COVID­19 detection from chest X-ray images using transfer learning.

COVID-19 is a kind of coronavirus that appeared in China in the Province of Wuhan in December 2019. The most significant influence of this virus is its very highly contagious characteristic which may lead to death. The standard diagnosis of COVID-19 is based on swabs from the throat and nose, their sensitivity is not high enough and so they are prone to errors. Early diagnosis of COVID-19 disease is important to provide the chance of quick isolation of the suspected cases and to decrease the opportunity of infection in healthy people. In this research, a framework for chest X-ray image classification tasks based on deep learning is proposed to help in early diagnosis of COVID-19. The proposed framework contains two phases which are the pre-processing phase and classification phase which uses pre-trained convolution neural network models based on transfer learning. In the pre-processing phase, different image enhancements have been applied to full and segmented X-ray images to improve the classification performance of the CNN models. Two CNN pre-trained models have been used for classification which are VGG19 and EfficientNetB0. From experimental results, the best model achieved a sensitivity of 0.96, specificity of 0.94, precision of 0.9412, F1 score of 0.9505 and accuracy of 0.95 using enhanced full X-ray images for binary classification of chest X-ray images into COVID-19 or normal with VGG19. The proposed framework is promising and achieved a classification accuracy of 0.935 for 4-class classification.

More than what meets the eye in COVID-19 critical illness: A case report of bilateral femoral neuropathy due to psoas hematomas.

Bilateral femoral neuropathy is rare, especially that caused by bilateral compressive iliopsoas, psoas, or iliacus muscle hematomas. We present a case of bilateral femoral neuropathy due to spontaneous psoas hematomas developed during COVID-19 critical illness. A 41-year-old patient developed COVID-19 pneumonia, and his condition deteriorated rapidly. A decrease in the hemoglobin level prompted imaging studies during his intensive care unit (ICU) stay. Bilateral psoas hematomas were identified as the source of bleeding. Thereafter, the patient complained of weakness in both upper and lower limbs and numbness in the lower limb. He was considered to have critical illness neuropathy and was referred to rehabilitation. Electrodiagnostic testing suggested bilateral femoral neuropathy because of compression due to hematomas developed during the course of his ICU stay. The consequences of iliopsoas hematomas occurring in the critically ill can be catastrophic, ranging from hemorrhagic shock to severe weakness, highlighting the importance of recognizing this entity.

[Identifying Novel Coronavirus Pneumonia With CT Images: A Deep Learning Approach With Detail Upsampling and Attention Guidance]. / 从CTå›¾åƒä¸­æ£€æµ‹æ–°åž‹å† çŠ¶ç— æ¯’æ„ŸæŸ“å¯¼è‡´çš„è‚ºç‚Žï¼šä¸€ç§ç»†èŠ‚ä¸Šé‡‡æ ·å’Œæ³¨æ„åŠ›å¼•å¯¼çš„æ·±åº¦å­¦ä¹ æ–¹æ³•.

Objective: To construct a deep learning-based target detection method to help radiologists perform rapid diagnosis of lesions in the CT images of patients with novel coronavirus pneumonia (NCP) by restoring detailed information and mining local information. Methods: We present a deep learning approach that integrates detail upsampling and attention guidance. A linear upsampling algorithm based on bicubic interpolation algorithm was adopted to improve the restoration of detailed information within feature maps during the upsampling phase. Additionally, a visual attention mechanism based on vertical and horizontal spatial dimensions embedded in the feature extraction module to enhance the capability of the object detection algorithm to represent key information related to NCP lesions. Results: Experimental results on the NCP dataset showed that the detection method based on the detail upsampling algorithm improved the recall rate by 1.07% compared with the baseline model, with the AP50 reaching 85.14%. After embedding the attention mechanism in the feature extraction module, 86.13% AP50, 73.92% recall, and 90.37% accuracy were achieved, which were better than those of the popular object detection models. Conclusion: The feature information mining of CT images based on deep learning can further improve the lesion detection ability. The proposed approach helps radiologists rapidly identify NCP lesions on CT images and provides an important clinical basis for early intervention and high-intensity monitoring of NCP patients.

