75
views
0
recommends
+1 Recommend
2 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data

      research-article

      Read this article at

      ScienceOpenPublisherPMC
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Detecting COVID-19 early may help in devising an appropriate treatment plan and disease containment decisions. In this study, we demonstrate how transfer learning from deep learning models can be used to perform COVID-19 detection using images from three most commonly used medical imaging modes X-Ray, Ultrasound, and CT scan. The aim is to provide over-stressed medical professionals a second pair of eyes through intelligent deep learning image classification models. We identify a suitable Convolutional Neural Network (CNN) model through initial comparative study of several popular CNN models. We then optimize the selected VGG19 model for the image modalities to show how the models can be used for the highly scarce and challenging COVID-19 datasets. We highlight the challenges (including dataset size and quality) in utilizing current publicly available COVID-19 datasets for developing useful deep learning models and how it adversely impacts the trainability of complex models. We also propose an image pre-processing stage to create a trustworthy image dataset for developing and testing the deep learning models. The new approach is aimed to reduce unwanted noise from the images so that deep learning models can focus on detecting diseases with specific features from them. Our results indicate that Ultrasound images provide superior detection accuracy compared to X-Ray and CT scans. The experimental results highlight that with limited data, most of the deeper networks struggle to train well and provides less consistency over the three imaging modes we are using. The selected VGG19 model, which is then extensively tuned with appropriate parameters, performs in considerable levels of COVID-19 detection against pneumonia or normal for all three lung image modes with the precision of up to 86% for X-Ray, 100% for Ultrasound and 84% for CT scans.

          Related collections

          Most cited references98

          • Record: found
          • Abstract: not found
          • Conference Proceedings: not found

          Deep Residual Learning for Image Recognition

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            ImageNet Large Scale Visual Recognition Challenge

              Bookmark
              • Record: found
              • Abstract: found
              • Article: found

              Detection of SARS-CoV-2 in Different Types of Clinical Specimens

              This study describes results of PCR and viral RNA testing for SARS-CoV-2 in bronchoalveolar fluid, sputum, feces, blood, and urine specimens from patients with COVID-19 infection in China to identify possible means of non-respiratory transmission.
                Bookmark

                Author and article information

                Contributors
                Journal
                IEEE Access
                IEEE Access
                0063500
                ACCESS
                IAECCG
                Ieee Access
                IEEE
                2169-3536
                2020
                14 August 2020
                : 8
                : 149808-149824
                Affiliations
                [1] divisionCentre for Advanced Modelling and Geospatial Information Systems (CAMGIS), School of Information, Systems, and Modeling, Faculty of Engineering and IT, institutionUniversity of Technology Sydney, institutionringgold 1994; Sydney NSW 2007 Australia
                [2] divisionMachine Vision and Digital Health (MaViDH), School of Computing and Mathematics, institutionCharles Sturt University, institutionringgold 1109; Bathurst NSW 2795 Australia
                [3] institutionManning Rural Referral Hospital; Taree NSW 2430 Australia
                [4] departmentDepartment of Energy and Mineral Resources Engineering, institutionSejong University, institutionringgold 35006; Seoul 05006 South Korea
                [5] institutionIBM Australia Limited; Sydney NSW 2065 Australia
                Article
                10.1109/ACCESS.2020.3016780
                8668160
                34931154
                e472257d-330d-43de-ad35-a778eca14994
                This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/

                This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/

                History
                : 06 August 2020
                : 11 August 2020
                : 25 August 2020
                Page count
                Figures: 9, Tables: 5, Equations: 17, References: 104, Pages: 17
                Categories
                Computational and artificial intelligence
                Imaging
                Biomedical Engineering

                covid-19 detection,image processing,model comparison,cnn models,x-ray,ultrasound and ct based detection

                Comments

                Comment on this article