Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 2.756
Filtrar
1.
J Clin Lab Anal ; 35(2): e23685, 2021 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-33576536

RESUMO

BACKGROUND: Pneumonia caused by the 2019 novel Coronavirus (COVID-2019) shares overlapping signs and symptoms, laboratory findings, imaging features with influenza A pneumonia. We aimed to identify their clinical characteristics to help early diagnosis. METHODS: We retrospectively retrieved data for laboratory-confirmed patients admitted with COVID-19-induced or influenza A-induced pneumonia from electronic medical records in Ningbo First Hospital, China. We recorded patients' epidemiological and clinical features, as well as radiologic and laboratory findings. RESULTS: The median age of influenza A cohort was higher and it exhibited higher temperature and higher proportion of pleural effusion. COVID-19 cohort exhibited higher proportions of fatigue, diarrhea and ground-glass opacity and higher levels of lymphocyte percentage, absolute lymphocyte count, red-cell count, hemoglobin and albumin and presented lower levels of monocytes, c-reactive protein, aspartate aminotransferase, alkaline phosphatase, serum creatinine. Multivariate logistic regression analyses showed that fatigue, ground-glass opacity, and higher level of albumin were independent risk factors for COVID-19 pneumonia, while older age, higher temperature, and higher level of monocyte count were independent risk factors for influenza A pneumonia. CONCLUSIONS: In terms of COVID-19 pneumonia and influenza A pneumonia, fatigue, ground-glass opacity, and higher level of albumin tend to be helpful for diagnosis of COVID-19 pneumonia, while older age, higher temperature, and higher level of monocyte count tend to be helpful for the diagnosis of influenza A pneumonia.


Assuntos
/diagnóstico , Técnicas de Laboratório Clínico , Vírus da Influenza A/fisiologia , Pneumonia/diagnóstico , Pneumonia/virologia , /fisiologia , /diagnóstico por imagem , Diagnóstico Diferencial , Feminino , Humanos , Modelos Logísticos , Masculino , Pessoa de Meia-Idade , Análise Multivariada , Pneumonia/diagnóstico por imagem , Fatores de Risco , Tomografia Computadorizada por Raios X
2.
Medicina (B Aires) ; 81(1): 37-46, 2021.
Artigo em Espanhol | MEDLINE | ID: mdl-33611243

RESUMO

Community-acquired pneumonia (CAP) represents a major health issue and ≈20% of the patients require in-hospital attention. The main objective of the study was to determine clinical-imaging features of CAP episodes requiring hospitalization. The secondary objectives were to determine the diagnostic yield of microbiological analyses and the medical complications. A retrospective analytical study was conducted on adults admitted due to CAP in a third-level hospital in the period 2017-2019. Pregnant women were excluded. A total of 340 CAP episodes were identified in 321 patients; the median age was 75 years old (interquartile range 57-85). The most frequent risk factors were immunocompromise 102 (30%), neurological disease 75 (22%), and chronic kidney disease 58 (17%). According to three prognostic scores, CURB65, qSOFA and PSI/PORT, 216 (63.5%), 290 (83.5%) and 130 (38%) patients were identified as low risk, respectively. A total of 49 (14.4%) episodes required admission at the critical care unit and 39 (11.5%) required mechanical ventilation; 30 patients (8.8%) died during hospitalization. The radiologic patterns most frequently found were consolidation in 134 (39.4%), interstitial-alveolar pattern in 98 (28.8%), and the combination of both patterns in 67 (19.7%) episodes. Identification of the causal agent was achieved in 79 (23.2%) episodes. The most frequently isolated microorganisms were influenza virus in 37 (10.9%) episodes and Streptococcus pneumoniae in 11 (3.2%). Most of the hospitalized CAP patients were elderly with consolidative radiological patterns. The causal agent could be identified in less than a quarter of the patients, with the influenza test being the method with the highest diagnostic yield.


Assuntos
Infecções Comunitárias Adquiridas , Pneumonia Pneumocócica , Pneumonia , Adulto , Idoso , Infecções Comunitárias Adquiridas/diagnóstico , Infecções Comunitárias Adquiridas/epidemiologia , Infecções Comunitárias Adquiridas/terapia , Feminino , Hospitalização , Humanos , Pneumonia/diagnóstico por imagem , Pneumonia/epidemiologia , Gravidez , Estudos Retrospectivos , Streptococcus pneumoniae
3.
J Med Ultrason (2001) ; 48(1): 31-43, 2021 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-33438132

RESUMO

In the coronavirus disease-2019 (COVID-19) era, point-of-care lung ultrasound (LUS) has attracted increased attention. Prospective studies on LUS for the assessment of pneumonia in adult patients were extensively carried out for more than 10 years before this era. None of these prospective studies attempted to differentiate bacterial and viral pneumonia in adult patients using LUS. The majority of studies considered the LUS examination to be positive if sonographic consolidations or multiple B-lines were observed. Significant differences existed in the accuracy of these studies. Some studies revealed that LUS showed superior sensitivity to chest X-ray. These results indicate that point-of-care LUS has the potential to be an initial imaging modality for the diagnosis of pneumonia. The LUS diagnosis of ventilator-associated pneumonia in intensive care units is more challenging in comparison with the diagnosis of community-acquired pneumonia in emergency departments due to the limited access to the mechanically ventilated patients and the high prevalence of atelectasis. However, several studies have demonstrated that the combination of LUS findings with other clinical markers improved the diagnostic accuracy. In the COVID-19 era, many case reports and small observational studies on COVID-19 pneumonia have been published in a short period. Multiple B-lines were the most common and consistent finding in COVID-19 pneumonia. Serial LUS showed the deterioration of the disease. The knowledge and ideas on the application of LUS in the management of pneumonia that are expected to accumulate in the COVID-19 era may provide us with clues regarding more appropriate management.


Assuntos
Pulmão/diagnóstico por imagem , Pneumonia/diagnóstico por imagem , Sistemas Automatizados de Assistência Junto ao Leito , /diagnóstico por imagem , Infecções Comunitárias Adquiridas/diagnóstico por imagem , Humanos , Pneumonia Bacteriana/diagnóstico por imagem , Pneumonia Associada à Ventilação Mecânica/diagnóstico por imagem , Ultrassonografia
4.
Eur J Radiol ; 134: 109442, 2021 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-33321459

RESUMO

PURPOSE: The vascular enlargement (VE) pattern differs from previously described imaging patterns for pneumonia. This study aimed to investigate the incidence, computed tomography (CT) characteristics, and diagnostic value of the VE pattern in coronavirus disease 2019 (COVID-19). METHOD: The CT data of 106 patients with COVID-19 from January 19 to February 29, 2020, and 52 patients with influenza virus pneumonia (IVP) from January 2018 to February 2020 were retrospectively collected. The incidences of the VE pattern between the two groups were compared. The CT manifestations of COVID-19 were analyzed with a particular focus on the VE pattern's specific CT signs, dynamic changes, and relationships with lesion size and disease severity. RESULTS: Peripheral and multilobar ground-glass opacities (GGOs) or mixed GGOs with various sizes and morphologies were typical features of COVID-19 on initial CT. The VE pattern was more common in COVID-19 (88/106, 83.02 %) than in IVP (10/52, 19.23 %) on initial CT (P < 0.001). Three special VE-pattern-specific CT signs, including central vascular sign, ginkgo leaf sign, and comb sign, were identified. Four types of dynamic changes in the VE pattern were observed on initial and follow-up CT, which were closely associated with the evolution of lesions and the time interval from the onset of symptoms to initial CT scan. The VE pattern in COVID-19 was more commonly seen in larger lesions and patients with severe-critical type (all P < 0.001). CONCLUSIONS: The VE pattern is a valuable CT sign for differentiating COVID-19 from IVP, which correlates with more extensive or serious disease. A good understanding of the CT characteristics of the VE pattern may contribute to the early and accurate diagnosis of COVID-19 and prediction of the evolution of lesions.


Assuntos
/diagnóstico por imagem , Pulmão/diagnóstico por imagem , Pneumonia/diagnóstico por imagem , Artéria Pulmonar/patologia , Veias Pulmonares/diagnóstico por imagem , Veias Pulmonares/patologia , Tomografia Computadorizada por Raios X/métodos , Adolescente , Adulto , Idoso , Idoso de 80 Anos ou mais , Criança , Diagnóstico Diferencial , Feminino , Humanos , Influenza Humana/diagnóstico por imagem , Influenza Humana/patologia , Pulmão/irrigação sanguínea , Pulmão/patologia , Masculino , Pessoa de Meia-Idade , Pneumonia/patologia , Artéria Pulmonar/diagnóstico por imagem , Estudos Retrospectivos , Adulto Jovem
5.
Public Health ; 190: 89-92, 2021 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-33373803

RESUMO

OBJECTIVES: The objective of the study is to determine the prevalence of COVID-19 in the context of a secondary pneumonia surveillance program targeted at low-risk patients and to identify clinical characteristics associated with COVID-19. STUDY DESIGN: This study design is a retrospective cohort study. METHODS: This study is conducted in Tan Tock Seng Hospital, a University affiliated 1600-bed public hospital in Singapore. Patients with pneumonia admitted under our Enhanced Pneumonia Surveillance (EPS) program from 7 February 2020 to 20 March 2020 were included. Relevant clinical variables were collated. RESULTS: Of 1295 patients admitted under our EPS program, 47 (3.6%) patients tested positive for COVID-19. The prevalence of a radiologist-reported normal chest X-ray (CXR) in the COVID-19-positive group was 62.8% compared with 6.2% in the COVID-19-negative group. In patients with a normal CXR, a low normal white blood cell (WBC) count and minimal C-reactive protein (CRP) elevation were associated with COVID-19. CONCLUSIONS: The pick-up rate of COVID-19 in low-risk patients with pneumonia is 3.6%. However, at least 7.9% of patients who were isolated had a normal CXR. For patients with pneumonia-like illness at presentation but a normal CXR, higher WBC and CRP values may guide early deisolation. Ultimately, this informs resource allocation for both COVID-19 and non-COVID-19 clinical services.