DDA-SSNets: Dual decoder attention-based semantic segmentation networks for COVID-19 infection segmentation and classification using chest X-Ray images.

BACKGROUND: COVID-19 needs to be diagnosed and staged to be treated accurately. However, prior studies' diagnostic and staging abilities for COVID-19 infection needed to be improved. Therefore, new deep learning-based approaches are required to aid radiologists in detecting and quantifying COVID-19-related lung infections. OBJECTIVE: To develop deep learning-based models to classify and quantify COVID-19-related lung infections. METHODS: Initially, Dual Decoder Attention-based Semantic Segmentation Networks (DDA-SSNets) such as Dual Decoder Attention-UNet (DDA-UNet) and Dual Decoder Attention-SegNet (DDA-SegNet) are proposed to facilitate the dual segmentation tasks such as lung lobes and infection segmentation in chest X-ray (CXR) images. The lung lobe and infection segmentations are mapped to grade the severity of COVID-19 infection in both the lungs of CXRs. Later, a Genetic algorithm-based Deep Convolutional Neural Network classifier with the optimum number of layers, namely GADCNet, is proposed to classify the extracted regions of interest (ROI) from the CXR lung lobes into COVID-19 and non-COVID-19. RESULTS: The DDA-SegNet shows better segmentation with an average BCSSDC of 99.53% and 99.97% for lung lobes and infection segmentations, respectively, compared with DDA-UNet with an average BCSSDC of 99.14% and 99.92%. The proposed DDA-SegNet with GADCNet classifier offered excellent classification results with an average BCCAC of 99.98%, followed by the GADCNet with DDA-UNet with an average BCCAC of 99.92% after extensive testing and analysis. CONCLUSIONS: The results show that the proposed DDA-SegNet has superior performance in the segmentation of lung lobes and COVID-19-infected regions in CXRs, along with improved severity grading compared to the DDA-UNet and improved accuracy of the GADCNet classifier in classifying the CXRs into COVID-19, and non-COVID-19.

Lung ultrasound score severity cut-off points in COVID-19 pneumonia. A systematic review and validating cohort / Puntos de corte de gravedad del Lung Ultrasound Score en la neumonía COVID-19. Revisión sistemática de la literatura y cohorte de validación

Objectives Our purpose was to establish different cut-off points based on the lung ultrasound score (LUS) to classify COVID-19 pneumonia severity. Methods Initially, we conducted a systematic review among previously proposed LUS cut-off points. Then, these results were validated by a single-centre prospective cohort study of adult patients with confirmed SARS-CoV-2 infection. Studied variables were poor outcome (ventilation support, intensive care unit admission or 28-days mortality) and 28-days mortality. Results From 510 articles, 11 articles were included. Among the cut-off points proposed in the articles included, only the LUS>15 cut-off point could be validated for its original endpoint, demonstrating also the strongest relation with poor outcome (odds ratio [OR]=3.636, confidence interval [CI] 1.411–9.374). Regarding our cohort, 127 patients were admitted. In these patients, LUS was statistically associated with poor outcome (OR=1.303, CI 1.137–1.493), and with 28-days mortality (OR=1.024, CI 1.006–1.042). LUS>15 showed the best diagnostic performance when choosing a single cut-off point in our cohort (area under the curve 0.650). LUS≤7 showed high sensitivity to rule out poor outcome (0.89, CI 0.695–0.955), while LUS>20 revealed high specificity to predict poor outcome (0.86, CI 0.776–0.917). Conclusions LUS is a good predictor of poor outcome and 28-days mortality in COVID-19. LUS≤7 cut-off point is associated with mild pneumonia, LUS 8–20 with moderate pneumonia and ≥20 with severe pneumonia. If a single cut-off point were used, LUS>15 would be the point which better discriminates mild from severe disease (AU)

