Optimized deep learning architecture for brain tumor classification using improved Hunger Games Search Algorithm

• Published in: Computers in biology and medicine Vol. 160; p. 106966
• Main Authors: Emam, Marwa M., Samee, Nagwan Abdel, Jamjoom, Mona M., Houssein, Essam H.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.06.2023; Elsevier Limited
• Subjects: Algorithms; Basic converters; Brain; Brain - diagnostic imaging; Brain architecture; Brain cancer; Brain Neoplasms - diagnostic imaging; Brain tumor; Brain tumors; Brownian motion; Cancer; Classification; Convergence; Convolutional neural network; Datasets; Deep Learning; Evolutionary computation; Games; Heuristic methods; Humans; Hunger; Hunger games search (HGS); Internal Medicine; Local escaping operator; Machine learning; Operators (mathematics); Optimization; Other; Residual network; Search algorithms; Synapses; Synaptogenesis; Transfer learning; Tumors; Visual discrimination learning; Brain tumor; Deep learning; Brownian motion; Hunger games search (HGS); Local escaping operator; Transfer learning; Convolutional neural network; Residual network
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.106966

One of the worst diseases is a brain tumor, which is defined by abnormal development of synapses in the brain. Early detection of brain tumors is essential for improving prognosis, and classifying tumors is a vital step in the disease’s treatment. Different classification strategies using deep learning have been presented for the diagnosis of brain tumors. However, several challenges exist, such as the need for a competent specialist in classifying brain cancers by deep learning models and the problem of building the most precise deep learning model for categorizing brain tumors. We propose an evolved and highly efficient model based on deep learning and improved metaheuristic algorithms to address these challenges. Specifically, we develop an optimized residual learning architecture for classifying multiple brain tumors and propose an improved variant of the Hunger Games Search algorithm (I-HGS) based on combining two enhancing strategies: Local Escaping Operator (LEO) and Brownian motion. These two strategies balance solution diversity and convergence speed, boosting the optimization performance and staying away from the local optima. First, we have evaluated the I-HGS algorithm on the IEEE Congress on Evolutionary Computation held in 2020 (CEC’2020) test functions, demonstrating that I-HGS outperformed the basic HGS and other popular algorithms regarding statistical convergence, and various measures. The suggested model is then applied to the optimization of the hyperparameters of the Residual Network 50 (ResNet50) model (I-HGS-ResNet50) for brain cancer identification, proving its overall efficacy. We utilize several publicly available, gold-standard datasets of brain MRI images. The proposed I-HGS-ResNet50 model is compared with other existing studies as well as with other deep learning architectures, including Visual Geometry Group 16-layer (VGG16), MobileNet, and Densely Connected Convolutional Network 201 (DenseNet201). The experiments demonstrated that the proposed I-HGS-ResNet50 model surpasses the previous studies and other well-known deep learning models. I-HGS-ResNet50 acquired an accuracy of 99.89%, 99.72%, and 99.88% for the three datasets. These results efficiently prove the potential of the proposed I-HGS-ResNet50 model for accurate brain tumor classification. •A new optimized deep learning architecture for brain tumor classification using MRI images.•Optimized the hyperparameters and architecture of Deep Residual Learning model.•I-HGS is proposed for optimizing the hyperparameters selection-based deep learning.•The proposed model surpasses other SOTA methods using three public datasets.•CEC’2020 benchmark functions are used to evaluate the proposed I-HGS.