Adaptive optimisation driven deep belief networks for lung cancer detection and severity level classification. (22nd September 2021)

• Record Type: Journal Article
• Authors: Shanid, Malayil; Anitha, A.
• Is Part Of: International journal of bio-inspired computation. Volume 18:Number 2(2021)
• Page Start: 114
• Page End: 121
• Publication Date: 2021-09-22
• Subjects: lung cancer -- severity level -- CT images -- segmentation -- lung nodules; Biologically-inspired computing -- Periodicals; Computational biology -- Periodicals; 572.0285
• Languages: English
• ISSNs: 1758-0366

Abstract

Computed tomography (CT) for lung cancer detection is trending research in determining the lung cancer on its earlier stages. However, accurate lung cancer detection with severity levels is a major challenge faced by most of the existing methods. This paper proposes a lung cancer detection model for analysing the severity levels using the CT images. The input CT images are obtained from the input lung cancer database using which the lung cancer detection and severity level classification is performed. The shape local binary texture (SLBT) is employed, which is generated by combining local directional pattern (LDP) and linear binary pattern (LBP), which is extracted from the nodules. The features are subjected to proposed adaptive-SEOA-DBN, which is the integration of adaptive-salp-elephant herding optimisation algorithm (adaptive-SEOA) in DBN for effective training of the model parameters. The proposed adaptive-SEOA is developed by combining self-adaptive concept in the SEOA. Finally, severity level classification is done to declare the severity of patient. The effectiveness of the proposed adaptive-SEOA-DBN is revealed based on maximal accuracy of 96.096 and minimal false detection rate (FDR) of 0.019, minimal false positive rate (FPR) of 4.999, and maximal true positive rate (TPR) of 96.096, respectively.