Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal

BMJ, Год журнала: 2020, Номер unknown, С. m1328 - m1328

Опубликована: Апрель 7, 2020

To review and appraise the validity usefulness of published preprint reports prediction models for diagnosing coronavirus disease 2019 (covid-19) in patients with suspected infection, prognosis covid-19, detecting people general population at increased risk covid-19 infection or being admitted to hospital disease.

Язык: Английский

---

Automated detection of COVID-19 cases using deep neural networks with X-ray images

Computers in Biology and Medicine, Год журнала: 2020, Номер 121, С. 103792 - 103792

Опубликована: Апрель 28, 2020

Язык: Английский

---

Can AI Help in Screening Viral and COVID-19 Pneumonia?

IEEE Access, Год журнала: 2020, Номер 8, С. 132665 - 132676

Опубликована: Янв. 1, 2020

Coronavirus disease (COVID-19) is a pandemic disease, which has already caused thousands of causalities and infected several millions people worldwide. Any technological tool enabling rapid screening the COVID-19 infection with high accuracy can be crucially helpful to healthcare professionals. The main clinical currently in use for diagnosis Reverse transcription polymerase chain reaction (RT-PCR), expensive, less-sensitive requires specialized medical personnel. X-ray imaging an easily accessible that excellent alternative diagnosis. This research was taken investigate utility artificial intelligence (AI) accurate detection from chest images. aim this paper propose robust technique automatic pneumonia digital images applying pre-trained deep-learning algorithms while maximizing accuracy. A public database created by authors combining databases also collecting recently published articles. contains mixture 423 COVID-19, 1485 viral pneumonia, 1579 normal Transfer learning used help image augmentation train validate deep Convolutional Neural Networks (CNNs). networks were trained classify two different schemes: i) pneumonia; ii) normal, without augmentation. classification accuracy, precision, sensitivity, specificity both schemes 99.7%, 99.7% 99.55% 97.9%, 97.95%, 98.8%, respectively.

Язык: Английский

---

Virology, Epidemiology, Pathogenesis, and Control of COVID-19

Viruses, Год журнала: 2020, Номер 12(4), С. 372 - 372

Опубликована: Март 27, 2020

The outbreak of emerging severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) disease (COVID-19) in China has been brought to global attention and declared a pandemic by the World Health Organization (WHO) on March 11, 2020. Scientific advancements since (SARS) 2002~2003 Middle East (MERS) 2012 have accelerated our understanding epidemiology pathogenesis SARS-CoV-2 development therapeutics treat viral infection. As no specific vaccines are available for control, epidemic COVID-19 is posing great threat public health. To provide comprehensive summary health authorities potential readers worldwide, we detail present introduce current state measures this review.

Язык: Английский

---

Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation, and Diagnosis for COVID-19

IEEE Reviews in Biomedical Engineering, Год журнала: 2020, Номер 14, С. 4 - 15

Опубликована: Апрель 16, 2020

The pandemic of coronavirus disease 2019 (COVID-19) is spreading all over the world. Medical imaging such as X-ray and computed tomography (CT) plays an essential role in global fight against COVID-19, whereas recently emerging artificial intelligence (AI) technologies further strengthen power tools help medical specialists. We hereby review rapid responses community (empowered by AI) toward COVID-19. For example, AI-empowered image acquisition can significantly automate scanning procedure also reshape workflow with minimal contact to patients, providing best protection technicians. Also, AI improve work efficiency accurate delineation infections CT images, facilitating subsequent quantification. Moreover, computer-aided platforms radiologists make clinical decisions, i.e., for diagnosis, tracking, prognosis. In this paper, we thus cover entire pipeline analysis techniques involved including acquisition, segmentation, follow-up. particularly focus on integration CT, both which are widely used frontline hospitals, order depict latest progress radiology fighting

Язык: Английский

---

Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks

Pattern Analysis and Applications, Год журнала: 2021, Номер 24(3), С. 1207 - 1220

