CoChat
Sign Up
Cited by 472COVID-19 diagnosis using AIArtificial Intelligence in Healthcare and EducationAdvanced Neural Network Applications

The DOI matches its Crossref record; 105 of the 110 references it cites were found in a registry or an index.

COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data

Open access
Horry, Michael J., Chakraborty, Subrata, Paul, Manoranjan, Ulhaq, Anwaar, Pradhan, Biswajeet, Saha, Manas, Shukla, Nagesh·2020·IEEE Access
DOI 10.1109/access.2020.3016780PMC PMC8668160
Open this paper in CoChat — free accountOpen PDF

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 suitableConvolutional 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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/access.2020.3016780

Cites

105 of 105 references verified0 citation errors · 0 not checkable

Statistics

Figures

FIGURE 1. COVID-19 progression over several days as evident in different imaging modes.
FIGURE 1. COVID-19 progression over several days as evident in different imaging modes.CC BY · PubMed Central
FIGURE 2. Different variations observed in the COVID-19 datasets.
FIGURE 2. Different variations observed in the COVID-19 datasets.CC BY · PubMed Central
FIGURE 3. Results of enhancement preprocessing on original samples for COVID-19, Pneumonia and Normal images.
FIGURE 3. Results of enhancement preprocessing on original samples for COVID-19, Pneumonia and Normal images.CC BY · PubMed Central
FIGURE 4. Experiment pipeline for preprocessing and classification.
FIGURE 4. Experiment pipeline for preprocessing and classification.CC BY · PubMed Central
FIGURE 5. Head architecture of the proposed models.
FIGURE 5. Head architecture of the proposed models.CC BY · PubMed Central
FIGURE 6. Model sensitivity to hyperparameters for experiment 1A.
FIGURE 6. Model sensitivity to hyperparameters for experiment 1A.CC BY · PubMed Central
FIGURE 7. Learning curves for different modes.
FIGURE 7. Learning curves for different modes.CC BY · PubMed Central
FIGURE 8. Confusion matrix for different modes.
FIGURE 8. Confusion matrix for different modes.CC BY · PubMed Central
FIGURE 9. Reduction of false negatives using thresholding.
FIGURE 9. Reduction of false negatives using thresholding.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 110 references

Research works printed but not linked: 6

  1. 2020, RSNA Challenge
  2. 2020, OPENCV Histograms-2 Histogram Equalization
  3. 2020, Nih Dataset
  4. 2020, Who COVID-19 Situation Reports
  5. bell, 2020, COVID-19 Radiopaedia
  6. 2020, ACR Recommendations

Cited by

Sorted by citations

Related

See all

Metadata

Authors
Horry, M. J., Chakraborty, S., Paul, M., Ulhaq, A., Pradhan, B., Saha, M., & Shukla, N.
Affiliations
  • University of Technology Sydney (AU)
  • Charles Sturt University (AU)
Corresponding author
Chakraborty, Subrata
ORCID
Venue
IEEE Access
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2020
Volume
8
Pages
149808-149824
ISSN
2169-3536 (ISSN-L)
DOI
10.1109/access.2020.3016780
PMC
PMC8668160
OpenAlex
W3049131298
Cited by
472
References
110
Citations by year
2026: 16 · 2025: 33 · 2024: 54 · 2023: 86 · 2022: 149 · 2021: 124 · 2020: 10
FWCI
44.93
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Access (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Victoria University Research Repository (Victoria University) (submittedVersion, cc-by)
  • RUNE (Research UNE) (submittedVersion, cc-by)
  • Charles Sturt University Research Output (CRO) (submittedVersion, other-oa)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • UTS ePRESS (University of Technology Sydney) (submittedVersion)
  • Griffith Research Online (submittedVersion, cc-by)
Topics
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
COVID-19 detection, transfer learning, multimodal medical imaging, chest radiography, ultrasonography, computed tomography, VGG19, convolutional neural networks, image preprocessing, image denoising, limited training data, pneumonia classification, automated disease diagnosis

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review