Implementation of Deep Learning-Based YOLOv8 for Brain Tumor Detection in MRI Images
DOI:
https://doi.org/10.30741/jid.v4i2.1955Keywords:
Brain Tumor, Computer Vision, Deep Learning, Object Detection, YOLOv8Abstract
Brain tumors are a condition with a high mortality rate that requires accurate early detection to support the medical diagnostic process. The goal of this project is to create a model that uses the You Only Look Once version 8 nano (YOLOv8n) algorithm to identify and locate brain cancers in Magnetic Resonance Imaging (MRI) scans and to evaluate its effectiveness using actual clinical data. This study employs an experimental method with a quantitative approach through the following stages: dataset collection, bounding box annotation, image preprocessing, data augmentation, model training, performance evaluation, and implementation in a simple web application. The dataset consists of 5,015 MRI images, comprising 5,000 public data points and 15 hospital clinical data points as external test data. Model evaluation was conducted using the precision, recall, mAP@50, and mAP@50–95 metrics. The YOLOv8n model's precision was 96.99%, recall was 94.37%, mAP@50 was 97.75%, and mAP@50–95 was 72.01%, according to the results. Testing on external data showed that the model was capable of detecting tumors in images that had not been previously trained on. These results indicate that YOLOv8n has the potential to be developed as an artificial intelligence-based early diagnosis support system for brain MRI images.
References
Abu-Srhan, A., Almallahi, I., Abushariah, M. A. M., Mahafza, W., & Al-Kadi, O. S. (2021). Paired-unpaired Unsupervised Attention Guided GAN with transfer learning for bidirectional brain MR-CT synthesis. Computers in Biology and Medicine, 136. https://doi.org/10.1016/j.compbiomed.2021.104763
Almalki, Y. E., Din, A. I., Ramzan, M., Irfan, M., Aamir, K. M., Almalki, A., Alotaibi, S., Alaglan, G., Alshamrani, H. A., & Rahman, S. (2022). Deep Learning Models for Classification of Dental Diseases Using Orthopantomography X-ray OPG Images. Sensors, 22(19). https://doi.org/10.3390/s22197370
Almufareh, M. F., Imran, M., Khan, A., Humayun, M., & Asim, M. (2024). Automated Brain Tumor Segmentation and Classification in MRI Using YOLO-Based Deep Learning. IEEE Access, 12, 16189–16207. https://doi.org/10.1109/ACCESS.2024.3359418
Chen, A., Lin, D., & Gao, Q. (2024). Enhancing brain tumor detection in MRI images using YOLO-NeuroBoost model. Frontiers in Neurology, 15. https://doi.org/10.3389/fneur.2024.1445882
Desmarescaux, M., Kaddah, W., Alfalou, A., & Deconninck, J. C. (2025). A Review: One-Shot Object Detection Methods for Conditional Detection of Retail and Warehouse Products. Neural Processing Letters, 57(2). https://doi.org/10.1007/s11063-025-11742-0
Kadyrov, O., & Batyrgaliyev, A. (2025). Multi-level Spam Protection Architecture: Integrating Rules, Blacklists, and Machine Learning Techniques. Computing & Engineering, 3, 11–22. https://doi.org/10.51301/ce.2025.i2.03
Kang, S., Hu, Z., Liu, L., Zhang, K., & Cao, Z. (2025). Object Detection YOLO Algorithms and Their Industrial Applications: Overview and Comparative Analysis. In Electronics (Switzerland) (Vol. 14, Number 6). Multidisciplinary Digital Publishing Institute (MDPI). https://doi.org/10.3390/electronics14061104
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
Schlosser, T., Friedrich, M., Meyer, T., Kowerko, D., & Professorship, J. (n.d.). A Consolidated Overview of Evaluation and Performance Metrics for Machine Learning and Computer Vision.
Yang, T., Lu, X., Yang, L., Yang, M., Chen, J., & Zhao, H. (2024). Application of MRI image segmentation algorithm for brain tumors based on improved YOLO. Frontiers in Neuroscience, 18. https://doi.org/10.3389/fnins.2024.1510175
Zhang, Z., Qu, Y., Wang, T., Rao, Y., Jiang, D., Li, S., & Wang, Y. (2024). An Improved YOLOv8n Used for Fish Detection in Natural Water Environments. Animals, 14(14). https://doi.org/10.3390/ani14142022
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