Опубликована: Май 9, 2021

Язык: Английский

---

Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT Images

IEEE Transactions on Medical Imaging, Год журнала: 2020, Номер 39(8), С. 2626 - 2637

Опубликована: Май 22, 2020

Coronavirus Disease 2019 (COVID-19) spread globally in early 2020, causing the world to face an existential health crisis. Automated detection of lung infections from computed tomography (CT) images offers a great potential augment traditional healthcare strategy for tackling COVID-19. However, segmenting infected regions CT slices faces several challenges, including high variation infection characteristics, and low intensity contrast between normal tissues. Further, collecting large amount data is impractical within short time period, inhibiting training deep model. To address these novel COVID-19 Lung Infection Segmentation Deep Network ( Inf-Net ) proposed automatically identify chest slices. In our , parallel partial decoder used aggregate high-level features generate global map. Then, implicit reverse attention explicit edge-attention are utilized model boundaries enhance representations. Moreover, alleviate shortage labeled data, we present semi-supervised segmentation framework based on randomly selected propagation strategy, which only requires few leverages primarily unlabeled data. Our can improve learning ability achieve higher performance. Extensive experiments xmlns:xlink="http://www.w3.org/1999/xlink">COVID-SemiSeg real volumes demonstrate that outperforms most cutting-edge models advances state-of-the-art

Язык: Английский

---

Digital technologies in the public-health response to COVID-19

Nature Medicine, Год журнала: 2020, Номер 26(8), С. 1183 - 1192

Опубликована: Авг. 1, 2020

Digital technologies are being harnessed to support the public-health response COVID-19 worldwide, including population surveillance, case identification, contact tracing and evaluation of interventions on basis mobility data communication with public. These rapid responses leverage billions mobile phones, large online datasets, connected devices, relatively low-cost computing resources advances in machine learning natural language processing. This Review aims capture breadth digital innovations for worldwide their limitations, barriers implementation, legal, ethical privacy barriers, as well organizational workforce barriers. The future public health is likely become increasingly digital, we review need alignment international strategies regulation, use strengthen pandemic management, preparedness other infectious diseases. has resulted an accelerated development applications health, symptom monitoring tracing. Their potential wide ranging must be integrated into conventional approaches best effect.

Язык: Английский

---

Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans

Nature Machine Intelligence, Год журнала: 2021, Номер 3(3), С. 199 - 217

Опубликована: Март 15, 2021

Machine learning methods offer great promise for fast and accurate detection prognostication of COVID-19 from standard-of-care chest radiographs (CXR) computed tomography (CT) images. Many articles have been published in 2020 describing new machine learning-based models both these tasks, but it is unclear which are potential clinical utility. In this systematic review, we search EMBASE via OVID, MEDLINE PubMed, bioRxiv, medRxiv arXiv papers preprints uploaded January 1, to October 3, describe the diagnosis or prognosis CXR CT Our identified 2,212 studies, 415 were included after initial screening and, quality screening, 61 studies review. review finds that none use due methodological flaws and/or underlying biases. This a major weakness, given urgency with validated needed. To address this, give many recommendations which, if followed, will solve issues lead higher model development well documented manuscripts.

Язык: Английский

---

Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network

Applied Intelligence, Год журнала: 2020, Номер 51(2), С. 854 - 864

Опубликована: Сен. 5, 2020

Chest X-ray is the first imaging technique that plays an important role in diagnosis of COVID-19 disease. Due to high availability large-scale annotated image datasets, great success has been achieved using convolutional neural networks (CNN s) for recognition and classification. However, due limited medical images, classification images remains biggest challenge diagnosis. Thanks transfer learning, effective mechanism can provide a promising solution by transferring knowledge from generic object tasks domain-specific tasks. In this paper, we validate deep CNN, called Decompose, Transfer, Compose (DeTraC), chest images. DeTraC deal with any irregularities dataset investigating its class boundaries decomposition mechanism. The experimental results showed capability detection cases comprehensive collected several hospitals around world. High accuracy 93.1% (with sensitivity 100%) was normal, severe acute respiratory syndrome cases.

Язык: Английский

---