Abstract
This research paper presents an innovative approach to brain tumor diagnosis using MRI scans, using the power of deep learning and metaheuristic algorithm. The study employs Mobilenetv2, a deep learning model, optimized by a novel metaheuristic known as the Contracted Fox Optimization Algorithm (MN-V2/CFO). This methodology allows for the optimal selection of Mobilenetv2 hyperparameters, enhancing the accuracy of tumor detection. The model is implemented on the Figshare dataset, a comprehensive collection of MRI scans, and its performance is validated against other processes the results are compared with some published works including Network (RN), wavelet transform, and deep learning (WT/DL), customized VGG19, and Convolutional neural network (CNN). The results of the study, highlight the superior performance of the proposed MN-V2/CFO model compared to other tactics. The recommended strategy achieves a precision of 97.68 %, an F1-score of 86.22 %, a sensitivity of 80.12 %, and an accuracy of 97.32 %. The findings validate the potential of the proposed model in revolutionizing brain tumor diagnosis, contributing to better treatment strategies, and improving patient outcomes.