A Multi-Task Attention-Driven SegNet for Lung Infection Segmentation and Classification From HRCT Images
TL;DR
This study introduces a multi-task attention-driven SegNet model for automated segmentation and classification of lung infections from HRCT images, leveraging deep learning to improve diagnostic accuracy in lung disease detection.
A Multi-Task Attention-Driven SegNet for Lung Infection Segmentation and Classification From HRCT Images
Upasana Bhattacharjya; Kandarpa Kumar Sarma; Anchita Kakati; Jyoti Prakash Medhi; Geetanjali Barman; Binoy Kumar Choudhury; Dmitrii Kaplun; Alexander Voznesensky
https://doi.org/10.1109/ACCESS.2025.3646487
Volume 14
High-resolution computed tomography (HRCT) plays a critical role in diagnosing lung diseases by providing detailed visualization of infections, inflammation, fibrosis and tumors. Recent advances in deep learning have enabled automated detection and segmentation of infected regions, with attention mechanisms further enhancing feature discrimination. This study proposes a multi-task attention-driven...