Differentiating pneumonia with and without COVID-19 using chest CT images: from qualitative to quantitative

Diagnostic Performance of Antigen Rapid Diagnostic Tests, Chest Computed Tomography, and Lung Point-of-Care-Ultrasonography for SARS-CoV-2 Compared with RT-PCR Testing: A Systematic Review and Network Meta-Analysis

(1) Background: The comparative performance of various diagnostic methods for severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) infection remains unclear. This study aimed to investigate the comparison of the 3 index test performances of rapid antigen diagnostic tests (RDTs), chest computed tomography (CT), and lung point-of-care-ultrasonography (US) with reverse transcription-polymerase chain reaction (RT-PCR), the reference standard, to provide more evidence-based data on the appropriate use of these index tests. (2) Methods: We retrieved data from electronic literature searches of PubMed, Cochrane Library, and EMBASE from 1 January 2020, to 1 April 2021. Diagnostic performance was examined using bivariate random-effects diagnostic test accuracy (DTA) and Bayesian network meta-analysis (NMA) models. (3) Results: Of the 3992 studies identified in our search, 118 including 69,445 participants met our selection criteria. Among these, 69 RDT, 38 CT, and 15 US studies in the pairwise meta-analysis were included for DTA with NMA. CT and US had high sensitivity of 0.852 (95% credible interval (CrI), 0.791-0.914) and 0.879 (95% CrI, 0.784-0.973), respectively. RDT had high specificity, 0.978 (95% CrI, 0.960-0.996). In accuracy assessment, RDT and CT had a relatively higher than US. However, there was no significant difference in accuracy between the 3 index tests. (4) Conclusions: This meta-analysis suggests that, compared with the reference standard RT-PCR, the 3 index tests (RDTs, chest CT, and lung US) had similar and complementary performances for diagnosis of SARS-CoV-2 infection. To manage and control COVID-19 effectively, future large-scale prospective studies could be used to obtain an optimal timely diagnostic process that identifies the condition of the patient accurately.

Differential diagnosis of COVID-19 at the chest computed tomography scan: A review with special focus on cancer patients

BACKGROUND

Given the several radiological features shared by coronavirus disease 2019 pneumonia and other infective or non-infective diseases with lung involvement, the differential diagnosis is often tricky, and no unequivocal tool exists to help the radiologist in the proper diagnosis. Computed tomography is considered the gold standard in detecting pulmonary illness caused by severe acute respiratory syndrome coronavirus 2.

AIM

To conduct a systematic review including the available studies evaluating computed tomography similarities and discrepancies between coronavirus disease 2019 pneumonia and other pulmonary illness, then providing a discussion focus on cancer patients.

METHODS

Using pertinent keywords, we performed a systematic review using PubMed to select relevant studies published until October 30, 2020.

RESULTS

Of the identified 133 studies, 18 were eligible and included in this review.

CONCLUSION

Ground-glass opacity and consolidations are the most common computed tomography lesions in coronavirus disease 2019 pneumonia and other respiratory diseases. Only two studies included cancer patients, and the differential diagnosis with early lung cancer and radiation pneumonitis was performed. A single lesion associated with pleural effusion and lymphadenopathies in lung cancer and the onset of the lesions in the radiation field in the case of radiation pneumonitis allowed the differential diagnosis. Nevertheless, the studies were heterogeneous, and the type and prevalence of lesions, distributions, morphology, evolution, and additional signs, together with epidemiological, clinical, and laboratory findings, are crucial to help in the differential diagnosis.

Chest computed tomography as a primary tool in COVID-19 detection: an update meta-analysis

PURPOSE

A growing number of publications have paid close attention to the chest computed tomography (CT) detection of COVID-19 with inconsistent diagnostic accuracy, the present meta-analysis assessed the available evidence regarding the overall performance of chest CT for COVID-19.

METHODS

2 × 2 diagnostic table was extracted from each of the included studies. Data on specificity (SPE), sensitivity (SEN), negative likelihood ratio (LR-), positive likelihood ratio (LR+), and diagnostic odds ratio (DOR) were calculated purposefully.

RESULTS

Fifteen COVID-19 related publications met our inclusion criteria and were judged qualified for the meta-analysis. The following were summary estimates for diagnostic parameters of chest CT for COVID-19: SPE, 0.49 (95% CI 46-52%); SEN, 0.94 (95% CI 93-95%); LR-, 0.15 (95% CI 11-20%); LR+, 1.93 (95% CI 145-256%); DOR, 17.14 (95% CI 918-3199%); and the area under the receiver operating characteristic curve (AUC), 0.93.

