Abstract: Lung cancer is one of the leading causes of cancer-related deaths worldwide. Early detection of lung cancer is crucial for successful treatment and improved survival rates. In this paper, we propose a system for lung cancer detection using digital image processing and machine learning techniques. The proposed system uses digital image processing techniques to segment lung nodules from computed tomography (CT) scans. Features are then extracted from the segmented nodules using texture analysis and shape analysis. These features are used to train a machine learning classifier that can differentiate between malignant and benign nodules. We evaluated the performance of the proposed system using a dataset of 300 CT scans from the Lung Image Database Consortium (LIDC). Our results show that the proposed system achieved an accuracy of 91.67% in detecting lung nodules, outperforming other state-of-the-art approaches. Overall, the proposed system has the potential to improve the accuracy and efficiency of lung cancer detection, leading to earlier diagnosis and better treatment outcomes.
Keywords: Feature Extraction, Adaptive Thresholding, Matching, Multi-Label Classification, CT (computed Tomography), Image Processing, Machine Learning, Convolutional Neural Network (CNN), etc
|
DOI:
10.17148/IJARCCE.2024.13458
