Chest CT for detecting COVID-19: a systematic review and meta-analysis of diagnostic accuracy

Xu, Bocheng; Xing, Yangbo; Peng, Jiahao; Zheng, Zhaohai; Tang, Weiliang; Sun, Yong; Xu, Chao; Peng, Fang

doi:10.1007/s00330-020-06934-2

Cited by 201 publications

(197 citation statements)

References 29 publications

(90 reference statements)

Supporting

Mentioning

172

Contrasting

Unclassified

Order By: Relevance

“…What would be desirable is a rapid and phenotypic test on the host that indicates the presence, and if possible the severity, of the consequences of infection. Presently, the standard method for this is based on CT chest scans for pneumonia, which have high sensitivity but lower specificity (see (5)(6)(7) and below), but this is neither cheap nor universally available.…”

Section: Introductionmentioning

confidence: 99%

Prevalence of amyloid blood clots in COVID-19 plasma

Pretorius

Venter

Laubscher

et al. 2020

Preprint

View full text Add to dashboard Cite

The rapid detection of COVID-19 uses genotypic testing for the presence of SARS-Cov-2 virus in nasopharyngeal swabs, but it can have a poor sensitivity. A rapid, host-based physiological test that indicated whether the individual was infected or not would be highly desirable. Coagulaopathies are a common accompaniment to COVID-19, especially micro-clots within the lungs. We show here that microclots can be detected in the native plasma of COVID-19 patient, and in particular that such clots are amyloid in nature as judged by a standard fluorogenic stain. This provides a rapid and convenient test (P<0.0001), and suggests that the early detection and prevention of such clotting could have an important role in therapy.

show abstract

Section: Introductionmentioning

confidence: 99%

Prevalence of amyloid blood clots in COVID-19 plasma

Pretorius

Venter

Laubscher

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…While the sensitivity of SARS‐CoV‐2 PCR is significantly higher for BAL versus nasopharyngeal specimens (~90‐95% versus ~60‐80%), variable resource availability among donor hospitals may limit the safety and feasibility of performing BAL, supporting the high prevalence of nasopharyngeal tests among donors in our study 22,25,26 . While chest computed tomography (CT) is highly sensitive (~97%) for detecting COVID‐19 and may help identify false‐negative nasopharyngeal tests, the specificity of CT is poor (~25%), 22,27 suggesting that routine use of CT in donor screening may result in considerable false positives, and avoidance of otherwise suitable donors. At our institution, ground glass opacities on CT were not considered sufficient to rule‐out donors in the absence of positive SARS‐CoV‐2 PCR and risk factors concerning for recent COVID‐19 exposure or infection.…”

Section: Discussionmentioning

confidence: 65%

Lung transplantation during the COVID-19 pandemic: Safely navigating the new “normal”

Halpern

Olaso

Krischak

et al. 2020

American Journal of Transplantation

View full text Add to dashboard Cite

In the United States, an overall national decline in organ transplants has accompanied the substantial burden of COVID‐19. Amidst significant regional variations in COVID‐19, lung transplantation (LTx) remains a critical life‐saving operation. Our LTx practice during the early pandemic may provide a blueprint for managing LTx in an era of continued community prevalence. Patients who underwent LTx at our institution between March 1 and May 20, 2020 were included. Recipient, operative, and donor characteristics were compared to those from our program in 2019, and COVID‐19 testing practices were evaluated for March, April, and May to understand how our practice adapted to the pandemic. Our program performed 36 LTx, 33% more than the same period in 2019. Recipient, operative, and donor characteristics during COVID‐19 were similar to those in 2019. By April 1, all donors and recipients underwent pretransplant COVID‐19 testing, all returning negative results. To date, no recipients have developed posttransplant COVID‐19. At our institution, pretransplant COVID‐19 testing, use of local donor lungs, and avoidance of donors from areas of increased community penetration supported a safe and effective LTx practice during the early COVID‐19 pandemic. Continued follow‐up is required to ensure the long‐term safety of these newly transplanted patients.

show abstract

“…During these difficult days of the worldwide pandemic, the proposed MULTI-DEEP CAD system has great potential to be used as a tool for COVID-19 detection. It was verified that CT provides a convenient and effective method to primary identify suspicious cases (Xu et al, 2020;Long et al, 2020). Thus, the proposed system can detect COVID-19 cases early, thereby avoiding the fast spread of the disease.…”

Section: Discussionmentioning

confidence: 84%

MULTI-DEEP: A novel CAD system for coronavirus (COVID-19) diagnosis from CT images using multiple convolution neural networks

Attallah¹,

Ragab²,

Sharkas³

2020

PeerJ

View full text Add to dashboard Cite

Coronavirus (COVID-19) was first observed in Wuhan, China, and quickly propagated worldwide. It is considered the supreme crisis of the present era and one of the most crucial hazards threatening worldwide health. Therefore, the early detection of COVID-19 is essential. The common way to detect COVID-19 is the reverse transcription-polymerase chain reaction (RT-PCR) test, although it has several drawbacks. Computed tomography (CT) scans can enable the early detection of suspected patients, however, the overlap between patterns of COVID-19 and other types of pneumonia makes it difficult for radiologists to diagnose COVID-19 accurately. On the other hand, deep learning (DL) techniques and especially the convolutional neural network (CNN) can classify COVID-19 and non-COVID-19 cases. In addition, DL techniques that use CT images can deliver an accurate diagnosis faster than the RT-PCR test, which consequently saves time for disease control and provides an efficient computer-aided diagnosis (CAD) system. The shortage of publicly available datasets of CT images, makes the CAD system’s design a challenging task. The CAD systems in the literature are based on either individual CNN or two-fused CNNs; one used for segmentation and the other for classification and diagnosis. In this article, a novel CAD system is proposed for diagnosing COVID-19 based on the fusion of multiple CNNs. First, an end-to-end classification is performed. Afterward, the deep features are extracted from each network individually and classified using a support vector machine (SVM) classifier. Next, principal component analysis is applied to each deep feature set, extracted from each network. Such feature sets are then used to train an SVM classifier individually. Afterward, a selected number of principal components from each deep feature set are fused and compared with the fusion of the deep features extracted from each CNN. The results show that the proposed system is effective and capable of detecting COVID-19 and distinguishing it from non-COVID-19 cases with an accuracy of 94.7%, AUC of 0.98 (98%), sensitivity 95.6%, and specificity of 93.7%. Moreover, the results show that the system is efficient, as fusing a selected number of principal components has reduced the computational cost of the final model by almost 32%.

show abstract

Chest CT for detecting COVID-19: a systematic review and meta-analysis of diagnostic accuracy

Cited by 201 publications

References 29 publications

Prevalence of amyloid blood clots in COVID-19 plasma

Prevalence of amyloid blood clots in COVID-19 plasma

Lung transplantation during the COVID-19 pandemic: Safely navigating the new “normal”

MULTI-DEEP: A novel CAD system for coronavirus (COVID-19) diagnosis from CT images using multiple convolution neural networks

Contact Info

Product

Resources

About