Dual-model approach for accurate chest disease detection using GViT and swin transformer V2.
Authors
Affiliations (5)
Affiliations (5)
- Department of Computer Science, National University of Computing and Emerging Sciences, Hayatabad, Peshawar, 24720, Pakistan.
- School of Computing and Data Sciences, Oryx Universal College with Liverpool John Moores University, Doha, 34110, Qatar.
- College of Technological Innovation, Zayed University, 19282, Dubai, United Arab Emirates.
- Department of Applied AI, School of Convergence, College of Computing and Informatics, Sungkyunkwan University, Seoul, 03063, Republic of Korea. [email protected].
- Centre for Autonomous Robotic Systems, Khalifa University, Abu Dhabi, United Arab Emirates. [email protected].
Abstract
The precise detection and localization of abnormalities in radiological images are very crucial for clinical diagnosis and treatment planning. To build reliable models, large and annotated datasets are required that contain disease labels and abnormality locations. Most of the time, radiologists face challenges in identifying and segmenting thoracic diseases such as COVID-19, Pneumonia, Tuberculosis, and lung cancer due to overlapping visual patterns in X-ray images. This study proposes a dual-model approach: Gated Vision Transformers (GViT) for classification and Swin Transformer V2 for segmentation and localization. GViT successfully identifies thoracic diseases that exhibit similar radiographic features, while Swin Transformer V2 maps lung areas and pinpoints affected regions. Classification metrics, including precision, recall, and F1-scores, surpassed 0.95 while the Intersection over Union (IoU) score reached 90.98%. Performance assessment via Dice Coefficient, Boundary F1-Score, and Hausdorff Distance demonstrated the system's excellent effectiveness. This artificial intelligence solution will help radiologists in decreasing their mental workload while improving diagnostic precision in healthcare systems that face resource constraints. Transformer-based architectures show strong promise for enhancing medical imaging procedures, according to the study results. Future AI tools should build on this foundation, focusing on comprehensive and precise detection of chest diseases to support effective clinical decision-making.