COVID-19 detection and analysis from lung CT images using novel channel boosted CNNs

Khan, Saddam Hussain; Iqbal, Javed; Hassnain, Syed Agha; Owais, Muhammad; Mostafa, Samih M.; Mahmoud, Amena

doi:10.1016/j.eswa.2023.120477

Cited by 22 publications

(9 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Detection metrics, including accuracy (Acc), sensitivity (S), precision (P), specificity (Sp), MCC, and F-score, are accompanied by equations (13)(14)(15)(16)(17)(18). Segmentation models are assessed based on segmentation accuracy (S-Acc), IoU, and DS coefficient, presented in equations ( 19) and (20).…”

Section: Performance Evaluationmentioning

confidence: 99%

“…Prior to the current pandemic, deep learning (DL)based systems supported radiologists in spotting lung anomalies, ensuring reproducibility, and detecting subtle irregularities not visible to the naked eye [13]. Amid the ongoing COVID-19 crisis, many research teams concentrate on creating automated systems for identifying infected individuals using CT images [14], [15].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Novel Deep CNNs Explore Regions, Boundaries, and Residual Learning for COVID-19 Infection Analysis in Lung CT

Alshemaimri,

Khan

2024

Preprint

Self Cite

View full text Add to dashboard Cite

COVID-19 poses a global health crisis, necessitating precise diagnostic methods for timely containment. However, accurately delineating COVID-19 affected regions in Lung CT scans is challenging due to contrast variations and significant texture diversity. In this regard, this study introduces a novel two-stage classification and segmentation CNN approach for COVID-19 lung radiological pattern analysis. A novel Residual-BRNet is developed to integrate boundary and regional operations with residual learning, capturing key COVID-19 radiological homogeneous regions, texture variations, and structural contrast patterns in the classification stage. Subsequently, infectious CT images undergo lesion segmentation in the second stage using the newly proposed RESeg segmentation CNN. The RESeg leverages both average and max-pooling implementations to simultaneously learn region homogeneity and boundary-related patterns. Furthermore, novel pixel attention (PA) blocks are integrated into RESeg to effectively address mildly infected regions. The evaluation of the proposed Residual-BRNet CNN demonstrates promising performance metrics, achieving an accuracy of 97.97%, F1-score of 98.01%, sensitivity of 98.42%, and MCC of 96.81%. Meanwhile, PA-RESeg achieves optimal segmentation performance with an IoU score of 98.43% and a Dice Similarity score of 95.96% of the lesion region. These findings highlight the potential of the proposed diagnosis framework to assist radiologists in identifying and analyzing COVID-19 affected lung regions.The CAD GUI diagnosis tool is provided at https://github.com/PRLAB21/COVID-19-Diagnostic-System.

show abstract

Section: Performance Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Novel Deep CNNs Explore Regions, Boundaries, and Residual Learning for COVID-19 Infection Analysis in Lung CT

Alshemaimri,

Khan

2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Initially, Khan et al [ 11 ] aimed to develop a large-scale screening model using chest CT images to distinguish COVID-19 pneumonia [ 11 – 14 ], Influenza-A viral pneumonia, and healthy cases. To achieve this, they employed ResNet18 with both location-attention mechanism and channel attention mechanism.…”

Section: Related Workmentioning

confidence: 99%

Big data analysis for Covid-19 in hospital information systems

Ying,

Peng,

Xie

2024

PLoS ONE

View full text Add to dashboard Cite

The COVID-19 pandemic has triggered a global public health crisis, affecting hundreds of countries. With the increasing number of infected cases, developing automated COVID-19 identification tools based on CT images can effectively assist clinical diagnosis and reduce the tedious workload of image interpretation. To expand the dataset for machine learning methods, it is necessary to aggregate cases from different medical systems to learn robust and generalizable models. This paper proposes a novel deep learning joint framework that can effectively handle heterogeneous datasets with distribution discrepancies for accurate COVID-19 identification. We address the cross-site domain shift by redesigning the COVID-Net’s network architecture and learning strategy, and independent feature normalization in latent space to improve prediction accuracy and learning efficiency. Additionally, we propose using a contrastive training objective to enhance the domain invariance of semantic embeddings and boost classification performance on each dataset. We develop and evaluate our method with two large-scale public COVID-19 diagnosis datasets containing CT images. Extensive experiments show that our method consistently improves the performance both datasets, outperforming the original COVID-Net trained on each dataset by 13.27% and 15.15% in AUC respectively, also exceeding existing state-of-the-art multi-site learning methods.

show abstract

“…In Eq (6), M and N stand for the height and width of the input image, respectively. Finally, an edge image (say, I e ) is obtained using Eq (7). Pixels with magnitude values above the threshold value (th) are considered as edge pixels (white in the output), while those below the threshold are considered as background pixels (black in the output).…”

Section: Roberts Edge Operatormentioning

confidence: 99%

DBU-Net: Dual branch U-Net for tumor segmentation in breast ultrasound images

Pramanik,

Schwenker

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

Breast ultrasound medical images often have low imaging quality along with unclear target boundaries. These issues make it challenging for physicians to accurately identify and outline tumors when diagnosing patients. Since precise segmentation is crucial for diagnosis, there is a strong need for an automated method to enhance the segmentation accuracy, which can serve as a technical aid in diagnosis. Recently, the U-Net and its variants have shown great success in medical image segmentation. In this study, drawing inspiration from the U-Net concept, we propose a new variant of the U-Net architecture, called DBU-Net, for tumor segmentation in breast ultrasound images. To enhance the feature extraction capabilities of the encoder, we introduce a novel approach involving the utilization of two distinct encoding paths. In the first path, the original image is employed, while in the second path, we use an image created using the Roberts edge filter, in which edges are highlighted. This dual branch encoding strategy helps to extract the semantic rich information through a mutually informative learning process. At each level of the encoder, both branches independently undergo two convolutional layers followed by a pooling layer. To facilitate cross learning between the branches, a weighted addition scheme is implemented. These weights are dynamically learned by considering the gradient with respect to the loss function. We evaluate the performance of our proposed DBU-Net model on two datasets, namely BUSI and UDIAT, and our experimental results demonstrate superior performance compared to state-of-the-art models.

show abstract

COVID-19 detection and analysis from lung CT images using novel channel boosted CNNs

Cited by 22 publications

References 46 publications

Novel Deep CNNs Explore Regions, Boundaries, and Residual Learning for COVID-19 Infection Analysis in Lung CT

Novel Deep CNNs Explore Regions, Boundaries, and Residual Learning for COVID-19 Infection Analysis in Lung CT

Big data analysis for Covid-19 in hospital information systems

DBU-Net: Dual branch U-Net for tumor segmentation in breast ultrasound images

Contact Info

Product

Resources

About