Automated Lung Tissue Segmentation in CT Images using Multi-Wavelet Filter Banks and Random Forest Algorithm

• Version
• Download 12
• File Size 0.00 KB
• File Count 1
• Create Date 13 December, 2025
• Last Updated 13 December, 2025

Automated Lung Tissue Segmentation in CT Images using Multi-Wavelet Filter Banks and Random Forest Algorithm

DOI : 10.46335/IJIES.2024.9.2.4

Authors : Narendra Lalchand Lokhande, Tushar Hrishikesh Jaware

Abstract – This research introduces an innovative methodology for automated tissue segmentation in lung CT images, aimed at enhancing precision in lung cancer detection. The proposed approach integrates a Multi-Wavelet Filter Bank for comprehensive feature extraction and the Random Forest algorithm for efficient tissue segmentation. The Multi-Wavelet Filter Bank captures diverse texture information across various scales and orientations, augmenting the discriminatory power of subsequent classification algorithms. Employing the Random Forest algorithm for tissue segmentation involves constructing an ensemble of decision trees, collectively contributing to a more robust segmentation process. The integration of Multi-Wavelet filters and Random Forest significantly improves the accuracy and reliability of automated tissue segmentation in lung CT images. This systematic fusion of Multi-Wavelet Filter Banks and Random Forest represents a promising advancement in lung cancer detection within clinical settings. The methodology presented herein serves as a valuable tool for healthcare professionals, aiding in the early and accurate interpretation of lung CT images for lung cancer diagnosis. While our results are promising, ongoing research is essential to refine and adapt the approach to diverse datasets, ensuring its applicability and effectiveness in real-world medical scenarios.