Related Experiment Video
Updated: Jan 14, 2026
07:53
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
Published on: October 13, 2023
2.0K
A novel Convolutional Shuffle Attention Xtreme Gradient Boost Network for improved lung cancer detection using
1Department of Computer Science and Engineering, R.M.K. College of Engineering and Technology, R.S.M. Nagar, Puduvoyal - 601206, Tamil Nadu, India.
Computational Biology and Chemistry
|October 17, 2025
Summary
This study introduces a novel hybrid model, SA-XGBNet, for automated lung cancer detection using Computed Tomography (CT) images. The model achieved high accuracy, demonstrating its potential for early and efficient lung cancer diagnosis.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Oncology
Background:
- Lung cancer is a leading cause of cancer-related mortality.
- Computed Tomography (CT) is crucial for lung cancer diagnosis.
- Manual interpretation of CT scans is time-consuming and prone to error, necessitating automated solutions.
Purpose of the Study:
- To propose a hybrid model, SA-XGBNet, for automated lung cancer detection in CT images.
- To integrate Shuffle Attention Network (SA-Net), Convolutional Xtreme Gradient Boost (ConvXGB), and Fractional Calculus (FC) for enhanced detection.
Main Methods:
- CT images were pre-processed using Kolmogorov-Wiener Filter and segmented with Dual Attention Network (DA-Net).
- Image augmentation techniques were applied to enhance the dataset.
- Feature extraction included shape, intensity, HOLBP with entropy, and texture-based descriptors, followed by detection using SA-XGBNet.
Main Results:
- The SA-XGBNet model achieved 92.975% accuracy on 90% training data.
- Achieved a True Positive Rate (TPR) of 94.977% and a True Negative Rate (TNR) of 90.866%.
- Performance was validated using the LIDC-IDRI dataset.
Conclusions:
- The proposed SA-XGBNet model demonstrates significant potential for accurate and automated lung cancer detection from CT images.
- This hybrid approach offers a promising advancement in computer-aided diagnosis for lung cancer, improving diagnostic efficiency and accuracy.
