Brain tumors are a deadly form of malignant neoplasms that pose a significant danger to patients’ health and life. This study aims to improve the diagnostic efficiency and precision of brain tumors by utilizing the YOLOv8m deep learning model for automatic detection of medical imaging. High-quality datasets from the Kaggle platform are employed in this study, comprising axial, coronal, and sagittal MRI images for brain tumor detection. The model undergoes 200 epochs of training and testing, with performance enhancement achieved via hyperparameter optimization and data augmentation techniques. During the experiments, the YOLOv8m model shows remarkable detection performance, achieving [email protected] of 95% and [email protected]:0.95 of 64.6%. The precision achieved is 95%, with recall at 89%. Additionally, the bounding box regression loss decreases from 3.0 to 0.5 throughout the training process, and the validation loss stabilizes at 1.4, suggesting substantial optimization in object localization and classification tasks, with no overfitting observed. The results of this study show that the YOLOv8m model can efficiently and accurately perform automatic detection of brain tumor regions, providing reliable technical support for clinical diagnosis.

Qingrong Duan, Peipei Ji. Research on Medical Imaging Detection of Brain Tumors Based on YOLOv8m Algorithm. Academic Journal of Computing & Information Science (2025), Vol. 8, Issue 4: 98-105. https://doi.org/10.25236/AJCIS.2025.080412.

[1] Sung Hyuna;Ferlay Jacques;Siegel Rebecca L.;Laversanne Mathieu;Soerjomataram Isabelle;Jemal Ahmedin;Bray Freddie.Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries[J].CA: A Cancer Journal for Clinicians, 2021(3):209-249. 

[2] Wu Wei, Zhao Liang. Brain tumor detection algorithm based on similarity model for magnetic resonance imaging [J]. Journal of Huazhong University of Science and Technology (Natural Science Edition), 2013, 41(10): 41-44. DOI: 10.13245/j.hust.2013.10.020.

[3] Zhou Chulin, Chen Jingdong, Wang Xinyu, et al. Brain tumor detection application based on improved antenna array confocal imaging algorithm [J]. Computer and Digital Engineering, 2021, 49(10): 1978-1982+2016.

[4] Miao Yang, Zhang Shuo, Chen Jun, et al. Review of medical image analysis for hypopharyngeal cancer based on convolutional neural networks [J]. Journal of Beijing University of Technology, 2024, 50(07): 883-896.

[5] Liang Hong, Qiu Dingqian, Ding Shiyu, et al. Detection of abnormal teeth and restoration X-ray images based on improved YOLOv8 [J/OL]. Chinese Laser, 1-18 [2024-12-22]. http://kns.cnki.net/kcms/detail/31.1339.TN.20241209.1115.036.html.

[6] Wang Bo, Feng Xupeng, Liu Lijun, et al. Lung CT image nodule detection research based on improved YOLO algorithm [J]. Beijing Biomedical Engineering, 2020, 39(06): 615-621.

[7] Lin Bingjie, Wang Meiyun. Research status and development prospects of deep learning in medical imaging [J]. Journal of Shandong University (Medical Edition), 2023, 61(12): 21-29.

[8] Wang Guoming, Jia Daiwang. Optimization of small target detection model based on YOLOv8 [J/OL]. Computer Engineering, 1-10 [2024-12-22]. https://doi.org/10.19678/j.issn.1000-3428.0070027.

[9] He Luhao, Zhou Yongzhang. Application research of directional bounding box target detection in tailing pond recognition based on YOLOv8-obb model [J/OL]. Earth Science Frontiers, 1-20 [2024-12-22]. https://doi.org/10.13745/j.esf.sf.2024.11.3.

[10] Liu Ruiming, Chen Lune, Xu Chunrong, et al. Fabric seam detection algorithm based on improved YOLOv8 [J/OL]. Electronic Measurement Technology, 1-10 [2025-01-03]. http://kns.cnki.net/kcms/detail/11.2175.TN.20241226.1653.040.html.

[11] Quan Wenjun, Luo Hongtao. Underwater target detection algorithm based on improved YOLOv8M [J/OL]. Computer Technology and Development, 1-8 [2025-01-03]. https://doi.org/10.20165/j.cnki.ISSN1673-629X.2024.0272.

[12] Xiang Lei, Jiang Wenbo. Research on urban driving road obstacle detection algorithm based on improved YOLOv8 [J/OL]. Electronic Measurement Technology, 1-11 [2024-12-22]. http://kns.cnki.net/kcms/detail/11.2175.TN.20241220.1359.027.html.

[13] Li Hongda, Yang Nan, Yao Dongyan, et al. Knee osteoarthritis detection classification based on improved YOLOv8 algorithm [J/OL]. Journal of Nanjing University of Information Science and Technology, 1-15 [2025-01-03]. https://doi.org/10.13878/j.cnki.jnuist.20241018003.

[14] Xiao Junfeng, Ding Peng. Automatic diagnosis algorithm for knee osteoarthritis based on improved YOLOv8s [J]. Automation and Information Engineering, 2024, 45(06): 29-35.

[15] Roberts, D., & Collaborator. (2021). Brain tumor object detection datasets [Data set]. Kaggle. https://www.kaggle.com/datasets/davidbroberts/brain-tumor-object-detection-datasets.