Comparative Evaluation of Lightweight CNN and YOLOv8 Models for Brain Tumor Detection in Resource-Constrained Settings
DOI:
https://doi.org/10.31436/ijpcc.v12i1.639Keywords:
deep learning, CNN, YOLO, Brain tumor detectionAbstract
Brain tumor detection is essential for timely diagnosis, early intervention, and effective treatment planning. With advancements in artificial intelligence (AI), deep learning methods have emerged as powerful tools in medical imaging, offering automated, consistent, and efficient detection of brain abnormalities. However, achieving clinically reliable performance requires models that can accurately differentiate between tumor and non-tumor cases. This paper investigates and compares the performance of two deep learning models which are a lightweight Convolutional Neural Network (CNN) and the You Only Look Once (YOLO) YOLOv8 model for brain tumor classification in resource-constrained setting. Both models were trained and evaluated using the BR35H dataset, which comprises 3,000 MRI scans categorized into tumor and non-tumor classes. The performance of the models are evaluated using accuracy, precision, recall, F1-score as well as inference time supplemented by confusion matrix, ROC analysis and Grad-CAM visualizations to assess class-wise prediction performance. The experimental results indicate that YOLOv8 demonstrated high predictions across both tumor and non-tumor categories. YOLOv8 outperformed the CNN, achieving an accuracy of 0.998, precision of 0.997, recall of 1.00, and an F1-score of 0.998. However, only a minimal difference was observed in the inference time per image between YOLOv8 and the CNN, with YOLOv8 being slower by just 10.6 ms. Finally, the results demonstrate YOLOv8’s robustness and reliability for early tumor detection, a critical factor in preventing diagnostic delays. The findings further highlight YOLOv8’s suitability for integration into clinical decision-support systems, particularly in resource-constrained environments where accurate and fast automated diagnosis can significantly enhance patient care.
References
N. M. Ramli and N. R. Mohd Zain, “The Growing Problem of Radiologist Shortage: Malaysia’s Perspective,” Korean J. Radiol., vol. 24, no. 10, pp. 936–937, 2023, doi: 10.3348/kjr.2023.0742.
S. Fong et al., “Education Research?: Training of Neurologists in South East Asian Countries,” vol. 0, no. 1, pp. 1–11, 2025, doi: 10.1212/NE9.0000000000200201.
O. J. P. Odong, M. Abo-Zahhad, and M. Abdelwahab, “An integrated deep convolutional neural networks framework for the automatic segmentation and grading of glioma tumors using multimodal MRI scans,” Discov. Appl. Sci., vol. 7, no. 8, 2025, doi: 10.1007/s42452-025-06968-5.
L. H. da Cruz, R. R. Batista, and C. C. Rangel, “MR imaging evaluation of posttreatment changes in brain neoplasms,” in Functional Imaging in Oncology: Clinical Applications - Volume 2, 2014, pp. 603–640. doi: 10.1007/978-3-642-40582-2_2.
A. K. Bhagat and D. Vekariya, “Computational Intelligence approach to improve the Classification accuracy of Brain Tumor Detection,” in Proceedings of 5th International Conference on Contemporary Computing and Informatics, IC3I 2022, 2022, pp. 659–664. doi: 10.1109/IC3I56241.2022.10073470.
M. P. Jeyaraj, M. S. Kumar, P. Jeyaraj M, and S. Kumar M, “Automated Brain Tumor Segmentation using Hybrid YOLO and SAM,” Curr. Med. IMAGING, vol. 21, 2025, doi: 10.2174/0115734056392711250718201911 WE - Science Citation Index Expanded (SCI-EXPANDED).
A. Ashar, V. Sabhani, and D. P. Bavirisetti, “Classification of Magnetic Resonance Imaging (MRI) Scans for Brain Tumor Using Improved EfficientNet Architecture and Transfer Learning,” in 2022 International Conference on Data Science, Agents and Artificial Intelligence, ICDSAAI 2022, 2022. doi: 10.1109/ICDSAAI55433.2022.10028839.
S. Margasagayan and N. Nageswaran, “Investigations of Deep Learning Algorithms for Identification of Brain Tumors,” SRM Valliammai Engineering College, Department of Medical Electronics, Kattankulathur, India: Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/ICCCSMD63546.2024.11015215.
S. N. Appe, G. Arulselvi, and G. N. Balaji, “Enhancing brain cancer detection and localization using Yolov8 object detection: A deep learning approach,” in Machine Learning and Generative AI in Smart Healthcare, 2024, pp. 261–280. doi: 10.4018/979-8-3693-3719-6.ch013.