Objetivos Establecer diferentes puntos de corte basados en el Lung Ultrasound Score (LUS) para clasificar la gravedad de la neumonía COVID-19. Métodos Inicialmente, realizamos una revisión sistemática entre los puntos de corte LUS propuestos previamente. Estos resultados fueron validados por una cohorte prospectiva unicéntrica de pacientes adultos con infección confirmada por SARS-CoV-2. Las variables analizadas fueron la mala evolución y la mortalidad a los 28 días. Resultados De 510 artículos, se incluyeron 11. Entre los puntos de corte propuestos en los artículos incluidos, solo LUS>15 pudo ser validado para su objetivo original, demostrando también la relación más fuerte con mala evolución (odds ratio [OR]=3,636, intervalo de confianza [IC] 1,411-9,374). Respecto a nuestra cohorte, se incluyeron 127 pacientes. En estos pacientes, el LUS se asoció estadísticamente con mala evolución (OR=1,303, IC 1,137-1,493) y con mortalidad a los 28 días (OR=1,024, IC 1,006-1,042). LUS>15 mostró el mejor rendimiento diagnóstico al elegir un único punto de corte en nuestra cohorte (área bajo la curva 0,650). LUS≤7 mostró una alta sensibilidad para descartar mal resultado (0,89, IC 0,695-0,955), mientras que LUS>20 reveló gran especificidad para predecir mala evolución (0,86, IC 0,776-0,917). Conclusiones LUS es un buen predictor de mala evolución y mortalidad a 28 días en COVID-19. LUS≤7 se asocia con neumonía leve, LUS 8-20 con neumonía moderada y ≥20 con neumonía grave. Si se utilizara un único punto de corte, LUS>15 sería el que mejor discriminaría la enfermedad leve de la grave (AU)

Tromboembolismo pulmonar durante la pandemia por SARS-CoV-2: características clínicas y radiológicas / Pulmonary embolism during SARS-CoV-2 pandemic: clinical and radiological features

Antecedentes Se ha descrito una elevada incidencia de tromboembolismo pulmonar (TEP) durante la pandemia por coronavirus. Métodos Estudio retrospectivo unicéntrico, con revisión de las angiografías pulmonares por tomografía computarizada solicitadas por sospecha de tromboembolismo pulmonar durante dos períodos, del 01 de marzo del 2020 al 31de mayo del 2020 (pandemia), e igual intervalo en 2019 (control). Resultados Se diagnosticaron 22 tromboembolismos pulmonares durante el período control y 99 en el pandémico, 74 asociados con COVID-19. El 5,3% de los pacientes hospitalizados con COVID-19 sufrió un tromboembolismo pulmonar, con un retraso entre ambos diagnósticos de 9,1 ± 8,4 días. Durante la pandemia, los pacientes con tromboembolismo pulmonar tenían menos condiciones predisponentes (tromboembolismo pulmonar previo 5,1 vs. 18,2%, p = 0,05, cirugía previa 2 vs. 35,4%, p = 0,0001, trombosis venosa profunda 11,1 vs. 45,5%, p = 0,0001), y los tromboembolismos pulmonares periféricos eran más frecuentes (73,5 vs. 50%, p = 0,029). Conclusiones Existe un riesgo incrementado de sufrir un TEP durante la pandemia por SARS-CoV-2, que afecta a pacientes con perfil clínico diferente y causa más frecuentemente TEP distales (AU)

Background A high incidence of pulmonary embolism has been described during the coronavirus pandemic. Methods This work is a single-center retrospective study which reviewed computed tomography pulmonary angiograms ordered due to suspected pulmonary embolism during two periods: from March 1, 2020 to May 31, 2020 (pandemic) and during the same interval in 2019 (control). Results Twenty-two pulmonary embolism were diagnosed during the control period and 99 in the pandemic, 74 of which were associated with COVID-19. Of all patients hospitalized with COVID-19, 5.3% had a pulmonary embolism, with a delay between the two diagnoses of 9.1 ± 8.4 days. During the pandemic, patients with pulmonary embolism had fewer predisposing conditions (previous pulmonary embolism 5.1 vs. 18.2%, p = .05; previous surgery 2 vs. 35.4%, p = .0001; deep vein thrombosis 11.1 vs. 45.5%, p = .0001); peripheral pulmonary embolisms were the most frequent (73.5 vs. 50%, p = . 029). Conclusions There is an increased risk of having a pulmonary embolism during the SARS-CoV-2 pandemic, which affects patients with a different clinical profile and more often causes distal pulmonary embolisms (AU)

Achados clínicos e radiológicos, perfil e evolução de pacientes internados com COVID-19 em uma enfermaria de referência em Salvador - BA / Clinical and radiological findings, profile and evolution of patients hospitalized for COVID-19 in a reference nurse in Salvador - BA

COVID-19 é a doença causada pelo coronavírus SARS-CoV-2. Esta doença foi responsável por uma pandemia no ano de 2020, que resultou em uma grande quantidade de óbitos. Nesse contexto, os exames radiológicos de pacientes com COVID-19 comumente demonstram distribuição bilateral de opacidades em vidro fosco, podendo existir consolidação periférica. Tais achados variam com a idade do paciente, progressão da doença, status da imunidade, comorbidades e intervenção médica inicial. Ademais, existem casos em que a sintomatologia do paciente não condiz com a gravidade das manifestações pulmonares. Objetivo: Analisar o perfil clínico radiológico e evolução de pacientes internados com diagnóstico de COVID-19, em uma enfermaria de um hospital de referência em Salvador-BA. Métodos: Estudo observacional, descritivo e analítico. Os dados foram coletados, por meio de análise de prontuário, acessados pelo computador (banco de dados) do Hospital Geral Ernesto Simões Filho (HGESF). Resultados: Foram coletados dados de um total de 70 pacientes. Destes, 29 (41,4%) participantes do sexo feminino e 41 (58,6%) do sexo masculino com idade variando entre menor que 60 anos (32,9%) e maior ou igual a 60 anos (67,1%), havendo 31 (44,3%) portadores de Diabetes Mellitus. Com relação aos sintomas apresentados, 59 (84,3%) pacientes cursaram com dispneia, 50 (71,4%) manifestaram tosse e 36 (51,4%) tiveram febre. Outros parâmetros clínicos como leucocitose foram evidenciados em 50 (71,4%) participantes, além da dessaturação (<90% spO2) presente em 25 (35,7%) participantes. Durante o internamento, 46 (65,7%) pacientes receberam tratamento com Azitromicina, 60(85,7%) pacientes foram transferidos para Unidade de Terapia Intensiva (UTI), 34 (48,6%) evoluíram com necessidade de intubação orotraqueal (IOT) e 32 (45,7%) foram a óbito. Tais variáveis foram analisadas junto ao percentual de acometimento pulmonar tomográfico que variou entre menor ou igual a 25% em 19 (27,1%) participantes, 26-49% em 19 (27,1%) participantes, 50-74% em 23 (32,9%) participantes e maior ou igual a 75% em 9 (12,9%) participantes. O envolvimento pulmonar foi preditor de óbito e acarretou mudança de conduta quanto ao tempo de internamento. Além disso, a presença de tosse foi constatada como um fator de alerta para o acometimento pulmonar mais grave. Ademais, o uso de azitromicina não predispôs menores percentuais de acometimento pulmonar.

COVID-19 is the disease caused by the coronavirus SARS-CoV-2. This disease was responsible for a pandemic in the year 2020, which resulted in a large number of deaths. In this context, it was noticed that the radiological examinations of patients with COVID-19 commonly demonstrate bilateral distribution of ground glass opacities, with the possibility of peripheral consolidation. Such findings vary with the patient's age, disease progression, immunity status, comorbidities and initial medical intervention. In addition, there are cases in which the patient's symptoms do not match the severity of the pulmonary manifestations. Objective: To analyze the clinical-radiological findings, profile and evolution of patients hospitalized with COVID-19 in a referral ward in Salvador-BA. MethodS: Observational, descriptive and analytical study. Data were collected through medical record analysis, accessed by the computer (database) of the Hospital Geral Ernesto Simões Filho (HGESF). Results: Data were collected from a total of 70 patients. Of these, 29 (41.4%) female participants and 41 (58.6%) male participants, aged between less than 60 years (32.9%) and greater than or equal to 60 years (67.1%), with 31 (44.3%) patients with Diabetes Mellitus. Regarding the symptoms presented, 59 (84.3%) patients had dyspnea, 50 (71.4%) had cough and 36 (51.4%) had fever. Other clinical parameters such as leukocytosis were evidenced in 50 (71.4%) participants, in addition to desaturation (<90% spO2) present in 25 (35.7%) participants. During hospitalization, 46 (65.7%) patients received treatment with Azithromycin, 60 (85.7%) patients were transferred to the intensive care unit (ICU), 34 (48.6%) envolved with the need for cheal intubation and 32 (45.7%) they died. These variables were analyzed along with the percentage of tomographic pulmonary involvement, which ranged from less than or equal to 25% in 19 (27.1%) participants, 26-49% in 19 (27.1%) participants, 50-74% in 23 (32.9%) participants and greater than or equal to 75% in 9 (12.9%) participants. Pulmonary involvement was a predictor of death and led to a change in conduct regarding the length of stay. In addition, the presence of cough was found to be an alert factor for the most severe pulmonary involvement. Furthermore, the use of azithromycin did not predispose lower percentages to pulmonary involvement

Interferon therapy in patients with SARS, MERS, and COVID-19: A systematic review and meta-analysis of clinical studies.

Concern regarding coronavirus (CoV) outbreaks has stayed relevant to global health in the last decades. Emerging COVID-19 infection, caused by the novel SARS-CoV2, is now a pandemic, bringing a substantial burden to human health. Interferon (IFN), combined with other antivirals and various treatments, has been used to treat and prevent MERS-CoV, SARS-CoV, and SARS-CoV2 infections. We aimed to assess the clinical efficacy of IFN-based treatments and combinational therapy with antivirals, corticosteroids, traditional medicine, and other treatments. Major healthcare databases and grey literature were investigated. A three-stage screening was utilized, and included studies were checked against the protocol eligibility criteria. Risk of bias assessment and data extraction were performed, followed by narrative data synthesis. Fifty-five distinct studies of SARS-CoV2, MERS-CoV, and SARS-CoV were spotted. Our narrative synthesis showed a possible benefit in the use of IFN. A good quality cohort showed lower CRP levels in Arbidol (ARB) + IFN group vs. IFN only group. Another study reported a significantly shorter chest X-ray (CXR) resolution in IFN-Alfacon-1 + corticosteroid group compared with the corticosteroid only group in SARS-CoV patients. In a COVID-19 trial, total adverse drug events (ADEs) were much lower in the Favipiravir (FPV) + IFN-α group compared with the LPV/RTV arm (P = 0.001). Also, nausea in patients receiving FPV + IFN-α regimen was significantly lower (P = 0.03). Quantitative analysis of mortality did not show a conclusive effect for IFN/RBV treatment in six moderately heterogeneous MERS-CoV studies (log OR = -0.05, 95% CI: (-0.71,0.62), I2 = 44.71%). A meta-analysis of three COVID-19 studies did not show a conclusive nor meaningful relation between receiving IFN and COVID-19 severity (log OR = -0.44, 95% CI: (-1.13,0.25), I2 = 31.42%). A lack of high-quality cohorts and controlled trials was observed. Evidence suggests the potential efficacy of several combination IFN therapies such as lower ADEs, quicker resolution of CXR, or a decrease in inflammatory cytokines; Still, these options must possibly be further explored before being recommended in public guidelines. For all major CoVs, our results may indicate a lack of a definitive effect of IFN treatment on mortality. We recommend such therapeutics be administered with extreme caution until further investigation uncovers high-quality evidence in favor of IFN or combination therapy with IFN.

Utilidad de la ecografía torácica en infección neonatal por SARS-CoV-2 / Usefulness of chest ultrasound in a neonatal infection due to SARS-CoV-2

No disponible

Neumomediastino masivo en paciente COVID-19 / Massive Pneumomediastinum in a COVID-19 Patient

No disponible