CONCLUSION

Chest CT has high SEN, but the SPE is not ideal. It is highly recommended to use a combination of different diagnostic tools to achieve sufficient SEN and SPE. It should be taken into account as a diagnostic tool for current COVID-19 detection, especially for patients with symptoms.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s40336-021-00434-z.

Thoracic imaging tests for the diagnosis of COVID-19

BACKGROUND

The respiratory illness caused by SARS-CoV-2 infection continues to present diagnostic challenges. Our 2020 edition of this review showed thoracic (chest) imaging to be sensitive and moderately specific in the diagnosis of coronavirus disease 2019 (COVID-19). In this update, we include new relevant studies, and have removed studies with case-control designs, and those not intended to be diagnostic test accuracy studies.

OBJECTIVES

To evaluate the diagnostic accuracy of thoracic imaging (computed tomography (CT), X-ray and ultrasound) in people with suspected COVID-19.

SEARCH METHODS

We searched the COVID-19 Living Evidence Database from the University of Bern, the Cochrane COVID-19 Study Register, The Stephen B. Thacker CDC Library, and repositories of COVID-19 publications through to 30 September 2020. We did not apply any language restrictions.

SELECTION CRITERIA

We included studies of all designs, except for case-control, that recruited participants of any age group suspected to have COVID-19 and that reported estimates of test accuracy or provided data from which we could compute estimates.

DATA COLLECTION AND ANALYSIS

The review authors independently and in duplicate screened articles, extracted data and assessed risk of bias and applicability concerns using the QUADAS-2 domain-list. We presented the results of estimated sensitivity and specificity using paired forest plots, and we summarised pooled estimates in tables. We used a bivariate meta-analysis model where appropriate. We presented the uncertainty of accuracy estimates using 95% confidence intervals (CIs).

MAIN RESULTS

We included 51 studies with 19,775 participants suspected of having COVID-19, of whom 10,155 (51%) had a final diagnosis of COVID-19. Forty-seven studies evaluated one imaging modality each, and four studies evaluated two imaging modalities each. All studies used RT-PCR as the reference standard for the diagnosis of COVID-19, with 47 studies using only RT-PCR and four studies using a combination of RT-PCR and other criteria (such as clinical signs, imaging tests, positive contacts, and follow-up phone calls) as the reference standard. Studies were conducted in Europe (33), Asia (13), North America (3) and South America (2); including only adults (26), all ages (21), children only (1), adults over 70 years (1), and unclear (2); in inpatients (2), outpatients (32), and setting unclear (17). Risk of bias was high or unclear in thirty-two (63%) studies with respect to participant selection, 40 (78%) studies with respect to reference standard, 30 (59%) studies with respect to index test, and 24 (47%) studies with respect to participant flow. For chest CT (41 studies, 16,133 participants, 8110 (50%) cases), the sensitivity ranged from 56.3% to 100%, and specificity ranged from 25.4% to 97.4%. The pooled sensitivity of chest CT was 87.9% (95% CI 84.6 to 90.6) and the pooled specificity was 80.0% (95% CI 74.9 to 84.3). There was no statistical evidence indicating that reference standard conduct and definition for index test positivity were sources of heterogeneity for CT studies. Nine chest CT studies (2807 participants, 1139 (41%) cases) used the COVID-19 Reporting and Data System (CO-RADS) scoring system, which has five thresholds to define index test positivity. At a CO-RADS threshold of 5 (7 studies), the sensitivity ranged from 41.5% to 77.9% and the pooled sensitivity was 67.0% (95% CI 56.4 to 76.2); the specificity ranged from 83.5% to 96.2%; and the pooled specificity was 91.3% (95% CI 87.6 to 94.0). At a CO-RADS threshold of 4 (7 studies), the sensitivity ranged from 56.3% to 92.9% and the pooled sensitivity was 83.5% (95% CI 74.4 to 89.7); the specificity ranged from 77.2% to 90.4% and the pooled specificity was 83.6% (95% CI 80.5 to 86.4). For chest X-ray (9 studies, 3694 participants, 2111 (57%) cases) the sensitivity ranged from 51.9% to 94.4% and specificity ranged from 40.4% to 88.9%. The pooled sensitivity of chest X-ray was 80.6% (95% CI 69.1 to 88.6) and the pooled specificity was 71.5% (95% CI 59.8 to 80.8). For ultrasound of the lungs (5 studies, 446 participants, 211 (47%) cases) the sensitivity ranged from 68.2% to 96.8% and specificity ranged from 21.3% to 78.9%. The pooled sensitivity of ultrasound was 86.4% (95% CI 72.7 to 93.9) and the pooled specificity was 54.6% (95% CI 35.3 to 72.6). Based on an indirect comparison using all included studies, chest CT had a higher specificity than ultrasound. For indirect comparisons of chest CT and chest X-ray, or chest X-ray and ultrasound, the data did not show differences in specificity or sensitivity.

AUTHORS' CONCLUSIONS

Our findings indicate that chest CT is sensitive and moderately specific for the diagnosis of COVID-19. Chest X-ray is moderately sensitive and moderately specific for the diagnosis of COVID-19. Ultrasound is sensitive but not specific for the diagnosis of COVID-19. Thus, chest CT and ultrasound may have more utility for excluding COVID-19 than for differentiating SARS-CoV-2 infection from other causes of respiratory illness. Future diagnostic accuracy studies should pre-define positive imaging findings, include direct comparisons of the various modalities of interest in the same participant population, and implement improved reporting practices.

RT-PCR Combined with CT Examination in the Diagnosis and Prognosis Evaluation of COVID-19 Patients in Fangcang Hospital: A Case Series

Rationale

Currently, the "gold standard" is real-time reverse transcriptase-polymerase chain reaction (RT-PCR) amplification of the viral DNA for diagnosis of COVID-19 infection. However, early reports of test performance in the Wuhan outbreak showed variable sensitivities. Therefore, the simple use of RT-PCR as a discharge standard for COVID-19 patients may be risky. Early discussions suggested that CT should be the preferred modality for the diagnosis of COVID-19. However, the use of CT for COVID-19 discharge is controversial. In the Fangcang hospital, we performed multiple nucleic acid tests and chest CT examinations in all patients. For discharged patients, we performed multiple nucleic acid tests and chest CT scans on the basis of discharge standards to minimize the incidence of false negatives in nucleic acid tests.

Patient Concerns

Two 42-year-old male patients with mild to moderate COVID-19 were treated in the Fangcang Hospital According to the treatment, one patient was cured and discharged, while the other patient was sent to a higher-level hospital for further treatment.

Diagnoses

Real-time reverse transcriptase-polymerase chain reaction amplification of the viral DNA for diagnosis of COVID-19 infection.

Interventions

The patients received Chinese medicine and antiviral treatment in the Fangcang Hospital.

Outcomes

At follow-up, both patients were cured after treatment and returned to normal life after 2 weeks of home isolation and a negative nucleic acid test.

Lessons

The use of nucleic acid testing combined with chest CT examination can quickly diagnose patients with COVID-19 infection and evaluate their treatment in the Fangcang Hospital.

Computer aid screening of COVID-19 using X-ray and CT scan images: An inner comparison

The objective of this study is to conduct a critical analysis to investigate and compare a group of computer aid screening methods of COVID-19 using chest X-ray images and computed tomography (CT) images. The computer aid screening method includes deep feature extraction, transfer learning, and machine learning image classification approach. The deep feature extraction and transfer learning method considered 13 pre-trained CNN models. The machine learning approach includes three sets of handcrafted features and three classifiers. The pre-trained CNN models include AlexNet, GoogleNet, VGG16, VGG19, Densenet201, Resnet18, Resnet50, Resnet101, Inceptionv3, Inceptionresnetv2, Xception, MobileNetv2 and ShuffleNet. The handcrafted features are GLCM, LBP & HOG, and machine learning based classifiers are KNN, SVM & Naive Bayes. In addition, the different paradigms of classifiers are also analyzed. Overall, the comparative analysis is carried out in 65 classification models, i.e., 13 in deep feature extraction, 13 in transfer learning, and 39 in the machine learning approaches. Finally, all classification models perform better when applying to the chest X-ray image set as comparing to the use of CT scan image set. Among 65 classification models, the VGG19 with SVM achieved the highest accuracy of 99.81%when applying to the chest X-ray images. In conclusion, the findings of this analysis study are beneficial for the researchers who are working towards designing computer aid tools for screening COVID-19 infection diseases.

Using artificial intelligence to assist radiologists in distinguishing COVID-19 from other pulmonary infections

BACKGROUND

Accurate and rapid diagnosis of coronavirus disease (COVID-19) is crucial for timely quarantine and treatment.

PURPOSE

In this study, a deep learning algorithm-based AI model using ResUNet network was developed to evaluate the performance of radiologists with and without AI assistance in distinguishing COVID-19 infected pneumonia patients from other pulmonary infections on CT scans.

METHODS

For model development and validation, a total number of 694 cases with 111,066 CT slides were retrospectively collected as training data and independent test data in the study. Among them, 118 are confirmed COVID-19 infected pneumonia cases and 576 are other pulmonary infection cases (e.g. tuberculosis cases, common pneumonia cases and non-COVID-19 viral pneumonia cases). The cases were divided into training and testing datasets. The independent test was performed by evaluating and comparing the performance of three radiologists with different years of practice experience in distinguishing COVID-19 infected pneumonia cases with and without the AI assistance.

RESULTS

Our final model achieved an overall test accuracy of 0.914 with an area of the receiver operating characteristic (ROC) curve (AUC) of 0.903 in which the sensitivity and specificity are 0.918 and 0.909, respectively. The deep learning-based model then achieved a comparable performance by improving the radiologists' performance in distinguish COVOD-19 from other pulmonary infections, yielding better average accuracy and sensitivity, from 0.941 to 0.951 and from 0.895 to 0.942, respectively, when compared to radiologists without using AI assistance.

CONCLUSION

A deep learning algorithm-based AI model developed in this study successfully improved radiologists' performance in distinguishing COVID-19 from other pulmonary infections using chest CT images.

Relationship of the cycle threshold values of SARS-CoV-2 polymerase chain reaction and total severity score of computerized tomography in patients with COVID 19

AIM

Studies analyzing viral load in COVID-19 patients and any data that compare viral load with chest computerized tomography (CT) severity are limited. This study aimed to evaluate the severity of chest CT in reverse transcriptase polymerase chain reaction (RT-PCR)-positive patients and factors associated with it.

METHODOLOGY

SARS-CoV-2 RNA was extracted from nasopharyngeal swab samples by using Bio-speedy viral nucleic acid buffer. The RT-PCR tests were performed with primers and probes targeting the RdRp gene (Bioexen LTD, Turkey) and results were quantified as cycle threshold (Ct) values. Chest CT of SARS-CoV-2 RNA-positive patients (n = 730) in a period from 22 March to 20 May 2020 were evaluated. The total severity score (TSS) of chest CT ranged 0-20 and was calculated by summing up the degree of acute lung inflammation lesion involvement of each of the five lung lobes.

RESULTS

Of the 284 patients who were hospitalized, 27 (9.5%) of them died. Of 236 (32.3%) patients, there were no findings on CT and 216 (91.5%) of them were outpatients (median age 35 years). TSS was significantly higher in hospitalized patients; 5.3% had severe changes. Ct values were lower among outpatients, indicating higher viral load. An inverse relation between viral load and TSS was detected in both groups. CT severity was related to age, and older patients had higher TSS (p < 0.01).

CONCLUSION

Viral load was not a critical factor for hospitalization and mortality. Outpatients had considerable amounts of virus in their nasopharynx, which made them contagious to their contacts. Viral load is important in detecting early stages of COVID-19, to minimize potential spread, whereas chest CT can help identify cases requiring extensive medical care.

The study of automatic machine learning base on radiomics of non-focus area in the first chest CT of different clinical types of COVID-19 pneumonia

To explore the possibility of predicting the clinical types of Corona-Virus-Disease-2019 (COVID-19) pneumonia by analyzing the non-focus area of the lung in the first chest CT image of patients with COVID-19 by using automatic machine learning (Auto-ML). 136 moderate and 83 severe patients were selected from the patients with COVID-19 pneumonia. The clinical and laboratory data were collected for statistical analysis. The texture features of the Non-focus area of the first chest CT of patients with COVID-19 pneumonia were extracted, and then the classification model of the first chest CT of COVID-19 pneumonia was constructed by using these texture features based on the Auto-ML method of radiomics, The area under curve(AUC), true positive rate(TPR), true negative rate (TNR), positive predictive value(PPV) and negative predictive value (NPV) of the operating characteristic curve (ROC) were used to evaluate the accuracy of the first chest CT image classification model in patients with COVID-19 pneumonia. The TPR, TNR, PPV, NPV and AUC of the training cohort and test cohort of the moderate group and the control group, the severe group and the control group, the moderate group and the severe group were all greater than 95% and 0.95 respectively. The non-focus area of the first CT image of COVID-19 pneumonia has obvious difference in different clinical types. The AUTO-ML classification model of Radiomics based on this difference can be used to predict the clinical types of COVID-19 pneumonia.