S. Roy, S. Sen, R. Mehera, R. K. Pal, and S. K. Bandyopadhyay, “Brain Tumor Detection: A Comparative Study Among Fast Object Detection Methods,” in Lecture Notes in Networks and Systems, 2021, pp. 179–196. doi: 10.1007/978-981-16-4294-4_12.
M. Z. Khan, F. U. Zaman, P. Bhatti, A. A. Khan, S. A. Sultan, and S. Dua Bhatti, “A Comparative Analysis of Deep Learning Architectures for Efficient Brain Tumor Detection,” in 2024 International Conference on Sustainable Technology and Engineering, i-COSTE 2024, 2024. doi: 10.1109/i-COSTE63786.2024.11024836.
M. Sajjad, S. Khan, K. Muhammad, W. Wu, A. Ullah, and S. W. Baik, “Multi-grade brain tumor classification using deep CNN with extensive data augmentation,” J. Comput. Sci., vol. 30, pp. 174–182, 2019.
S. Deepak and P. M. Ameer, “Brain tumor classification using deep CNN features via transfer learning,” Comput. Biol. Med., vol. 111, p. 103345, 2019, doi: 10.1016/j.compbiomed.2019.103345.
D. Reyes and J. Sánchez, “Performance of convolutional neural networks for the classification of brain tumors using magnetic resonance imaging,” Heliyon, vol. 10, no. 3, p. e25468, 2024, doi: 10.1016/j.heliyon.2024.e25468.
F. Muftic, M. Kadunic, A. Musinbegovic, A. A. Almisreb, and H. Ja’afar, “Deep learning for magnetic resonance imaging brain tumor detection: evaluating ResNet, EfficientNet, and VGG-19,” Int. J. Electr. Comput. Eng., vol. 14, no. 6, pp. 6360–6372, 2024, doi: 10.11591/ijece.v14i6.pp6360-6372.
S. Kulkarni, P. A. Bhosale, and S. Das, “Using CNN for brain tumor diagnosis: An overview,” in Future of AI in Biomedicine and Biotechnology, 2024, pp. 104–124. doi: 10.4018/979-8-3693-3629-8.ch006.
P. K. Parhi, S. Mohanty, A. Mohanty, and P. K. Patra, “Deep Learning Techniques to Detect Brain Tumors Using the EfficientNet-B0 CNN Architecture,” in Artificial Intelligence in Oncology: Cancer Diagnosis and Treatment, Medical Imaging, and Personalized Medicine, 2025, pp. 115–126. doi: 10.1007/978-3-031-94302-7_8.
P. Kataria, A. Dogra, M. Gupta, T. Sharma, and B. Goyal, “Trends in DNN Model based Classification and Segmentation of Brain Tumor Detection,” Open Neuroimag. J., vol. 16, 2023, doi: 10.2174/18744400-v16-230405-2022-3.
N. Verma and V. K. Bohat, “EfficientNet-based deep learning approach for early detection of brain tumors,” Qual. Quant., 2025, doi: 10.1007/s11135-025-02499-8.
A. Y. Jaffar, “Combining Local and Global Feature Extraction for Brain Tumor Classification: A Vision Transformer and iResNet Hybrid Model,” Eng. Technol. Appl. Sci. Res., vol. 14, no. 5, pp. 17011–17018, 2024, doi: 10.48084/etasr.8271.
G. N. Sundar, D. Narmadha, N. A. Jerry, S. K. Thangavel, S. K. Shanmugam, and A. A. Ajibesin, “Brain Tumor Detection and Classification using Vision Transformer (ViT),” in 3rd International Conference on Automation, Computing and Renewable Systems, ICACRS 2024 - Proceedings, 2024, pp. 562–567. doi: 10.1109/ICACRS62842.2024.10841703.
X. Jia, E. Shkolyar, M. A. Laurie, O. Eminaga, J. C. Liao, and L. Xing, “Tumor detection under cystoscopy with transformer-augmented deep learning algorithm,” Phys. Med. Biol., vol. 68, no. 16, 2023, doi: 10.1088/1361-6560/ace499.
S. S. Mahanty, D. Muduli, A. Kumari, and S. K. Sharma, “Pretrained DeIT for Brain Tumor Classification: A Fine-Tuning Approach with Label Smoothing,” in 2024 15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024, 2024. doi: 10.1109/ICCCNT61001.2024.10725957.
