Advanced lung cancer classification approach adopting modified graph clustering and whale optimisation‐based feature selection technique accompanied by a hybrid ensemble classifier. Issue 10 (8th July 2020)

• Record Type: Journal Article
• Authors: Mary Adline Priya, Michael; Joseph Jawhar, S.
• Is Part Of: IET image processing. Volume 14:Issue 10(2020)
• Page Start: 2204
• Page End: 2215
• Publication Date: 2020-07-08
• Subjects: computerised tomography -- support vector machines -- image segmentation -- feature extraction -- cancer -- pattern clustering -- image classification -- medical image processing -- lung -- feature selection -- graph theory -- optimisation -- nearest neighbour methods -- random forests; classification accuracy -- optimum feature selection -- modified graph clustering‐based whale optimisation algorithm -- advanced lung cancer classification approach -- whale optimisation‐based feature selection technique -- hybrid ensemble classifier -- cancer death -- cancerous cells -- medical field -- computed tomography -- imaging technique -- normal cancer -- CT lung image -- thresholding operations -- morphological operations -- lung regions -- feature extraction stage -- radiomic features -- noise removal -- histogram analysis -- support vector machine -- K‐nearest neighbour -- random forest -- F‐measure; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2019.0178
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Nowadays, lung cancer is the leading cause of cancer death in both men and women. The early detection of potentially cancerous cells is the best way to improve the patient's chances of survival. In the medical field, computed tomography (CT) is the best imaging technique and it is helpful for doctors to accurately find the cancerous cells. The authors propose an automatic approach to analyse and segment the lungs and classify each lung into normal or cancer. Initially, the CT lung image is pre‐processed to remove noise. Then, they combine the histogram analysis with thresholding and morphological operations to segment and extract the lung regions. In feature extraction stage, the radiomic features of each lung image are extracted separately. Then to improve the classification accuracy, some of the optimum features are selected using modified graph clustering‐based whale optimisation algorithm. Finally, the selected features are classified using ensemble classifiers such as support vector machine, K‐nearest neighbour, and random forest. Experimental result demonstrates that the proposed method achieves better performance in terms of sensitivity, specificity, precision, recall, F ‐measure, and accuracy when compared with other state‐of‐art approaches.