Assuntos
/diagnóstico por imagem , Pneumonia/diagnóstico por imagem , Radiografia Torácica/métodos , Medição de Risco/métodos , Adulto , Idoso , Idoso de 80 Anos ou mais , /virologia , Feminino , Hospitalização , Hospitais , Humanos , Masculino , Pessoa de Meia-Idade , Pneumonia/epidemiologia , Pneumonia/virologia , Vigilância em Saúde Pública , Estudos Retrospectivos , Singapura/epidemiologia
7.
Medicine (Baltimore) ; 99(50): e23671, 2020 Dec 11.
Artigo em Inglês | MEDLINE | ID: mdl-33327356

RESUMO

BACKGROUND: The aim of this meta-analysis was to evaluate the diagnostic value of lung ultrasound (LUS) in comparison to chest radiography (CXR) in children with pneumonia. METHODS: Computer-based retrieval was performed on PubMed and EMBASE. Quality was evaluated according to the quality assessment of diagnostic accuracy studies-2, and Meta-Disc was adopted to perform meta-analysis. Heterogeneity was assessed using Q and I statistics. The pooled sensitivity, specificity, and diagnostic odds ratio (DOR) with 95% confidence intervals (CIs) as the primary outcomes were calculated for each index test. RESULTS: Twenty two studies with a total of 2470 patients met the inclusion criteria. Our results showed that the pooled sensitivity, specificity, and DOR for children with pneumonia diagnosed by LUS were 0.95 (95% CI: 0.94 to 0.96), 0.90 (95% CI: 0.87 to 0.92), and 137.49 (95% CI: 60.21 to 313.98), respectively. The pooled sensitivity, specificity, and DOR for pediatric pneumonia diagnosed by CXR was 0.91 (95% CI: 0.90 to 0.93), 1.00 (95% CI: 0.99 to 1.00), and 369.66 (95% CI: 137.14 to 996.47), respectively. Four clinical signs, including pulmonary consolidation, positive air bronchogram, abnormal pleural line, and pleural effusion were most frequently observed using LUS in the screening of children with pneumonia. CONCLUSIONS: The available evidence suggests that LUS is a reliable, valuable, and alternative method to CXR for the diagnosis of pediatric pneumonia.


Assuntos
Pneumonia/diagnóstico , Radiografia Torácica/métodos , Ultrassonografia/métodos , Adolescente , Fatores Etários , Broncografia/métodos , Broncografia/normas , Criança , Pré-Escolar , Humanos , Lactente , Pulmão/diagnóstico por imagem , Derrame Pleural/patologia , Pneumonia/diagnóstico por imagem , Pneumonia/patologia , Radiografia Torácica/normas , Sensibilidade e Especificidade , Fatores Sexuais , Ultrassonografia/normas
8.
Sci Rep ; 10(1): 19649, 2020 11 12.
Artigo em Inglês | MEDLINE | ID: mdl-33184424

RESUMO

We examined characteristics of chest CT across different time periods for patients with COVID-19 pneumonia in Huizhou, China. This study included 56 COVID-19 patients with abnormal CT acquired between January 22 and March 3, 2020. The 141 scans of 56 patients were classified into four groups (Groups 1-4) based on dates on which scans were obtained at the 1st, 2nd, 3rd week or longer than three weeks after illness onset. Forty-five patients with follow-up scans were categorized into four groups (Groups A-D) according to extent that lesions reduced (≥ 75%, 50-75%, 25-50% and < 25%). Ground-glass opacities (GGO) was prevalent in Groups 1-4 (58.1-82.6%), while percentages of consolidation ranged between 9.7% in Group 4 and 26.2% in Group 2. The highest frequency of fibrous stripes occurred in Group 3 (46.7%). Total CT scores were on average higher in Groups 2-3. Among 45 follow-up patients, 11 (24.4%) of them recovered with lesions reducing ≥ 75%, with the lowest median age and total CT scores on admission. There are temporal patterns of lung abnormalities in COVID-19 patients, with higher extent of lesion involvement occurring in the 2nd and 3rd week. Persisting lung changes indicate some patients may need isolation after discharge from hospital.


