Deep Learning System for COVID-19 Diagnostic and Predictive Analysis
Keywords:
CT scan, RT-PCR, ROI identification, UNetAbstract
Beginning in early 2020, COVID-19, a health emergency and existential threat to society, began to spread globally. The current healthcare approach to combat COVID-19 has the potential to be considerably improved by automated lung infection detection utilising computed tomography (CT) images. To segment contaminated areas from CT slices, however, there are a number of difficulties, including low intensity and a wide range of infectious features when comparing infected and healthy tissues. Additionally, it is not feasible to collect a big amount of data quickly, which inhibits the deep model from being trained. To overcome these difficulties, a novel COVID-19 Lung Infection Deep Network Segmentation is proposed to autonomously separate unhealthy areas from slices of a chest CT image. This study provides a segmentation technique for Ground Glass Opacity or ROI identification in CT images caused by corona viruses. The area of interest was categorised down to the pixel level using a modified Unet model structure. Instead of the time consuming RT-PCR test, CT scans can be utilised to diagnose COVID-19. Using this segmentation method, doctors were able to diagnose COVID-19 more quickly, precisely, and consistently.
References
- Wang D, Hu B, Hu C, et al. Clinical characteristics of 138 hospitalized patients with 2019 novel coronavirus–infected pneumonia in Wuhan, China. JAMA 2020; 323: 1061–1069.
- Li Q, Guan X, Wu P, et al. Early transmission dynamics in Wuhan, China, of novel coronavirus–infected pneumonia. N Engl J Med 2020; 382: 1199–1207.
- Yang X, Yu Y, Xu J, et al. Clinical course and outcomes of critically ill patients with SARS-CoV-2 pneumonia in Wuhan, China: a single-centered, retrospective, observational study. Lancet Respir Med 2020; 8: 475–481.
- Ji Y, Ma Z, Peppelenbosch MP, et al. Potential association between COVID-19 mortality and health-care resource availability. Lancet Glob Health 2020; 8: e480.
- Xie X, Zhong Z, Zhao W, et al. Chest CT for typical 2019-nCoV pneumonia: relationship to negative RT-PCR testing. Radiology 2020; 296; E41–E45.
- Ai T, Yang Z, Hou H, et al. Correlation of chest CT and RT-PCR testing in coronavirus disease 2019 (COVID-19) in China: a report of 1014 cases. Radiology 2020; 296; E32–E40.
- Zhang S, Li H, Huang S, et al. High-resolution computed tomography features of 17 cases of coronavirus disease 2019 in Sichuan province, China. Eur Respir J 2020; 55; 2000334.
- Wang L, Gao Y-h, Zhang G-J. The clinical dynamics of 18 cases of COVID-19 outside of Wuhan, China. Eur Respir J 2020; 55; 2000398.
- Shi H, Han X, Jiang N, et al. Radiological findings from 81 patients with COVID-19 pneumonia in Wuhan, China: a descriptive study. Lancet Infect Dis 2020; 20; 425–434.
- Lee EY, Ng M-Y, Khong P-L. COVID-19 pneumonia: what has CT taught us? Lancet Infect Dis 2020; 20: 384–385.
- Wang S, Shi J, Ye Z, et al. Predicting EGFR mutation status in lung adenocarcinoma on computed tomography image using deep learning. Eur Respir J 2019; 53: 1800986.
- Walsh SL, Calandriello L, Silva M, et al. Deep learning for classifying fibrotic lung disease on high-resolution computed tomography: a case-cohort study. Lancet Respir Med 2018; 6: 837–845.
- Walsh SL, Humphries SM, Wells AU, et al. Imaging research in fibrotic lung disease; applying deep learning to unsolved problems. Lancet Respir Med 2020; in press [https://doi.org/10.1016/S2213-2600(20)30003-5].
- Angelini E, Dahan S, Shah A. Unravelling machine learning: insights in respiratory medicine. Eur Respir J 2019; 54: 1901216.
- Wang S, Zhou M, Liu Z, et al. Central focused convolutional neural networks: developing a data-driven model for lung nodule segmentation. Med Image Anal 2017; 40: 172–183.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRSET
This work is licensed under a Creative Commons Attribution 4.0 International License.