Characterization of abnormalities in breast cancer images using nature‐inspired metaheuristic optimized convolutional neural networks model. (22nd September 2021)

• Record Type: Journal Article
• Authors: Oyelade, Olaide N.; Ezugwu, Absalom E.
• Is Part Of: Concurrency and computation. Volume 34:Number 4(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-09-22
• Subjects: breast cancer -- convolutional neural network -- deep learning -- metaheuristic algorithm -- optimization; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.6629
• Languages: English
• ISSNs: 1532-0626

Abstract

Summary: Convolutional neural networks (CNN) are deep learning models widely reported as performing well in several image classification tasks. Training the networks for optimal performance is considered an NP‐hard problem. The combination of a metaheuristic algorithm with CNN has been proposed to address this problem because the metaheuristic algorithms have efficient performance, parameter tuning, and stagnation prevention methods. Moreover, there is now an increasing need to apply the best performing metaheuristic algorithm to optimize the parameters, training and learning rate of the CNN models. This study aims to investigate the best performing metaheuristic algorithm for fine‐tuning the weights, biases, and hyperparameters of CNN networks for solving the problem of characterization of abnormalities in breast images. Furthermore, hybrid models consisting of a CNN architecture and five representative metaheuristic algorithms to efficiently detect breast cancer abnormalities are presented. The adopted approach involves training a CNN network using genetic algorithm (GA), whale optimization algorithm (WOA), multiverse optimizer (MVO), satin bower optimization (SBO), and life choice‐based optimization (LCBO) algorithms to optimize only weights and bias of the model. Two categories of experiments were carried out: the first involved training of the CNN model, while the second involved optimizing the training of CNN model with metaheuristic algorithms. A comparative analysis of the impact of the proposed GA, WOA, MVO, SBO, and LCBO metaheuristic algorithms on the performance of the CNN architecture was carried out. Empirical and statistical analyses are presented to validate further the findings obtained in the study. Results obtained showed that MVO, SBO and LCBO outperformed GA, WOA. The classification accuracy obtained for CNN‐GA, CNN‐WOA, CNN‐MVO, CNN‐SBO, and CNN‐LCBO at the fifth epoch was 0.76, 0.75, 0.84, 0.80, and 0.86, respectively. At the same time, the traditional CNN achieved an accuracy of 0.66. The outcome of this study showed that contrary to widespread practice, physics‐based, biology‐based, and human‐based optimization algorithms promise better performance parameter tuning for CNN as compared with evolutionary‐based and swarm‐based metaheuristic algorithms.