humans , Male , Middle Aged , Severity of Illness Index
20.
IEEE Trans Ultrason Ferroelectr Freq Control ; 68(6): 2023-2037, 2021 06.
Article in English | MEDLINE | ID: covidwho-1243581

ABSTRACT

Lung ultrasound (US) imaging has the potential to be an effective point-of-care test for detection of COVID-19, due to its ease of operation with minimal personal protection equipment along with easy disinfection. The current state-of-the-art deep learning models for detection of COVID-19 are heavy models that may not be easy to deploy in commonly utilized mobile platforms in point-of-care testing. In this work, we develop a lightweight mobile friendly efficient deep learning model for detection of COVID-19 using lung US images. Three different classes including COVID-19, pneumonia, and healthy were included in this task. The developed network, named as Mini-COVIDNet, was bench-marked with other lightweight neural network models along with state-of-the-art heavy model. It was shown that the proposed network can achieve the highest accuracy of 83.2% and requires a training time of only 24 min. The proposed Mini-COVIDNet has 4.39 times less number of parameters in the network compared to its next best performing network and requires a memory of only 51.29 MB, making the point-of-care detection of COVID-19 using lung US imaging plausible on a mobile platform. Deployment of these lightweight networks on embedded platforms shows that the proposed Mini-COVIDNet is highly versatile and provides optimal performance in terms of being accurate as well as having latency in the same order as other lightweight networks. The developed lightweight models are available at https://github.com/navchetan-awasthi/Mini-COVIDNet.


Subject(s)
COVID-19/diagnostic imaging , Deep Learning , Image Interpretation, Computer-Assisted/methods , Point-of-Care Systems , Ultrasonography/methods , Humans , SARS-CoV-2
SELECTION OF CITATIONS
SEARCH DETAIL
...