C. Sankari, V. Jamuna, and A. R. Kavitha, “Hierarchical multi-scale vision transformer model for accurate detection and classification of brain tumors in MRI-based medical imaging,” Sci. Rep., vol. 15, no. 1, 2025, doi: 10.1038/s41598-025-23100-0.
S. Jraba, M. Elleuch, H. Ltifi, and M. Kherallah, “Enhanced Brain Tumor Detection Using Integrated CNN-ViT Framework: A Novel Approach for High-Precision Medical Imaging Analysis,” in 10th 2024 International Conference on Control, Decision and Information Technologies, CoDIT 2024, 2024, pp. 2120–2125. doi: 10.1109/CoDIT62066.2024.10708482.
M. N. I. Shanto, M. T. Mubtasim, S. V Rakshit, and M. A. Aman Ullah, “Enhanced Classification of Brain Tumors from MRI Scans Using a Hybrid CNN-Transformer Model,” M. S. Shah, Ed., Kennesaw State University, Department of Computer Science, Kennesaw, United States: Institute of Electrical and Electronics Engineers Inc., 2025. doi: 10.1109/QPAIN66474.2025.11171896.
H. Lin, J. Wang, Y. Guo, and L. Fang, “A Lightweight Brain Tumor Detection Network with Dynamic Inverted Residuals and Synergistic Attention,” in 2025 4th International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology, AIoTC 2025, 2025, pp. 185–191. doi: 10.1109/AIoTC66747.2025.11198723.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779–788.
J. Redmon and A. Farhadi, “YOLO9000: better, faster, stronger,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 7263–7271.
A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “Yolov4: Optimal speed and accuracy of object detection,” arXiv Prepr. arXiv2004.10934, 2020.
F. Ghufran, A. Kumar, A. Kumar, A. Kaushik, and S. Saxena, “Detection of Brain Tumors in MRI Images through Machine Learning, Deep Learning, Faster R-CNN & YOLOv5,” V. Sharma and J. Sinha, Eds., GNIT Group of Institutions, Department of Computer Science and Engineering, Noida, India: Institute of Electrical and Electronics Engineers Inc., 2024, pp. 754–759. doi: 10.1109/ICAC2N63387.2024.10895900.
C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023, pp. 7464–7475.
“Explore Ultralytics YOLOv8.” Accessed: Nov. 16, 2025. [Online]. Available: https://docs.ultralytics.com/models/yolov8/
A. P. Taradale and S. L. Kattimani, “Effective Segmentation and Classification of Brain Tumour MRI Images Using YOLOv8 Technique,” in 2024 International Conference on Innovation and Novelty in Engineering and Technology (INNOVA), IEEE, 2024, pp. 1–6.
O. Zougari et al., “Deep Learning-Based Brain Tumor Detection Using YOLOv8 on MRI Images,” in Lecture Notes in Networks and Systems, 2026, pp. 389–401. doi: 10.1007/978-3-032-01967-7_37.
S. Verma, A. Choudhury, P. Narad, and A. Sengupta, “Optimizing Brain Tumor Classification Using YOLOv8: A Comparative Study with CNN Architectures on MRI Scans,” in International Conference on Signal Processing and Communication, ICSC, 2025, pp. 500–505. doi: 10.1109/ICSC64553.2025.10968576.
K. Dhivya, U. Surya, and A. Devi, “Empowered Brain Tumor Detection Using Deep Learning Methodology,” in International Conference on Advancements in Power, Communication and Intelligent Systems, APCI 2024, 2024. doi: 10.1109/APCI61480.2024.10616431.
“Br35H: Brain Tumor Detection 2020, Kaggle, 2020.” [Online]. Available: https://www.kaggle.com/datasets/ahmedhamada0/brain-tumor-detection
M. Reza Keyvanpour and M. B. Shirzad, Machine learning techniques for agricultural image recognition. INC, 2022. doi: 10.1016/B978-0-323-90550-3.00011-4.
E. Casas, L. Ramos, E. Bendek, and F. Rivas-Echeverria, “Yolov5 vs. yolov8: Performance benchmarking in wildfire and smoke detection scenarios,” J. Image Graph., vol. 12, no. 2, pp. 127–136, 2024.
D. Garg, “A Deep Learning Approach for Face Detection using YOLO,” 2018 IEEE Punecon, pp. 1–4.
S. Arora and M. Sharma, “Deep Learning for Brain Tumor Classification from MRI Images,” in Proceedings of the IEEE International Conference Image Information Processing, The NorthCap University, Department of Computer Science and Engineering, Gurugram, India: Institute of Electrical and Electronics Engineers Inc., 2021, pp. 409–412. doi: 10.1109/ICIIP53038.2021.9702609.