Assuntos
Infecções por Coronavirus/complicações , Pulmão/diagnóstico por imagem , Pneumonia Viral/complicações , Pneumonia/complicações , Pneumonia/diagnóstico por imagem , Tomografia Computadorizada por Raios X , Adulto , Idoso , Infecções por Coronavirus/epidemiologia , Progressão da Doença , Feminino , Seguimentos , Humanos , Pulmão/patologia , Masculino , Pessoa de Meia-Idade , Pandemias , Pneumonia Viral/epidemiologia
9.
Int J Med Sci ; 17(17): 2644-2652, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-33162792

RESUMO

Rationale: The clinical data and corresponding dynamic CT findings were investigated in detail to describe the clinical and imaging profiles of COVID-19 pneumonia disease progression. Methods: Forty HCWs with COVID-19 were included in this study and 30 enrolled for imaging assessment. Disease was divided into four stages based on time from onset: stage 1 (1-6 days), stage 2 (7-13 days), stage 3 (14-22 days), and stage 4 (> 22 days). Clinical wand imaging data were analyzed retrospectively. Results: The cohort included 33 female and 7 male cases, with a median age of 40 years. Six had underlying comorbidities. More than half of the cases were nurses (22, 55%). Each stage included 39, 37, 34 and 32 CTs, respectively. Bilateral lesions, multifocal lesions and lesions with GGO pattern occurred in both lower lobes at all stages. The crazy-paving pattern (20, 54%), air bronchogram (13, 35%), and pleural effusion (2, 5%) were the most common CT features in stage 2. Consolidation score peaked in stage 2 whereas total lesions score peaked in stage 3. Conclusions: COVID-19 pneumonia in HCWs has a potential predilection for younger female workers. Stage 2 of COVID-19 pneumonia may be the key period for controlling progression of the disease, and consolidation scores may be an objective reflection of the severity of lung involvement.


Assuntos
Infecções por Coronavirus/diagnóstico por imagem , Pulmão/fisiopatologia , Pneumonia Viral/diagnóstico por imagem , Pneumonia/diagnóstico por imagem , Tórax/diagnóstico por imagem , Adulto , Betacoronavirus/patogenicidade , Infecções por Coronavirus/fisiopatologia , Infecções por Coronavirus/virologia , Progressão da Doença , Feminino , Pessoal de Saúde , Humanos , Pulmão/diagnóstico por imagem , Masculino , Pessoa de Meia-Idade , Pandemias , Pneumonia/fisiopatologia , Pneumonia/virologia , Pneumonia Viral/fisiopatologia , Pneumonia Viral/virologia , Estudos Retrospectivos , Tórax/fisiopatologia , Tórax/virologia , Tomografia Computadorizada por Raios X , Adulto Jovem
10.
Int J Med Sci ; 17(17): 2653-2662, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-33162793

RESUMO

Background and aim: To perform a longitudinal analysis of serial CT findings over time in patients with COVID-19 pneumonia. Methods: From February 5 to March 8, 2020, 73 patients (male to female, ratio of 43:30; mean age, 51 years) with COVID-19 pneumonia were retrospectively enrolled and followed up until discharge from three institutions in China. The patients were divided into the severe and non-severe groups according to treatment option. The patterns and distribution of lung abnormalities, total CT scores, single ground-glass opacity (GGO) CT scores, single consolidation CT scores, single reticular CT scores and the amounts of zones involved were reviewed by 2 radiologists. These features were analyzed for temporal changes. Results: In non-severe group, total CT scores (median, 9.5) and the amounts of zones involved were slowly increased and peaked in disease week 2. In the severe group, the increase was faster, with scores also peaking at 2 weeks (median, 20). In both groups, the later parameters began to decrease in week 4 (median values of 9 and 19 in the non-severe and severe groups, respectively). In the severe group, the dominant residual lung lesions were reticular (median single reticular CT score, 10) and consolidation (median single consolidation CT score, 7). In the non-severe group, the dominant residual lung lesions were GGO (median single GGO CT score, 7) and reticular (median single reticular CT score, 4). In both non-severe and severe groups, the GGO pattern was dominant in week 1, with a higher proportion in the severe group compared with the non-severe group (72% vs. 65%). The consolidation pattern peaked in week 2, with 9 (32%) and 19 (73%) in the non-severe and severe groups, respectively; the reticular pattern became dominant from week 4 (both group >40%). Conclusion: The extent of CT abnormalities in the severe and non-severe groups peaked in disease week 2. The temporal changes of CT manifestations followed a specific pattern, which might indicate disease progression and recovery.


Assuntos
Infecções por Coronavirus/diagnóstico por imagem , Pulmão/diagnóstico por imagem , Pandemias , Pneumonia Viral/diagnóstico por imagem , Pneumonia/diagnóstico por imagem , Adulto , Idoso , Idoso de 80 Anos ou mais , Betacoronavirus/patogenicidade , China , Infecções por Coronavirus/fisiopatologia , Infecções por Coronavirus/virologia , Progressão da Doença , Feminino , Humanos , Estudos Longitudinais , Pulmão/fisiopatologia , Pulmão/virologia , Masculino , Pessoa de Meia-Idade , Pneumonia/fisiopatologia , Pneumonia/virologia , Pneumonia Viral/fisiopatologia , Pneumonia Viral/virologia , Tomografia Computadorizada por Raios X
11.
Sci Rep ; 10(1): 19196, 2020 11 05.
Artigo em Inglês | MEDLINE | ID: mdl-33154542

