AUTHOR=Agarwal Sushant , Saxena Sanjay , Carriero Alessandro , Chabert Gian Luca , Ravindran Gobinath , Paul Sudip , Laird John R. , Garg Deepak , Fatemi Mostafa , Mohanty Lopamudra , Dubey Arun K. , Singh Rajesh , Fouda Mostafa M. , Singh Narpinder , Naidu Subbaram , Viskovic Klaudija , Kukuljan Melita , Kalra Manudeep K. , Saba Luca , Suri Jasjit S. 

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

JOURNAL=Frontiers in Artificial Intelligence

VOLUME=Volume 7 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1304483

DOI=10.3389/frai.2024.1304483

ISSN=2624-8212

ABSTRACT=Background: Detection of COVID-19 lesion location and position in Computed Tomography (CT) scans is essential for understanding COVID severity for early diagnosis of the disease, especially in patients having high ground-glass opacities, consolidations, and crazy paving, where RT-PCR is ineffective. Radiologists find the manual method for lesion detection very challenging and tedious. Previously solo deep learning (SDL) was tried but with low to moderate-level performance. This study presents two 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, five-fold cross-validation protocols, training on 3500 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. Conclusions: 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.