HADCNet: Automatic segmentation of COVID-19 infection based on a hybrid attention dense connected network with dilated convolution

Chen, Ying; Zhou, Taohui; Chen, Yi; Feng, Longfeng; Zheng, Cheng; Liu, Lan; Hu, Liping; Pan, Bailin

doi:10.1016/j.compbiomed.2022.105981

Cited by 27 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ADID-UNet achieved an average Dice score of 0.803 on the MedSeg + Radiopaedia dataset with the Dice loss. Ying Chen et al proposed a HADCNet model based on UNet that contains hybrid attention modules in five stages of the encoder and decoder [42]. It helps balance the semantic differences between various levels of features, which refines the feature information.…”

Section: Related Workmentioning

confidence: 99%

SAA-UNet: Spatial Attention and Attention Gate UNet for COVID-19 Pneumonia Segmentation from Computed Tomography

2023

View full text Add to dashboard Cite

The disaster of the COVID-19 pandemic has claimed numerous lives and wreaked havoc on the entire world due to its transmissible nature. One of the complications of COVID-19 is pneumonia. Different radiography methods, particularly computed tomography (CT), have shown outstanding performance in effectively diagnosing pneumonia. In this paper, we propose a spatial attention and attention gate UNet model (SAA-UNet) inspired by spatial attention UNet (SA-UNet) and attention UNet (Att-UNet) to deal with the problem of infection segmentation in the lungs. The proposed method was applied to the MedSeg, Radiopaedia 9P, combination of MedSeg and Radiopaedia 9P, and Zenodo 20P datasets. The proposed method showed good infection segmentation results (two classes: infection and background) with an average Dice similarity coefficient of 0.85, 0.94, 0.91, and 0.93 and a mean intersection over union (IOU) of 0.78, 0.90, 0.86, and 0.87, respectively, on the four datasets mentioned above. Moreover, it also performed well in multi-class segmentation with average Dice similarity coefficients of 0.693, 0.89, 0.87, and 0.93 and IOU scores of 0.68, 0.87, 0.78, and 0.89 on the four datasets, respectively. Classification accuracies of more than 97% were achieved for all four datasets. The F1-scores for the MedSeg, Radiopaedia P9, combination of MedSeg and Radiopaedia P9, and Zenodo 20P datasets were 0.865, 0.943, 0.917, and 0.926, respectively, for the binary classification. For multi-class classification, accuracies of more than 96% were achieved on all four datasets. The experimental results showed that the framework proposed can effectively and efficiently segment COVID-19 infection on CT images with different contrast and utilize this to aid in diagnosing and treating pneumonia caused by COVID-19.

show abstract

Section: Related Workmentioning

confidence: 99%

SAA-UNet: Spatial Attention and Attention Gate UNet for COVID-19 Pneumonia Segmentation from Computed Tomography

2023

View full text Add to dashboard Cite

show abstract

A Resampling Ant Colony Optimization with Elite Exploration and Convergence Mechanism for Multithreshold Segmentation of Breast Cancer Images

Wang,

Zhao,

Heidari

et al. 2024

Advanced Intelligent Systems

View full text Add to dashboard Cite

Previous studies have emphasized the potential of threshold image segmentation for early breast cancer detection. However, traditional methods encounter challenges regarding low segmentation efficiency and accuracy. Addressing this, the ant colony optimization algorithm for continuous optimization (ACOR) shows promise. Yet, existing ACOR variants still grapple with poor initial population quality, affecting convergence speed and avoiding local optimization. These issues impact segmentation efficiency and accuracy. To tackle them, this study introduces RESACO, an enhanced ACOR version integrating three novel optimization strategies: resampling initialization (RIS), elite exploration (EES), and strengthened convergence mechanism (SCM). RIS enhances initial population quality by resampling regions with individuals demonstrating superior fitness and segmentation efficiency. EES promotes exploration across the search space, preventing local optima entrapment and enhancing model stability. SCM expediting convergence, segmentation efficiency, and precision. RESACO's performance is assessed through extensive experiments using IEEE CEC 2014 and IEEE CEC 2022 benchmark functions, including ablation experiments and comparisons with basic and improved algorithms and ACOR variants. Subsequently, the threshold image segmentation model based on RESACO is compared with other models using metaheuristic algorithms for segmenting realistic breast cancer medical images. Results demonstrate the proposed model's faster convergence and higher segmentation accuracy, preserving more lesion tissue details.

show abstract

Dual Self-attention Fusion Message Neural Network for Virtual Screening in Drug Discovery by Molecular Property Prediction

Wang,

Hou,

Chen

et al. 2024

J Bionic Eng

View full text Add to dashboard Cite

HADCNet: Automatic segmentation of COVID-19 infection based on a hybrid attention dense connected network with dilated convolution

Cited by 27 publications

References 35 publications

SAA-UNet: Spatial Attention and Attention Gate UNet for COVID-19 Pneumonia Segmentation from Computed Tomography

SAA-UNet: Spatial Attention and Attention Gate UNet for COVID-19 Pneumonia Segmentation from Computed Tomography

A Resampling Ant Colony Optimization with Elite Exploration and Convergence Mechanism for Multithreshold Segmentation of Breast Cancer Images

Dual Self-attention Fusion Message Neural Network for Virtual Screening in Drug Discovery by Molecular Property Prediction

Contact Info

Product

Resources

About