RESUMO

Computed tomography (CT) is the preferred imaging method for diagnosing 2019 novel coronavirus (COVID19) pneumonia. We aimed to construct a system based on deep learning for detecting COVID-19 pneumonia on high resolution CT. For model development and validation, 46,096 anonymous images from 106 admitted patients, including 51 patients of laboratory confirmed COVID-19 pneumonia and 55 control patients of other diseases in Renmin Hospital of Wuhan University were retrospectively collected. Twenty-seven prospective consecutive patients in Renmin Hospital of Wuhan University were collected to evaluate the efficiency of radiologists against 2019-CoV pneumonia with that of the model. An external test was conducted in Qianjiang Central Hospital to estimate the system's robustness. The model achieved a per-patient accuracy of 95.24% and a per-image accuracy of 98.85% in internal retrospective dataset. For 27 internal prospective patients, the system achieved a comparable performance to that of expert radiologist. In external dataset, it achieved an accuracy of 96%. With the assistance of the model, the reading time of radiologists was greatly decreased by 65%. The deep learning model showed a comparable performance with expert radiologist, and greatly improved the efficiency of radiologists in clinical practice.


Assuntos
Infecções por Coronavirus/complicações , Aprendizado Profundo , Processamento de Imagem Assistida por Computador/métodos , Pneumonia Viral/complicações , Pneumonia/complicações , Pneumonia/diagnóstico por imagem , Razão Sinal-Ruído , Tomografia Computadorizada por Raios X , Adulto , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Pandemias , Estudos Retrospectivos
12.
In Vivo ; 34(6): 3735-3746, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-33144492

RESUMO

BACKGROUND/AIM: This study investigated the correlation of chest computed tomography (CT), findings, graded using two different scoring methods, with clinical and laboratory features and disease outcome, including a novel clinical predictive score, in patients with novel coronavirus-infected pneumonia (NCIP). PATIENTS AND METHODS: In this retrospective, observational study, CT scan of 92 NCIP patients admitted to Policlinico Tor Vergata, were analyzed using a quantitative, computed-based and a semiquantitative, radiologist-assessed scoring system. Correlations of the two radiological scores with clinical and laboratory features, the CALL score, and their association with a composite adverse outcome were assessed. RESULTS: The two scores correlated significantly with each other (ρ=0.637, p<0.0001) and were independently associated with age, LDH, estimated glomerular filtration rate, diabetes, and with the composite outcome, which occurred in 24 patients. CONCLUSION: In NCIP patients, two different radiological scores correlated with each other and with several clinical, laboratory features, and the CALL score. The quantitative score was a better independent predictor of the composite adverse outcome than the semiquantitative score.


Assuntos
Infecções por Coronavirus/diagnóstico por imagem , Pneumonia Viral/diagnóstico por imagem , Pneumonia/diagnóstico por imagem , Tórax/diagnóstico por imagem , Idoso , Idoso de 80 Anos ou mais , Betacoronavirus/patogenicidade , Infecções por Coronavirus/mortalidade , Infecções por Coronavirus/fisiopatologia , Infecções por Coronavirus/terapia , Infecções por Coronavirus/virologia , Feminino , Hospitalização , Humanos , Unidades de Terapia Intensiva , Masculino , Pessoa de Meia-Idade , Pandemias , Pneumonia/mortalidade , Pneumonia/fisiopatologia , Pneumonia/virologia , Pneumonia Viral/fisiopatologia , Pneumonia Viral/terapia , Pneumonia Viral/virologia , Tórax/fisiopatologia , Tórax/virologia , Tomografia Computadorizada por Raios X
13.
Nat Commun ; 11(1): 5088, 2020 10 09.
Artigo em Inglês | MEDLINE | ID: mdl-33037212

RESUMO

Early detection of COVID-19 based on chest CT enables timely treatment of patients and helps control the spread of the disease. We proposed an artificial intelligence (AI) system for rapid COVID-19 detection and performed extensive statistical analysis of CTs of COVID-19 based on the AI system. We developed and evaluated our system on a large dataset with more than 10 thousand CT volumes from COVID-19, influenza-A/B, non-viral community acquired pneumonia (CAP) and non-pneumonia subjects. In such a difficult multi-class diagnosis task, our deep convolutional neural network-based system is able to achieve an area under the receiver operating characteristic curve (AUC) of 97.81% for multi-way classification on test cohort of 3,199 scans, AUC of 92.99% and 93.25% on two publicly available datasets, CC-CCII and MosMedData respectively. In a reader study involving five radiologists, the AI system outperforms all of radiologists in more challenging tasks at a speed of two orders of magnitude above them. Diagnosis performance of chest x-ray (CXR) is compared to that of CT. Detailed interpretation of deep network is also performed to relate system outputs with CT presentations. The code is available at https://github.com/ChenWWWeixiang/diagnosis_covid19 .


Assuntos
Inteligência Artificial , Infecções por Coronavirus/diagnóstico por imagem , Pneumonia Viral/diagnóstico por imagem , Adulto , Idoso , Idoso de 80 Anos ou mais , Betacoronavirus , Aprendizado Profundo , Diagnóstico Diferencial , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Pandemias , Pneumonia/diagnóstico por imagem , Curva ROC , Tomografia Computadorizada por Raios X , Adulto Jovem
14.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 2186-2189, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018440

RESUMO

Chest radiography has become the modality of choice for diagnosing pneumonia. However, analyzing chest X-ray images may be tedious, time-consuming and requiring expert knowledge that might not be available in less-developed regions. therefore, computer-aided diagnosis systems are needed. Recently, many classification systems based on deep learning have been proposed. Despite their success, the high development cost for deep networks is still a hurdle for deployment. Deep transfer learning (or simply transfer learning) has the merit of reducing the development cost by borrowing architectures from trained models followed by slight fine-tuning of some layers. Nevertheless, whether deep transfer learning is effective over training from scratch in the medical setting remains a research question for many applications. In this work, we investigate the use of deep transfer learning to classify pneumonia among chest X-ray images. Experimental results demonstrated that, with slight fine-tuning, deep transfer learning brings performance advantage over training from scratch. Three models, ResNet-50, Inception V3 and DensetNet121, were trained separately through transfer learning and from scratch. The former can achieve a 4.1% to 52.5% larger area under the curve (AUC) than those obtained by the latter, suggesting the effectiveness of deep transfer learning for classifying pneumonia in chest X-ray images.


Assuntos
Aprendizado Profundo , Pneumonia , Diagnóstico por Computador , Humanos , Pneumonia/diagnóstico por imagem , Radiografia , Raios X
15.
Comput Math Methods Med ; 2020: 9756518, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-33014121

RESUMO

The COVID-19 diagnostic approach is mainly divided into two broad categories, a laboratory-based and chest radiography approach. The last few months have witnessed a rapid increase in the number of studies use artificial intelligence (AI) techniques to diagnose COVID-19 with chest computed tomography (CT). In this study, we review the diagnosis of COVID-19 by using chest CT toward AI. We searched ArXiv, MedRxiv, and Google Scholar using the terms "deep learning", "neural networks", "COVID-19", and "chest CT". At the time of writing (August 24, 2020), there have been nearly 100 studies and 30 studies among them were selected for this review. We categorized the studies based on the classification tasks: COVID-19/normal, COVID-19/non-COVID-19, COVID-19/non-COVID-19 pneumonia, and severity. The sensitivity, specificity, precision, accuracy, area under the curve, and F1 score results were reported as high as 100%, 100%, 99.62, 99.87%, 100%, and 99.5%, respectively. However, the presented results should be carefully compared due to the different degrees of difficulty of different classification tasks.


Assuntos
Betacoronavirus , Técnicas de Laboratório Clínico , Infecções por Coronavirus/diagnóstico por imagem , Pandemias , Pneumonia Viral/diagnóstico por imagem , Interpretação de Imagem Radiográfica Assistida por Computador/métodos , Tomografia Computadorizada por Raios X/estatística & dados numéricos , Inteligência Artificial , Infecções por Coronavirus/diagnóstico , Infecções por Coronavirus/epidemiologia , Aprendizado Profundo , Humanos , Redes Neurais de Computação , Pneumonia/classificação , Pneumonia/diagnóstico por imagem , Pneumonia Viral/epidemiologia , Interpretação de Imagem Radiográfica Assistida por Computador/estatística & dados numéricos , Radiografia Torácica/estatística & dados numéricos , Sensibilidade e Especificidade
16.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 1238-1241, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018211

RESUMO

Pneumonia is one of the leading causes of childhood mortality worldwide. Chest x-ray (CXR) can aid the diagnosis of pneumonia, but in the case of low contrast images, it is important to include computational tools to aid specialists. Deep learning is an alternative because it can identify patterns automatically, even in low-resolution images. We propose herein a convolutional neural network (CNN) architecture with different training strategies towards detecting pneumonia on CXRs and distinguishing its subforms of bacteria and virus. We also evaluated different image pre-processing methods to improve the classification. This study used CXRs from pediatric patients from a public pneumonia CXR dataset. The pre-processing methods evaluated were image cropping and histogram equalization. To classify the images, we adopted the VGG16 CNN and replaced its fully-connected layers with a customized multilayer perceptron. With this architecture, we proposed and evaluated four different training strategies: original CXR image (baseline), chest-cavity-cropped image (A), and histogram-equalized segmented image (B). The last strategy method (C) implemented is based on ensemble between strategies A and B. The performance was assessed by the area under the ROC curve (AUC) with 95% confidence interval (CI), accuracy, sensitivity, specificity, and F1-score. The ensemble model C yielded the highest performances: AUC of 0.97 (CI: 0.96-0.99) to classify pneumonia vs. normal, and AUC of 0.91 (CI: 0.88-0.94) to classify bacterial vs. viral cases. All models that used pre-processed images showed higher AUC than baseline, which used the original CXR image. Image cropping and histogram equalization reduced irrelevant information from the exam, enhanced contrast, and was able to identify fine CXR texture details. The proposed ensemble model increased the representation of inflammatory patterns from bacteria and viruses with few epochs to train the deep CNNs.Clinical relevance- Deep learning can identify complex radiographic patterns in low contrast images due to pneumonia and distinguish its subforms of bacteria and virus. The correlation of imaging with lab results could accelerate the adoption of complementary exams to confirm the disease's cause.


