Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jun 28:7:1304483.
doi: 10.3389/frai.2024.1304483. eCollection 2024.

COVLIAS 3.0: cloud-based quantized hybrid UNet3+ deep learning for COVID-19 lesion detection in lung computed tomography

Sushant Agarwal  1   2 , Sanjay Saxena  3 , Alessandro Carriero  4 , Gian Luca Chabert  5 , Gobinath Ravindran  6 , Sudip Paul  7 , John R Laird  8 , Deepak Garg  9 , Mostafa Fatemi  10 , Lopamudra Mohanty  11   12 , Arun K Dubey  13 , Rajesh Singh  14 , Mostafa M Fouda  15 , Narpinder Singh  16 , Subbaram Naidu  17 , Klaudija Viskovic  18 , Melita Kukuljan  19 , Manudeep K Kalra  20 , Luca Saba  5 , Jasjit S Suri  15   21   22   23
Affiliations

COVLIAS 3.0: cloud-based quantized hybrid UNet3+ deep learning for COVID-19 lesion detection in lung computed tomography

Sushant Agarwal et al. Front Artif Intell. .

Abstract

Background and novelty: When RT-PCR is ineffective in early diagnosis and understanding of COVID-19 severity, Computed Tomography (CT) scans are needed for COVID diagnosis, especially in patients having high ground-glass opacities, consolidations, and crazy paving. Radiologists find the manual method for lesion detection in CT very challenging and tedious. Previously solo deep learning (SDL) was tried but they had low to moderate-level performance. This study presents two new cloud-based quantized deep learning UNet3+ hybrid (HDL) models, which incorporated full-scale skip connections to enhance and improve the detections.

Methodology: Annotations from expert radiologists were used to train one SDL (UNet3+), and two HDL models, namely, VGG-UNet3+ and ResNet-UNet3+. For accuracy, 5-fold cross-validation protocols, training on 3,500 CT scans, and testing on unseen 500 CT scans were adopted in the cloud framework. Two kinds of loss functions were used: Dice Similarity (DS) and binary cross-entropy (BCE). Performance was evaluated using (i) Area error, (ii) DS, (iii) Jaccard Index, (iii) Bland-Altman, and (iv) Correlation plots.

Results: Among the two HDL models, ResNet-UNet3+ was superior to UNet3+ by 17 and 10% for Dice and BCE loss. The models were further compressed using quantization showing a percentage size reduction of 66.76, 36.64, and 46.23%, respectively, for UNet3+, VGG-UNet3+, and ResNet-UNet3+. Its stability and reliability were proved by statistical tests such as the Mann-Whitney, Paired t-Test, Wilcoxon test, and Friedman test all of which had a p < 0.001.

Conclusion: Full-scale skip connections of UNet3+ with VGG and ResNet in HDL framework proved the hypothesis showing powerful results improving the detection accuracy of COVID-19.

Keywords: COVID lesions; COVID-19; computed tomography; glass ground opacities; hybrid deep learning; quantization; segmentation.

PubMed Disclaimer

Conflict of interest statement

SA was employed at GBTI, United States. JS was employed by AtheroPoint™, United States. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Raw CT images from the Croatian dataset.
Figure 2
Figure 2
Manual overlays (red) on raw CT images.
Figure 3
Figure 3
Top: UNet (Ronneberger et al., 2015), Middle UNet++ (Zhou et al., 2020), and Bottom: UNet 3+ (Huang et al., 2020).
Figure 4
Figure 4
AI predicted COVID-19 lesion overlay, using three models: UNet3+ (row 1 and 2), VGG-UNet3+ (row 3 and 4), and ResNet-UNet3+ (row 5 and 6). BCE and Dice are the two loss functions.
Figure 5
Figure 5
Area error.
Figure 6
Figure 6
Dice Similarity plot.
Figure 7
Figure 7
Jaccard Index plot.
Figure 8
Figure 8
BA Plot.
Figure 9
Figure 9
CC Plot.
Figure 10
Figure 10
Landing page of COVLIAS 3.0: Hybrid AI-Based COVID-19 Lesion Segmentation system.
Figure 11
Figure 11
Snapshot of the result page using COVLIAS 3.0: Hybrid AI-Based COVID-19 Lesion Segmentation system.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Acharya R. U., Faust O., Alvin A. P. C., Sree S. V., Molinari F., Saba L., et al. . (2012a). Symptomatic vs. asymptomatic plaque classification in carotid ultrasound. J. Med. Syst. 36, 1861–1871. doi: 10.1007/s10916-010-9645-2, PMID: - DOI - PubMed
    1. Acharya U. R., Faust O., Vinitha Sree S., Alvin A. P. C., Krishnamurthi G., Seabra J. C. R., et al. . (2013b). Understanding symptomatology of atherosclerotic plaque by image-based tissue characterization. Comput. Methods Prog. Biomed. 110, 66–75. doi: 10.1016/j.cmpb.2012.09.008, PMID: - DOI - PubMed
    1. Acharya U. R., Mookiah M. R. K., Vinitha Sree S., Afonso D., Sanches J., Shafique S., et al. . (2013c). Atherosclerotic plaque tissue characterization in 2D ultrasound longitudinal carotid scans for automated classification: a paradigm for stroke risk assessment. Med. Biol. Eng. Comput. 51, 513–523. doi: 10.1007/s11517-012-1019-0, PMID: - DOI - PubMed
    1. Acharya U. R., Saba L., Molinari F., Guerriero S., Suri J. S. (2012b). “Ovarian tumor characterization and classification: a class of GyneScan™ systems” in 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, pp. 4446–4449. - PubMed
    1. Acharya U. R., Vinitha Sree S., Mookiah M. R. K., Yantri R., Molinari F., Zieleźnik W., et al. . (2013a). Diagnosis of Hashimoto’s thyroiditis in ultrasound using tissue characterization and pixel classification. Proc. Inst. Mech. Eng. H J. Eng. Med. 227, 788–798. doi: 10.1177/0954411913483637, PMID: - DOI - PubMed

LinkOut - more resources