Convolution-based adaptive ResUNet3 + with attention-based ensemble convolution networks for COVID-19 segmentation and classification
Year: 2025
Type: article
Abstract: In 2018, residual U-shaped network (Res-UNet) and dense U-shaped network (Dense-UNet) were born based on the U-Net architecture. Inspired by dense and residual connections, respectively, Res-UNet and Dense-UNet substitute a kind of dense or residual connection for each U-Net sub-module. The community of artificial intelligence has produced a variety of deep learning models with the intention of recognising COVID-19 based on the visual features of chest X-rays. It is unfortunate that this is the case since constructing really deployable clinical models often requires segmentation as a crucial precursor step. Other applications in radiology typically need segmentation. It might be difficult to differentiate COVID-19 from other pulmonary disorders due to the fact that many lung diseases have similar visual characteristics with COVID-19. Using a segmentation module and an ensemble classifier, we have constructed our deep learning pipeline with the intention of assisting in the clarification of the diagnosis of individuals who are suspected of having COVID-19. Following the completion of an exhaustive comparison investigation, we are able to show that our most advantageous model is capable of effectively achieving an accuracy of 91% and a sensitivity of 92%.
Authors: S. Salini, B. SelvaPriya
Language: English
Topic: COVID-19 diagnosis using AI
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: diamond
OpenAlex ID: W4417305469
FWCI:
Cites:
Cited by:
Related to: