Deep Learning-Based Multi-Class Brain Tumor Classification from MRI Images Using DenseNet121 & OpenCV
DOI:
https://doi.org/10.69996/jsihs.2026007Keywords:
Deep Learning, Brain Tumor Classification, MRI, DenseNet121, OpenCVAbstract
Brain tumors are among the most life-threatening neurological conditions. Early detection through medical imaging plays a critical role in improving patient outcomes, but manual analysis of MRI scans is time-intensive and subject to human error. This project addressesthat problem by building a desktop application that can automatically classify brain MRI images into four categories: Glioma, Meningioma, Pituitary tumor, and No Tumor. The classification model is based on DenseNet121, a deep convolutional neural network architecture known for its dense connectivity pattern that improves gradient flow and feature reuse across layers. The model was trained on a labeled dataset containing thousands of MRI images and achieved an overall accuracy of 83% on a held-out test set of more than 1,300 images. Among the individual classes, No Tumor detection achieves the highest accuracy at 93%, followed by Pituitary at 88%, Glioma at 83%, and Meningioma at 65%. Once trained, the Keras model was exported to the ONNX format, which allows it to run through OpenCV's DNN module without requiring Tensor Flow or any GPU-specific libraries at runtime. This makes the application significantly lighter and more portable than typical deep learning deployments.
References
[1] G. Huang, Z. Liu, L. Van Der Maaten and K.Q. Weinberger, “Densely Connected Convolutional Networks,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4700–4708, 2017.
[2] K. Vinay Kumar, Sumanaswini Palakurthy, Sri Harsha Balijadaddanala, Sharmila Reddy Pappula, and Anil Kumar Lavudya, “Early Detection and Diagnosis of Oral Cancer Using Deep Neural Network”, JCAI, vol. 2, no. 2, pp. 22–34, 2024.
[3] G. Bradski and A. Kaehler, “Learning OpenCV: Computer Vision with the OpenCV Library,” O'Reilly Media, 2008.
[4] Swapna Saturi, Rafia Adiba, I. Yeshwanth Reddy, Md.Arsalan Shareef, and D.Prathyush, “Advanced MRI-Based Alzheimer’s Disease Classification with Hybrid Convolutional Neural Networks”, JCAI, vol. 3, no. 1, pp. 31–39, 2025
[5] ONNX Community. (2019). ONNX: Open Neural Network Exchange Format. Available at:https://onnx.ai
[6] G. Litjens, T. Kooi, B.E. Bejnordi, A.A.A. Setio, F. Ciompi et al., “A Survey on Deep Learning in Medical Image Analysis,” Medical Image Analysis, vol.42, pp.60–88, 2017.
[7] J. Canny, “A Computational Approach to Edge Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI, vol.8, no.6, pp.679–698, 1986.
[8] M. Tan and Q. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” Proceedings of the 36th International Conference on Machine Learning (ICML), pp.6105–6114, 2019.
[9] K. He, X. Zhang, S. Ren and J. Sun, “Deep Residual Learning for Image Recognition,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.770–778, 2016.
[10] K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for LargeScale Image Recognition,” arXiv preprint arXiv:1409.1556, 2014.
[11] S. Pereira, A. Pinto, V. Alves and C.A. Silva, “Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images,” IEEE Transactions on Medical Imaging, vol.35, no.5, pp.1240–1251, 2016.
[12] B.H. Menze, A. Jakab, S. Bauer, J. Kalpathy-Cramer, K. Farahani et al., “The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS),” IEEE Transactions on Medical Imaging, vol.34, no.10, pp.1993–2024, 2014.
[13] I. Goodfellow, Y. Bengio and A. Courville, “Deep Learning,” MIT Press, 2016.
[14] Brain Tumor MRI Dataset MasoudNickparvar. Available on Kaggle:https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset
[15] Rekha Gangula and Dayakar Thalla, “Machine Learning in Predicting Alzheimer’s Disease: Exploring Applications and Advancements”, JCAI, vol. 2, no. 1, pp. 1–7, 2024
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Sensors, IoT & Health Sciences (JSIHS,ISSN: 2584-2560)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Fringe Global Scientific Press publishes all the papers under a Creative Commons Attribution-Non-Commercial 4.0 International (CC BY-NC 4.0) (https://creativecommons.org/licenses/by-nc/4.0/) license. Authors have the liberty to replicate and distribute their work. Authors have the ability to use either the whole or a portion of their piece in compilations or other publications that include their own work. Please see the licensing terms for more information on reusing the work.
