Oludele Adeleke is a Senior Lecturer in the Department of ICT & Cybersecurity, Faculty of Computing, University of Ibadan, Nigeria. He holds a Ph.D. in Computer Science from the University of Ibadan, an M.Tech. in Communication Physics from the Federal University of Technology, Akure, and a B.Sc. in Computer Science from Lagos State University. His research interests include cybersecurity, machine learning, artificial intelligence, network security, data communication, deep learning, and information systems. He has published research in refereed journals and conference proceedings on topics including machine learning, cybersecurity, telecommunications, healthcare prediction, artificial intelligence, and environmental data analysis. Dr. Adeleke has also received research support through TETFund grants, including serving as Principal Investigator for the establishment of a University of Ibadan Cyber Emergency Response Team (UI-CERT). He is a member of the Nigerian Computer Society and has undertaken international academic exchanges through the Erasmus+ programme.

 Enhanced Deep Learning Model for Automated Brain Tumor Detection in MRI Images using YOLO versions INTRODUCTION Brain tumor is a disease that requires early diagnosis to enhance patient survival and treatment outcomes. The traditional forms of diagnosis are time-consuming, subject to human misinterpretation and require the skills of radiologists because they are based on manual interpretation of Magnetic Resonance Imaging (MRI). The limitations can result in the slow appearance of the diagnosis and the decreased accuracy in determining the areas of the tumor. The incorporation of the systems of Artificial Intelligence (AI)-based systems is associated with the possibility to improve the speed, accuracy, and reliability of diagnoses. Nonetheless, it is not possible to ensure strong and accurate tumor detection in complex MRI images because of the changes in the size, shape, and intensity of tumor. AIM The aim of this study is to develop an hybridized YOLOv8 deep learning framework for automated detection and localization of brain tumors in MRI images. MATERIALS AND METHODS There were 2,618 MRI images in a dataset acquired through Roboflow, two classes, tumor and normal. The data was labeled using YOLO format and separated into training (1, 940 images), validation (323 images), and testing (355 images). The size of all images was reduced to 640 × 640 pixels. The hybrid model proposed is based on the basis of the YOLOv8m architecture, which is improved with preprocessing approaches like image normalization and noise reduction to enhance feature representation. The given model was trained with the help of optimized parameters i.e., 50 epochs, batch size 16, and a learning rate of 0.001, on a GPU. The metrics of performance were assessed with the standard object detection ones, such as Accuracy, Precision, Recall, F1-score, mAP@0.5, and mAP@0.5:0.95.  RESULTS The hybrid model proposed had a high detection performance: precision of 0.9537, recall of 0.9474, and F1-score of 0.9505. The model achieved mAP0.5:0.9727 and mAP0.5:0.7612, which portrays the high localization and classification performance. The findings suggest that the model is effective model in identifying tumor locations and distinguishing between tumor and normal brain tissues with a high level of accuracy. The confusion matrix also supports that there was little misclassification of classes indicating that the proposed approach is strong. CONCLUSION The hybrid YOLOv8 system has potentials of being an excellent tool in automated detection of brain tumors in MRI images. It can be used in supporting clinical decision making due to its high level of accuracy, reliability and generalizes across unknown data. This paper emphasizes the significance of AI-based solutions in medical imaging to enhance early diagnosis and patient outcomes. The work in the future will be centered on adding more complicated architectures and bigger datasets to further improve the performance of models. Keywords Deep Learning, Brain Tumor Detection, MRI Images, YOLOv8, Medical Image Analysis, Artificial Intelligence, Automated Diagnosis