Assuntos
Aprendizado Profundo , Pneumonia , Criança , Humanos , Redes Neurais de Computação , Pneumonia/diagnóstico por imagem , Tórax , Raios X
17.
Trials ; 21(1): 875, 2020 Oct 22.
Artigo em Inglês | MEDLINE | ID: mdl-33092632

RESUMO

OBJECTIVES: The primary objective is to demonstrate that COVID-19 convalescent plasma (CCP) prevents progression to severe pneumonia in elderly COVID-19 pneumonia patients with chronic comorbidities. Secondary objectives are to demonstrate that CCP decreases the viral load in nasopharyngeal swabs and increases the anti-SARS-CoV-2 antibody titre in recipients. TRIAL DESIGN: This is a randomized, open-label, parallel group, phase II/III study with a superiority framework. The trial starts with a screening phase II designed with two-tailed alpha=0.2. In case of positive results, the trial will proceed in a formally comparative phase III (alpha=0.05). PARTICIPANTS: Adult patients with confirmed or suspected COVID-19 who are at risk according to CDC definition are eligible. Inclusion criteria are all the following: age ≥ 65; pneumonia at CT scan; PaO2/FiO2 ≥300 mmHg; presence of one or more comorbidities; signed informed consent. Exclusion criteria are one of the following: age < 65; PaO2/FiO2 < 300 mmHg; pending cardiopulmonary arrest; refusal to blood product transfusions; severe IgA deficiency; any life-threatening comorbidity or any other medical condition which, in the opinion of the investigator, makes the patient unsuitable for inclusion. The trial is being conducted at three reference COVID-19 centres in the middle of Italy. INTERVENTION AND COMPARATOR: Intervention: COVID-19 Convalescent Plasma (CCP) in addition to standard therapy. Patients receive three doses (200 ml/day on 3 consecutive days) of ABO matched CCP. Comparator: Standard therapy MAIN OUTCOMES: A. Primary outcome for Phase II: Proportion of patients without progression in severity of pulmonary disease, defined as worsening of 2 points in the ordinal scale of WHO by day 14. B. Primary outcome for Phase III: Proportion of patients without progression in severity of pulmonary disease, defined as worsening of 2 points in the ordinal scale of WHO by day 14. Secondary outcomes for Phase III: Decreased viral load on nasopharyngeal swab at days 6, 9 and 14; Decreased viremia at days 6 and 9; Increased antibody titer against SARS-CoV2 at days 30 and 60; Proportion of patients with negative of SARS-CoV2 nasopharyngeal swab at day 30; Length of hospital stay; Mortality rate at day 28; Total plasma related adverse event (day 60); Total non-plasma related adverse events (day 60); Severe adverse events (SAE) (day 60). RANDOMISATION: Treatment allocation is randomized with a ratio 1:1 in both phase II and phase III. Randomization sequences will be generated at Fondazione Policlinico Gemelli IRCCS through the RedCap web application. Randomized stratification is performed according to age (under/over 80 years), and sex. BLINDING (MASKING): None, this is an open-label trial. NUMBERS TO BE RANDOMISED (SAMPLE SIZE): Phase II: 114 patients (57 per arm). Phase III: 182 patients (91 per arm) TRIAL STATUS: The trial recruitment started on May 27, 2020. The anticipated date of recruitment completion is April 30, 2021. The protocol version is 2 (May 10, 2020). TRIAL REGISTRATION: The trial has been registered on ClinicalTrials.gov (May 5, 2020). The Identifier number is NCT04374526 FULL PROTOCOL: The full protocol is attached as an additional file, accessible from the Trials website (Additional file 1). In the interest in expediting dissemination of this material, the familiar formatting has been eliminated; this Letter serves as a summary of the key elements of the full protocol.


Assuntos
Betacoronavirus/genética , Transfusão de Sangue/métodos , Infecções por Coronavirus/terapia , Pneumonia Viral/terapia , Idoso , Idoso de 80 Anos ou mais , Betacoronavirus/imunologia , Comorbidade , Infecções por Coronavirus/epidemiologia , Infecções por Coronavirus/virologia , Progressão da Doença , Feminino , Humanos , Imunização Passiva/efeitos adversos , Imunização Passiva/métodos , Consentimento Livre e Esclarecido/ética , Itália/epidemiologia , Masculino , Mortalidade/tendências , Pandemias , Pneumonia/diagnóstico por imagem , Pneumonia/prevenção & controle , Pneumonia Viral/epidemiologia , Pneumonia Viral/virologia , Tomografia Computadorizada por Raios X/métodos , Carga Viral/imunologia , Carga Viral/estatística & dados numéricos
18.
Interdiscip Sci ; 12(4): 555-565, 2020 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-32959234

RESUMO

The novel coronavirus severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a major pandemic outbreak recently. Various diagnostic technologies have been under active development. The novel coronavirus disease (COVID-19) may induce pulmonary failures, and chest X-ray imaging becomes one of the major confirmed diagnostic technologies. The very limited number of publicly available samples has rendered the training of the deep neural networks unstable and inaccurate. This study proposed a two-step transfer learning pipeline and a deep residual network framework COVID19XrayNet for the COVID-19 detection problem based on chest X-ray images. COVID19XrayNet firstly tunes the transferred model on a large dataset of chest X-ray images, which is further tuned using a small dataset of annotated chest X-ray images. The final model achieved 0.9108 accuracy. The experimental data also suggested that the model may be improved with more training samples being released. COVID19XrayNet, a two-step transfer learning framework designed for biomedical images.