S. Krishnapriya and Y. Karuna, “A deep learning model for the localization and extraction of brain tumors from MR images using YOLOv7 and grab cut algorithm,” Front. Oncol., vol. 14, 2024, doi: 10.3389/fonc.2024.1347363 WE - Science Citation Index Expanded (SCI-EXPANDED).
S. Iftikhar, N. Anjum, A. B. Siddiqui, M. Ur Rehman, and N. Ramzan, “Explainable CNN for brain tumor detection and classification through XAI based key features identification,” Brain Informatics, vol. 12, no. 1, 2025, doi: 10.1186/s40708-025-00257-y.
M. S. Mou et al., “Brain Tumor Detection on MRI Images Using a Combination of CNN and Ensemble Learning Approach,” M. B. Islam, M. E. Hamid, and S. Biswas, Eds., Rabindra Maitree University, Department of Computer Science and Engineering, Kushtia, Bangladesh: Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/ICRPSET64863.2024.10955888.
P. Venkateswarlu Reddy et al., “Implementation of Latest Deep Learning Techniques for Brain Tumor Identification from MRI Images,” in 2023 8th International Conference on Communication and Electronics Systems (ICCES), IEEE, 2023, pp. 1166–1171. doi: 10.1109/ICCES57224.2023.10192620.
H. Mzoughi, I. Njeh, M. BenSlima, N. Farhat, and C. Mhiri, “Vision transformers (ViT) and deep convolutional neural network (D-CNN)-based models for MRI brain primary tumors images multi-classification supported by explainable artificial intelligence (XAI),” Vis. Comput., vol. 41, no. 4, pp. 2123–2142, 2025, doi: 10.1007/s00371-024-03524-x.
S. Sarker, “Transfer Learning and Explainable AI for Brain Tumor Classification: A Study Using MRI Data from Bangladesh,” 2024 6th Int. Conf. Sustain. Technol. Ind. 5.0, STI 2024, vol. 0, pp. 1–6, 2024, doi: 10.1109/STI64222.2024.10951092.
A. M. J. Zubair Rahman et al., “Advanced AI-driven approach for enhanced brain tumor detection from MRI images utilizing EfficientNetB2 with equalization and homomorphic filtering,” BMC Med. Inform. Decis. Mak., vol. 24, no. 1, pp. 1–19, 2024, doi: 10.1186/s12911-024-02519-x.
R. Deebika and M. Sangeetha, “Optimized ResNet-50 Deep Learning Model for Highly Accurate Plant Disease Classification and Detection Efficiency,” in Proceedings of 6th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2025, 2025, pp. 47–52. doi: 10.1109/ICICV64824.2025.11085739.
W. H. M. Isa, M. A. Abdullah, M. A. M. Razman, A. P. P. A. Majeed, and I. M. Khairuddin, “Deep Learning Algorithms for Recognition of Badminton Strokes: A Study Using SDNN, RNN, and RNN-GRU Models with Off-Court Video Capture,” in Lecture Notes in Networks and Systems, 2024, pp. 53–60. doi: 10.1007/978-981-99-8498-5_5.
S. John and M. G. Jibukumar, “Lightweight Sequential CNN for Alzheimer’s Disease Progress Classification,” in 2024 Asian Conference on Intelligent Technologies, ACOIT 2024, 2024. doi: 10.1109/ACOIT62457.2024.10939666.
?. Ceran, M. Kaya, Y. Kaçmaz, A. E. Ergün, T. Çelikten, and A. Onan, “A Deep Learning Approach to Sentiment Classification: Insights from Product Review Analysis,” in Lecture Notes in Networks and Systems, 2025, pp. 37–44. doi: 10.1007/978-3-031-97992-7_5.
V. S. Threshika, P. Naiba Sree, P. R. Pravin, and S. Madhavi, “A Deep Learning Framework for the Classification of Indian Heritage Using Curated Datasets and CNN Models,” in Proceedings - 3rd International Conference on Advancement in Computation and Computer Technologies, InCACCT 2025, 2025, pp. 951–954. doi: 10.1109/InCACCT65424.2025.11011360.
A. Gholamy, V. Kreinovich, and O. Kosheleva, “Why 70/30 or 80/20 relation between training and testing sets: A pedagogical explanation,” 2018.
