This is the authors' abstract. We don't add key points for this paper.
A coronavirus disease known as COVID-19 caused a pandemic that killed a great number of people. Combined with reverse transcriptase-polymerase chain reaction, computed tomography has been considered a valuable and additional screening technique since its conception. Given their strong performance in related medical tasks, deep learning algorithms could provide COVID-19 solutions based on patient medical photos. The Global Healthcare System and patients have been impacted greatly by COVID-19. It is possible to combine the computed tomography and RT-PCR assays. A convolutional neural network was used in this study to evaluate COVID-19. When given bigger, out-of-field datasets, pertained models perform better on CT tests. The findings suggest that by offering a priori model knowledge, external training can improve CT scans. In terms of efficacy, the proposed transfer learning strategy performs better than the current methods discussed in the literature. We believe that the identification performance that our approach has so far provided is state-of-the-art. Trials utilizing randomly selected training datasets demonstrate our model's satisfactory performance. We examined the visual features of the CT scans that were important to the model; these might support manual screening by healthcare practitioners.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Prabu et al. (2024) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: