Application of Machine Learning to X-Ray and CT images in the diagnosis of COVID-19

By Ahmed El-Medany

Chest CT scans and X-ray images have been reported to have sensitivity values of 98 and 69%, respectively, with regards to diagnosing SARS-CoV-2 pneumonitis.

In this review by Mohammad-Rahimi et al, 105 studies reporting on machine and deep learning methods on CT and X-ray images in COVID-19 were analysed and compared. The accuracy of these methods ranged from 76% to more than 99%, suggesting the applicability of machine and deep learning methods in the clinical diagnosis of COVID-19; albeit with the requirement for multidisciplinary approaches in cases of clinical uncertainty.

**Figure 1**. PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) chart showing the process of systematic identification, screening, and selection of articles.

Read the full article at: https://www.frontiersin.org/articles/10.3389/fcvm.2021.638011/full#h1

Mohammad-Rahimi, H., Nadimi, M., Langeroudi, A.G., Taheri, M. and Ghafouri-Fard, S., 2021. Application of Machine Learning in Diagnosis of COVID-19 through X-Ray and CT Images: A Scoping Review. Frontiers in Cardiovascular Medicine, 8, p.185. https://doi.org/10.3389/fcvm.2021.63801