Accurately Discriminating COVID-19 from Viral and Bacterial Pneumonia According to CT Images Via Deep Learning

Zheng, Fudan; Li, Liang; Zhang, Xiang; Song, Ying; Huang, Ziwang; Chong, Yutian; Chen, Zhiguang; Zhu, Hui‐Ling; Wu, Jiahao; Chen, Weifeng; Lu, Yutong; Yang, Yuedong; Zha, Yunfei; Zhao, Huiying; Shen, Jun

doi:10.1007/s12539-021-00420-z

Cited by 20 publications

(9 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After reading the full text, we kept 32 descriptive studies including 51392 COVID-19 pneumonia patients in this meta-analysis. [1–32] The entire process was shown in Figure 1. All the included studies were retrospective studies.…”

Section: Resultsmentioning

confidence: 99%

Diagnostic performance of corona virus disease 2019 chest computer tomography image recognition based on deep learning: Systematic review and meta-analysis

Wang

Zhang

et al. 2022

Medicine

View full text Add to dashboard Cite

Background: To analyze the diagnosis performance of deep learning model used in corona virus disease 2019 (COVID-19) computer tomography(CT) chest scans. The included sample contains healthy people, confirmed COVID-19 patients and unconfirmed suspected patients with corresponding symptoms. Methods: PubMed, Web of Science, Wiley, China National Knowledge Infrastructure, WAN FANG DATA, and Cochrane Library were searched for articles. Three researchers independently screened the literature, extracted the data. Any differences will be resolved by consulting the third author to ensure that a highly reliable and useful research paper is produced. Data were extracted from the final articles, including: authors, country of study, study type, sample size, participant demographics, type and name of AI software, results (accuracy, sensitivity, specificity, ROC, and predictive values), other outcome(s) if applicable. Results: Among the 3891 searched results, 32 articles describing 51,392 confirmed patients and 7686 non-infected individuals met the inclusion criteria. The pooled sensitivity, the pooled specificity, positive likelihood ratio, negative likelihood ratio and the pooled diagnostic odds ratio (OR) is 0.87(95%CI [confidence interval]: 0.85, 0.89), 0.85(95%CI: 0.82, 0.87), 6.7(95%CI: 5.7, 7.8), 0.14(95%CI: 0.12, 0.16), and 49(95%CI: 38, 65). Further, the AUROC (area under the receiver operating characteristic curve) is 0.94(95%CI: 0.91, 0.96). Secondary outcomes are specific sensitivity and specificity within subgroups defined by different models. Resnet has the best diagnostic performance, which has the highest sensitivity (0.91[95%CI: 0.87, 0.94]), specificity (0.90[95%CI: 0.86, 0.93]) and AUROC (0.96[95%CI: 0.94, 0.97]), according to the AUROC, we can get the rank Resnet > Densenet > VGG > Mobilenet > Inception > Effficient > Alexnet. Conclusions: Our study findings show that deep learning models have immense potential in accurately stratifying COVID-19 patients and in correctly differentiating them from patients with other types of pneumonia and normal patients. Implementation of deep learning-based tools can assist radiologists in correctly and quickly detecting COVID-19 and, consequently, in combating the COVID-19 pandemic.

show abstract

Section: Resultsmentioning

confidence: 99%

Diagnostic performance of corona virus disease 2019 chest computer tomography image recognition based on deep learning: Systematic review and meta-analysis

Wang

Zhang

et al. 2022

Medicine

View full text Add to dashboard Cite

show abstract

“…More so, the algorithm with 85.2% accuracy detected 46 out of 54 COVID-19 images as COVID-19 positive, with the first two nucleic acid test outcomes were negative. Similarly, the work of [ 34 ] obtained CT images of 262 persons for COVID-19, 100 persons for bacterial pneumonia, 219 persons for common viral pneumonia, and 78 persons for healthy control. They combined the newly developed ResNet50 backbone and SE blocks for image analysis to come up with a model that can effectively detect and obtain the indefinite or abstruse differences in CT images.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Novel Crow Swarm Optimization Algorithm and Selection Approach for Optimal Deep Learning COVID-19 Diagnostic Model

Mohammed

Al‐Khateeb

Yousif

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Due to the COVID-19 pandemic, computerized COVID-19 diagnosis studies are proliferating. The diversity of COVID-19 models raises the questions of which COVID-19 diagnostic model should be selected and which decision-makers of healthcare organizations should consider performance criteria. Because of this, a selection scheme is necessary to address all the above issues. This study proposes an integrated method for selecting the optimal deep learning model based on a novel crow swarm optimization algorithm for COVID-19 diagnosis. The crow swarm optimization is employed to find an optimal set of coefficients using a designed fitness function for evaluating the performance of the deep learning models. The crow swarm optimization is modified to obtain a good selected coefficient distribution by considering the best average fitness. We have utilized two datasets: the first dataset includes 746 computed tomography images, 349 of them are of confirmed COVID-19 cases and the other 397 are of healthy individuals, and the second dataset are composed of unimproved computed tomography images of the lung for 632 positive cases of COVID-19 with 15 trained and pretrained deep learning models with nine evaluation metrics are used to evaluate the developed methodology. Among the pretrained CNN and deep models using the first dataset, ResNet50 has an accuracy of 91.46% and a F1-score of 90.49%. For the first dataset, the ResNet50 algorithm is the optimal deep learning model selected as the ideal identification approach for COVID-19 with the closeness overall fitness value of 5715.988 for COVID-19 computed tomography lung images case considered differential advancement. In contrast, the VGG16 algorithm is the optimal deep learning model is selected as the ideal identification approach for COVID-19 with the closeness overall fitness value of 5758.791 for the second dataset. Overall, InceptionV3 had the lowest performance for both datasets. The proposed evaluation methodology is a helpful tool to assist healthcare managers in selecting and evaluating the optimal COVID-19 diagnosis models based on deep learning.

show abstract

“…Numerous applications of Machine Learning (ML) have been utilized in activities such as sanitizing places with drones [6], tracking users using face recognition, drug development, automated robots delivering medicine and food, COVID-19 diagnosis, etc. According to the current literature, ML and hybridised models have been successfully applied in several domains of engineering [7][8][9][10], psychometric analysis [11,12], medical and pharmaceutics [13][14][15], graph theory [16], and social sciences [17][18][19].…”

Section: Introductionmentioning

confidence: 99%

Clinical and Laboratory Approach to Diagnose COVID-19 Using Machine Learning

Chadaga

Chakraborty

Prabhu

et al. 2022

Interdiscip Sci Comput Life Sci

View full text Add to dashboard Cite

Coronavirus 2 (SARS-CoV-2), often known by the name COVID-19, is a type of acute respiratory syndrome that has had a significant influence on both economy and health infrastructure worldwide. This novel virus is diagnosed utilising a conventional method known as the RT-PCR (Reverse Transcription Polymerase Chain Reaction) test. This approach, however, produces a lot of false-negative and erroneous outcomes. According to recent studies, COVID-19 can also be diagnosed using X-rays, CT scans, blood tests and cough sounds. In this article, we use blood tests and machine learning to predict the diagnosis of this deadly virus. We also present an extensive review of various existing machine-learning applications that diagnose COVID-19 from clinical and laboratory markers. Four different classifiers along with a technique called Synthetic Minority Oversampling Technique (SMOTE) were used for classification. Shapley Additive Explanations (SHAP) method was utilized to calculate the gravity of each feature and it was found that eosinophils, monocytes, leukocytes and platelets were the most critical blood parameters that distinguished COVID-19 infection for our dataset. These classifiers can be utilized in conjunction with RT-PCR tests to improve sensitivity and in emergency situations such as a pandemic outbreak that might happen due to new strains of the virus. The positive results indicate the prospective use of an automated framework that could help clinicians and medical personnel diagnose and screen patients. Graphical abstract

show abstract

Accurately Discriminating COVID-19 from Viral and Bacterial Pneumonia According to CT Images Via Deep Learning

Cited by 20 publications

References 31 publications

Diagnostic performance of corona virus disease 2019 chest computer tomography image recognition based on deep learning: Systematic review and meta-analysis

Diagnostic performance of corona virus disease 2019 chest computer tomography image recognition based on deep learning: Systematic review and meta-analysis

Novel Crow Swarm Optimization Algorithm and Selection Approach for Optimal Deep Learning COVID-19 Diagnostic Model

Clinical and Laboratory Approach to Diagnose COVID-19 Using Machine Learning

Contact Info

Product

Resources

About