A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis

Wang, Shuo; Zha, Yunfei; Liu, Weimin; Wu, Qingxia; Li, Xiaohu; Niu, Meng; Wang, Meiyun; Qiu, Xiaoming; Li, Hongjun; He, Yu; Gong, Wei; Bai, Yan; Li, Li; Zhu, Yongbei; Wang, Liusu; Tian, Jie

doi:10.1183/13993003.00775-2020

Cited by 428 publications

(260 citation statements)

References 28 publications

(39 reference statements)

Supporting

Mentioning

256

Contrasting

Unclassified

Order By: Relevance

“…CT images were segmented via U-net, then COVNet distinguished between COVID-19 and CAP. Wang [23] proposed a fully automatic deep learning system for COVID-19 diagnosis and prognosis based on CT image analysis. First, they made a DenseNet121-FPN for lung segmentation in chest CT images and the proposed novel COVID-19Net for COVID-19 diagnosis and prognosis.…”

Section: Introductionmentioning

confidence: 99%

The ensemble deep learning model for novel COVID-19 on CT images

Tao

Yang

et al. 2021

Applied Soft Computing

208

118

View full text Add to dashboard Cite

The rapid detection of the novel coronavirus disease, COVID-19, has a positive effect on preventing propagation and enhancing therapeutic outcomes. This article focuses on the rapid detection of COVID-19. We propose an ensemble deep learning model for novel COVID-19 detection from CT images. 2933 lung CT images from COVID-19 patients were obtained from previous publications, authoritative media reports, and public databases. The images were preprocessed to obtain 2500 high-quality images. 2500 CT images of lung tumor and 2500 from normal lung were obtained from a hospital. Transfer learning was used to initialize model parameters and pretrain three deep convolutional neural network models: AlexNet, GoogleNet, and ResNet. These models were used for feature extraction on all images. Softmax was used as the classification algorithm of the fully connected layer. The ensemble classifier EDL-COVID was obtained via relative majority voting. Finally, the ensemble classifier was compared with three component classifiers to evaluate accuracy, sensitivity, specificity, F value, and Matthews correlation coefficient. The results showed that the overall classification performance of the ensemble model was better than that of the component classifier. The evaluation indexes were also higher. This algorithm can better meet the rapid detection requirements of the novel coronavirus disease COVID-19.

show abstract

Section: Introductionmentioning

confidence: 99%

The ensemble deep learning model for novel COVID-19 on CT images

Tao

Yang

et al. 2021

Applied Soft Computing

208

118

View full text Add to dashboard Cite

show abstract

“…The fact that during inference, suspicious or disputable CT slices selected for analysis by the deep model should have been identified by an expert radiologist from the raw CT volume, might be considered as a limitation since a fully automated diagnosis is not possible. That said, as presented in Table I, the proposed methodology outperforms the current literature (19)(20)(21) in terms of AUC performance. In particular, the deep model proposed by Zhang et al (21) demonstrates similar performance with the present analysis but the examined CT slices were manually segmented on lesion basis before classification (COVID-19 versus common pneumonia versus normal patients).…”

Section: Discussionmentioning

confidence: 64%

Advancing Covid‑19 differentiation with a robust preprocessing and integration of multi‑institutional open‑repository computer tomography datasets for deep learning analysis

et al. 2020

View full text Add to dashboard Cite

The coronavirus pandemic and its unprecedented consequences globally has spurred the interest of the artificial intelligence research community. A plethora of published studies have investigated the role of imaging such as chest X-rays and computer tomography in coronavirus disease 2019 (COVID-19) automated diagnosis. Οpen repositories of medical imaging data can play a significant role by promoting cooperation among institutes in a worldwide scale. However, they may induce limitations related to variable data quality and intrinsic differences due to the wide variety of scanner vendors and imaging parameters. In this study, a state-of-the-art custom U-Net model is presented with a dice similarity coefficient performance of 99.6% along with a transfer learning VGG-19 based model for COVID-19 versus pneumonia differentiation exhibiting an area under curve of 96.1%. The above was significantly improved over the baseline model trained with no segmentation in selected tomographic slices of the same dataset. The presented study highlights the importance of a robust preprocessing protocol for image analysis within a heterogeneous imaging dataset and assesses the potential diagnostic value of the presented COVID-19 model by comparing its performance to the state of the art.

show abstract

“…For Hong Kong, Xu et al [ 61 ] showed deep learning yielded better prediction performance for flu-like diseases than the generalized linear model, the least absolute shrinkage and selection operator model, and the autoregressive integrated moving average (ARIMA) model. Wang et al [ 62 ] found deep learning provided a convenient tool for fast screening COVID-19 and finding potential high-risk patients, which may be helpful for medical resource optimization and early prevention before patients show severe COVID-19 symptoms. Various non-China studies indicate that infectious disease can be predicted more effectively when large amounts of data including weather variables and internet big data are used to predict infectious diseases.…”

Section: Resultsmentioning

confidence: 99%

Application of Big Data Technology for COVID-19 Prevention and Control in China: Lessons and Recommendations

Wu¹,

Wang²,

Nicholas³

et al. 2020

J Med Internet Res

123

View full text Add to dashboard Cite

Background In the prevention and control of infectious diseases, previous research on the application of big data technology has mainly focused on the early warning and early monitoring of infectious diseases. Although the application of big data technology for COVID-19 warning and monitoring remain important tasks, prevention of the disease’s rapid spread and reduction of its impact on society are currently the most pressing challenges for the application of big data technology during the COVID-19 pandemic. After the outbreak of COVID-19 in Wuhan, the Chinese government and nongovernmental organizations actively used big data technology to prevent, contain, and control the spread of COVID-19. Objective The aim of this study is to discuss the application of big data technology to prevent, contain, and control COVID-19 in China; draw lessons; and make recommendations. Methods We discuss the data collection methods and key data information that existed in China before the outbreak of COVID-19 and how these data contributed to the prevention and control of COVID-19. Next, we discuss China’s new data collection methods and new information assembled after the outbreak of COVID-19. Based on the data and information collected in China, we analyzed the application of big data technology from the perspectives of data sources, data application logic, data application level, and application results. In addition, we analyzed the issues, challenges, and responses encountered by China in the application of big data technology from four perspectives: data access, data use, data sharing, and data protection. Suggestions for improvements are made for data collection, data circulation, data innovation, and data security to help understand China’s response to the epidemic and to provide lessons for other countries’ prevention and control of COVID-19. Results In the process of the prevention and control of COVID-19 in China, big data technology has played an important role in personal tracking, surveillance and early warning, tracking of the virus’s sources, drug screening, medical treatment, resource allocation, and production recovery. The data used included location and travel data, medical and health data, news media data, government data, online consumption data, data collected by intelligent equipment, and epidemic prevention data. We identified a number of big data problems including low efficiency of data collection, difficulty in guaranteeing data quality, low efficiency of data use, lack of timely data sharing, and data privacy protection issues. To address these problems, we suggest unified data collection standards, innovative use of data, accelerated exchange and circulation of data, and a detailed and rigorous data protection system. Conclusions China has used big data technology to prevent and control COVID-19 in a timely manner. To prevent and control infectious diseases, countries must collect, clean, and integrate data from a wide range of sources; use big data technology to analyze a wide range of big data; create platforms for data analyses and sharing; and address privacy issues in the collection and use of big data.

show abstract

A fully automatic deep learning system for COVID-19 diagnostic and prognostic analysis

Cited by 428 publications

References 28 publications

The ensemble deep learning model for novel COVID-19 on CT images

The ensemble deep learning model for novel COVID-19 on CT images

Advancing Covid‑19 differentiation with a robust preprocessing and integration of multi‑institutional open‑repository computer tomography datasets for deep learning analysis

Application of Big Data Technology for COVID-19 Prevention and Control in China: Lessons and Recommendations

Contact Info

Product

Resources

About