A Flexible Multi-Channel Deep Network Leveraging Texture and Spatial Features for Diagnosing New COVID-19 Variants in...

The COVID-19 pandemic has claimed thousands of lives worldwide. While infection rates have declined in recent years, emerging variants remain a deadly threat. Accurate diagnosis is critical to curbing transmission and improving treatment outcomes. However, the similarity of COVID-19 symptoms to those of the common cold and flu has spurred the development of automated diagnostic methods, particularly through lung computed-tomography (CT) scan analysis.

This paper proposes a novel deep learning-based approach for detecting diverse COVID-19 variants using advanced textural feature extraction. The framework employs a dual-channel convolutional neural network (CNN), where one channel processes texture-based features and the other analyzes spatial information. Unlike existing methods, our model dynamically learns textural patterns during training, eliminating reliance on predefined features. A modified local binary pattern (LBP) technique extracts texture data in matrix form, while the CNN's adaptable internal architecture optimizes the balance between accuracy and computational efficiency. To enhance performance, hyperparameters are fine-tuned using the Adam optimizer and focal loss function.

The proposed method is evaluated on two benchmark datasets, COVID-349 and Italian COVID-Set, which include diverse COVID-19 variants.

The results demonstrate its superior accuracy (94.63% and 95.47%, respectively), outperforming competing approaches in precision, recall, and overall diagnostic reliability.