Assuntos
Técnicas de Laboratório Clínico/métodos , Infecções por Coronavirus/diagnóstico , Aprendizado Profundo , Pulmão/diagnóstico por imagem , Modelos Biológicos , Redes Neurais de Computação , Pneumonia Viral/diagnóstico , Raios X , Algoritmos , Betacoronavirus , Coronavirus , Infecções por Coronavirus/complicações , Infecções por Coronavirus/diagnóstico por imagem , Infecções por Coronavirus/virologia , Bases de Dados Factuais , Conjuntos de Dados como Assunto , Humanos , Aprendizado de Máquina , Pandemias , Pneumonia/diagnóstico , Pneumonia/diagnóstico por imagem , Pneumonia/etiologia , Pneumonia/virologia , Pneumonia Viral/complicações , Pneumonia Viral/diagnóstico por imagem , Pneumonia Viral/virologia , Radiografia/métodos , Valores de Referência , Tomografia Computadorizada por Raios X/métodos
19.
J Xray Sci Technol ; 28(5): 821-839, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32773400

RESUMO

BACKGROUND: The novel coronavirus disease 2019 (COVID-19) constitutes a public health emergency globally. The number of infected people and deaths are proliferating every day, which is putting tremendous pressure on our social and healthcare system. Rapid detection of COVID-19 cases is a significant step to fight against this virus as well as release pressure off the healthcare system. OBJECTIVE: One of the critical factors behind the rapid spread of COVID-19 pandemic is a lengthy clinical testing time. The imaging tool, such as Chest X-ray (CXR), can speed up the identification process. Therefore, our objective is to develop an automated CAD system for the detection of COVID-19 samples from healthy and pneumonia cases using CXR images. METHODS: Due to the scarcity of the COVID-19 benchmark dataset, we have employed deep transfer learning techniques, where we examined 15 different pre-trained CNN models to find the most suitable one for this task. RESULTS: A total of 860 images (260 COVID-19 cases, 300 healthy and 300 pneumonia cases) have been employed to investigate the performance of the proposed algorithm, where 70% images of each class are accepted for training, 15% is used for validation, and rest is for testing. It is observed that the VGG19 obtains the highest classification accuracy of 89.3% with an average precision, recall, and F1 score of 0.90, 0.89, 0.90, respectively. CONCLUSION: This study demonstrates the effectiveness of deep transfer learning techniques for the identification of COVID-19 cases using CXR images.


Assuntos
Infecções por Coronavirus/diagnóstico por imagem , Aprendizado Profundo , Pneumonia Viral/diagnóstico por imagem , Tomografia Computadorizada por Raios X/métodos , Algoritmos , Betacoronavirus , Bases de Dados Factuais , Diagnóstico Diferencial , Humanos , Redes Neurais de Computação , Pandemias , Pneumonia/diagnóstico por imagem , Radiografia Torácica , Reprodutibilidade dos Testes
20.
J Comput Assist Tomogr ; 44(5): 652-655, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-32842069

RESUMO

Immune checkpoint inhibitor therapy has revolutionized the treatment of many different types of cancer. However, despite dramatic improvements in tumor oncologic response and patient outcomes, immune checkpoint blockade has been associated with multiple distinctive side-effects termed immune-related adverse events. These often have important clinical implications because these can vary in severity, sometimes even resulting in death. Therefore, it is important for both radiologists and clinicians to recognize and be aware of these reactions to help appropriately guide patient management. This article specifically highlights imaging manifestations of the most common cardiothoracic toxicities of these agents, including pneumonitis, sarcoid-like granulomatosis and lymphadenopathy, and myocarditis.


Assuntos
Antineoplásicos Imunológicos/efeitos adversos , Pneumonia , Sarcoidose , Idoso , Idoso de 80 Anos ou mais , Antineoplásicos Imunológicos/uso terapêutico , Humanos , Pulmão/diagnóstico por imagem , Pulmão/patologia , Masculino , Pessoa de Meia-Idade , Neoplasias/tratamento farmacológico , Pneumonia/induzido quimicamente , Pneumonia/diagnóstico por imagem , Pneumonia/patologia , Sarcoidose/induzido quimicamente , Sarcoidose/diagnóstico por imagem , Sarcoidose/patologia , Tomografia Computadorizada por Raios X
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA