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; Li, Li; Zhu, Yongbei; Wang, Liusu; Hui, Hui

doi:10.1101/2020.03.24.20042317

Cited by 108 publications

(123 citation statements)

References 19 publications

Supporting

Mentioning

122

Contrasting

Unclassified

Order By: Relevance

“…The studies using small dataset (e.g., <300 patients) often showed high AUC or accuracy. However, in several studies with larger dataset (> 1000 patients) [13,83], the performance drops. Consequently, the very high accuracy of AI models in small dataset may be caused by overfitting.…”

Section: Discussionmentioning

confidence: 99%

“…Due to the limited training data of COVID-19, transfer learning using chest CT images should be a good strategy. In [83], the CNN model was first trained using lung cancer dataset including 4106 patients, and finally achieved good performance in diagnosing COVID-19. Many transfer learning models in current studies used ResNet that was pre-trained in ImageNet dataset.…”

Section: Discussionmentioning

confidence: 99%

“…In the five-fold validation, the method achieved sensitivity of 0.907, specificity of 0.833, and accuracy of 0.879. In another study, Wang et al [83] proposed a fully automatic deep-learning system for COVID-19 classification and prognostic analysis. In their study, an FPN network [89] with a DenseNet121 [90] backbone was used to segment lung areas automatically.…”

Section: Ai-based Image Analysis For Covid-19mentioning

confidence: 99%

See 2 more Smart Citations

The Role of Imaging in the Detection and Management of COVID-19: A Review

Dong

Tang

Wang

et al. 2021

IEEE Rev. Biomed. Eng.

Self Cite

342

247

View full text Add to dashboard Cite

Coronavirus disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is spreading rapidly around the world, resulting in a massive death toll. Lung infection or pneumonia is the common complication of COVID-19, and imaging techniques, especially computed tomography (CT), have played an important role in diagnoses and treatment assessment of the disease. Herein, we review the use of imaging characteristics and computing models that have been applied for the management of COVID-19. CT, positron emission tomography -CT (PET/CT), lung ultrasound, and magnetic resonance imaging (MRI) have been used for detection, treatment, and follow-up. The quantitative analysis of imaging data using artificial intelligence (AI) is also explored. Our findings indicate that typical imaging characteristics and their changes can play an important role in the detection and management of COVID-19. In addition, AI or other quantitative image analysis methods are urgently needed to maximize the value of imaging in the management of COVID-19.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Ai-based Image Analysis For Covid-19mentioning

confidence: 99%

See 1 more Smart Citation

The Role of Imaging in the Detection and Management of COVID-19: A Review

Dong

Tang

Wang

et al. 2021

IEEE Rev. Biomed. Eng.

Self Cite

342

247

View full text Add to dashboard Cite

show abstract

“…Nonetheless, performing CT scans as a screening method presents significant limitations, both considering the risk of radiation exposure and operator or machine-type dependence. [20] Aside from these studies, many Authors propose COVID-19 AI-powered diagnostic tools not based on CT scans data. Feng et al [17] developed and validated a diagnosis aid model without CT images for early identification of suspected COVID-19 pneumonia on admission in adult fever patients and made the validated model available via an online triage calculator that needs clinical and serological data (e.g.…”

Section: Diagnosismentioning

confidence: 99%

How the COVID-19 pandemic is favoring the adoption of digital technologies in healthcare: a rapid literature review

Golinelli

Boetto

Carullo

et al. 2020

Preprint

View full text Add to dashboard Cite

Background.Healthcare is responding to the COVID-19 pandemic through the fast adoption of digital solutions and advanced technology tools. The aim of this study is to describe which digital solutions have been reported in the scientific literature and to investigate their potential impact in the fight against the COVID-19 pandemic. Methods. We conducted a literature review searching PubMed and MedrXiv with terms considered adequate to find relevant literature on the use of digital technologies in response to COVID-19. We developed an impact score to evaluate the potential impact on COVID-19 pandemic of all the digital solutions addressed in the selected papers. Results. The search identified 269 articles, of which 145 full-text articles were assessed and 124 included in the review after screening and impact evaluation. Of selected articles, most of them addressed the use of digital technologies for diagnosis, surveillance and prevention. We report that digital solutions and innovative technologies have mainly been proposed for the diagnosis of COVID-19. In particular, within the reviewed articles we identified numerous suggestions on the use of artificial-intelligence-powered tools for the diagnosis and screening of COVID-19. Digital technologies are useful also for prevention and surveillance measures, for example through contact-tracing apps or monitoring of internet searches and social media usage. Discussion. It is worth taking advantage of the push given by the crisis, and mandatory to keep track of the digital solutions proposed today to implement tomorrow's best practices and models of care, and to be ready for any new moments of emergency.

show abstract

“…Current studies have demonstrated that arti cial intelligence could distinguish COVID-19 from other pneumonia [11,12], improve radiologists' performance in distinguishing COVID-19 from non-COVID-19 pneumonia on chest CT and provide clinical prognosis with good accuracy that can assist clinicians to timely adjust their clinical management and allocate resources appropriately [13][14][15][16][17][18][19]. However, COVID-19 is caused by SARS-CoV-2 virus, its CT manifestations resemble other types of viruses.…”

mentioning

confidence: 99%

Machine learning-based CT radiomics model Distinguishes COVID-19 from other viral pneumonia

Chen

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Purpose To develop a machine learning-based CT radiomics model is critical for the accurate diagnosis of the rapid spread Coronavirus disease 2019 (COVID-19).Methods In this retrospective study, a machine learning-based CT radiomics model was developed to extract features from chest CT exams for the detection of COVID-19. Other viral-pneumonia CT exams of the corresponding period were also included. The radiomics features extracted from the region of interest (ROI), the radiological features evaluated by the radiologists, the quantity features calculated by the AI segmentation and evaluation, and the clinical parameters including clinical symptoms, epidemiology history and biochemical results were enrolled in this study. The SVM model was built and the performance on the testing cohort was evaluated by the area under the receiver operating characteristic curve (AUC), sensitivity and specificity. Results For the SVM model that built on the radiomics features only, it reached an AUC of 0.688(95% CI 0.496 to 0.881) on the testing cohort. After the radiological features were enrolled, the AUC achieved 0.696(95% CI 0.501 to 0.892), then the AUC reached 0.753(95% CI 0.596 to 0.910) after the quantity features were included. Our final model employed all the features, reached the per-exam sensitivity and specificity for differentiating COVID-19 was 29 of 38 (0.763, 95% CI: 0.598 to 0.886]) and 12 of 13 (0.923, 95% CI: 0.640 to 0.998]), respectively, with an AUC of 0.968(95% CI 0.911 to 1.000). Conclusion The machine learning-based CT radiomics models may accurately detect COVID-19 and differentiate it from other viral pneumonia.

show abstract

A Fully Automatic Deep Learning System for COVID-19 Diagnostic and Prognostic Analysis

Cited by 108 publications

References 19 publications

The Role of Imaging in the Detection and Management of COVID-19: A Review

The Role of Imaging in the Detection and Management of COVID-19: A Review

How the COVID-19 pandemic is favoring the adoption of digital technologies in healthcare: a rapid literature review

Machine learning-based CT radiomics model Distinguishes COVID-19 from other viral pneumonia

Contact Info

Product

Resources

About