RTsDEN: reverse task attention enabled deep learning model for lung cancer detection using computed tomography

BACKGROUND: Lung cancer remains the most significant cause of cancer-related death worldwide due to the critical challenges in diagnosis. Despite the promising efforts, the existing models faced challenges in capturing the complex patterns in medical imaging data while minimizing the computational complexity. In this research, the lung cancer detection using Computed Tomography (CT) images is performed using the Reverse Task attention-enabled Distributed Elman convolutional neural Network (RTsDEN) model that helps in mitigating the challenges in existing methods and improving the detection performance for real-time applications. RESEARCH DESIGN AND METHODS: The proposed model, combining the Reverse Task attention-(RTsAt) module and the distributed Elman concept, significantly contributes to capturing the intricate disease patterns from the complex backgrounds and varying environmental conditions. In addition, the proposed method exploits the adaptive lobe and multigranular nodule segmentation stage to facilitate better understanding and interpretation for accurate diagnosis. RESULTS: Experimental results reveal that the proposed RTsDEN outperforms other existing models by attaining 97.12% accuracy, 98.03% precision 96.22% recall using LUNA 16 dataset and 97.72% accuracy, 98.31% precision, 97.14% recall using the LIDC-IDRI dataset. CONCLUSION: The research introduces an efficient DL model with an ensemble approach, which significantly influences effective lung cancer detection.