English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Reverse transcription-polymerase chain reaction (RT-PCR) is currently thegold standard in COVID-19 diagnosis. It can, however, take days to provide thediagnosis, and false negative rate is relatively high. Imaging, in particularchest computed tomography (CT), can assist with diagnosis and assessment ofthis disease. Nevertheless, it is shown that standard dose CT scan givessignificant radiation burden to patients, especially those in need of multiplescans. In this study, we consider low-dose and ultra-low-dose (LDCT and ULDCT)scan protocols that reduce the radiation exposure close to that of a singleX-Ray, while maintaining an acceptable resolution for diagnosis purposes. Sincethoracic radiology expertise may not be widely available during the pandemic,we develop an Artificial Intelligence (AI)-based framework using a collecteddataset of LDCT/ULDCT scans, to study the hypothesis that the AI model canprovide human-level performance. The AI model uses a two stage capsule networkarchitecture and can rapidly classify COVID-19, community acquired pneumonia(CAP), and normal cases, using LDCT/ULDCT scans. The AI model achieves COVID-19sensitivity of 89.5% +\- 0.11, CAP sensitivity of 95% +\- 0.11, normal casessensitivity (specificity) of 85.7% +\- 0.16, and accuracy of 90% +\- 0.06. Byincorporating clinical data (demographic and symptoms), the performance furtherimproves to COVID-19 sensitivity of 94.3% +\- pm 0.05, CAP sensitivity of 96.7%+\- 0.07, normal cases sensitivity (specificity) of 91% +\- 0.09 , and accuracyof 94.1% +\- 0.03. The proposed AI model achieves human-level diagnosis basedon the LDCT/ULDCT scans with reduced radiation exposure. We believe that theproposed AI model has the potential to assist the radiologists to accuratelyand promptly diagnose COVID-19 infection and help control the transmissionchain during the pandemic.

Human-level COVID-19 Diagnosis from Low-dose CT Scans Using a Two-stage Time-distributed Capsule Network