Non-Invasive Glioma vs. Meningioma Discrimination on MRI: A Comparative Study of Baseline CNN, Transfer-Learned AlexNet and Custom FF-CNN Architectures
DOI:
https://doi.org/10.29304/jqcsm.2025.17.42578Keywords:
brain tumor classification;, magnetic resonance imaging (MRI);, deep learning; convolutional neural networks (CNN); transfer learning; AlexNet; FF-CNN;, glioma; meningioma; non-invasive diagnosis.Abstract
Brain tumoruzrds are a group of very aggressive and frequently fatal neurological diseases and early and accurate diagnosis are required for successful therapy and for increased patient survival. Traditional diagnostic methods, including histopathological examination using surgical biopsies, are the only gold standard tests for diagnosis, but are invasive, time-consuming, and risky—associated with a high risk of infection, hemorrhage and neurological complications. The emergence of machine learning, in particularly deep learning has provided an unprecedented non-invasive tumour detection/classification tools which has transformed the medical imaging analysis field.
Here we investigate and benchmark three deep learning architectures for classifying brain tumors on magnetic resonance images (MRI): a baseline CNN, a modified pre-trained AlexNet via transfer learning, and a custom FF-CNN tailored for our problem. The models were trained and tested on a curated Brain Tumor MRI dataset containing annotated images of two major tumour types: glioma and meningioma.
For CNN, AlexNet, FF-CNN, the classification accuracies were 97.1%, 98.6%, and 95.1%, respectively. The better performance of the AlexNet is due to its higher depth and its possibility to be used as a transfer learning model able to perform strong feature extraction on small medical datasets. Taken together, they demonstrate the substantial potential of DL methods for quick, accurate and non-invasive detection of brain tumors. Incorporating such technologies into clinical decision support systems can greatly improve radiological workflow efficiency, reduce diagnostic delay, and eventually improve the quality of patient care and prognostication.
Downloads
References
Louis, D. N., Perry, A., Reifenberger, G., Deimling, A. V., Figarella-Branger, D., Cavenee, W. K., Ohgaki, H., Wiestler, O. D., Kleihues, P., & Ellison, D. W. (2016). The 2016 World Health Organization classification of tumors of the central nervous system: A summary. Acta Neuropathologica, 131(6), 803–820. https://doi.org/10.1007/s00401-016-1545-1
Tandel, G. S., Biswas, M., Kakde, O. G., Tiwari, A., Suri, H. S., Turk, M., Laird, J. R., Asare, C. K., Ankrah, A. A., Khanna, N. N., & others. (2019). A review on a deep learning perspective in brain cancer classification. Cancers, 11(1), 111. https://doi.org/10.3390/cancers11010111
Anaraki, A. K., Ayati, M., & Kazemi, F. (2019). Magnetic resonance imaging-based brain tumor grades classification and grading via convolutional neural networks and genetic algorithms. Biocybernetics and Biomedical Engineering, 39(1), 63–74. https://doi.org/10.1016/j.bbe.2018.10.002
Srinivas, C., Prasad, K. S. N., Zakariah, M., Alothaibi, Y. A., Shaukat, K., Partibane, B., & Awal, H. (2021). Deep transfer learning approaches in performance analysis of brain tumor classification using MRI images. Journal of Medical Systems, 45(4), 82. https://doi.org/10.1007/s10916-021-01723-4
Visser, M., Müller, D. M. J., van Duijn, R. J. M., Ikram, M. A., Luider, T. M., Niessen, W. J., & Smits, M. (2019). Inter-rater agreement in glioma segmentations on longitudinal MRI. NeuroImage: Clinical, 22, 101727. https://doi.org/10.1016/j.nicl.2019.101727
Khan, H. A., Jue, W., Mushtaq, M., & Mushtaq, M. U. (2020). Brain tumor classification in MRI image using convolutional neural network. Mathematical Biosciences and Engineering, 17(5), 6203–6216. https://doi.org/10.3934/mbe.2020331
Halicek, M., Dormer, J. D., Little, J. V., Chen, A. Y., & Fei, B. (2020). Tumor detection of the thyroid and salivary glands using hyperspectral imaging and deep learning. Biomedical Optics Express, 11(3), 1383–1400. https://doi.org/10.1364/BOE.382126
Ahmad, I., Ullah, I., Khan, W. U., Rehman, A. U., Adrees, M. S., Saleem, M. Q., Cheikhrouhou, O., Hamam, H., & Shafiq, M. (2021). Efficient algorithms for e-healthcare to solve multi-object fusion detection problem. Journal of Healthcare Engineering, 2021, Article 8846416. https://doi.org/10.1155/2021/8846416
Raza, A., Ayub, H., Khan, J. A., Ahmad, I., Salama, A. S., Daradkeh, Y. I., Javeed, D., Rehman, A. U., & Hamam, H. (2022). A hybrid deep learning based approach for brain tumor classification. Electronics, 11(7), 1146. https://doi.org/10.3390/electronics11071146
El-Dahshan, E.-S. A., Hosny, T., & Salem, A.-B. M. (n.d.). Hybrid intelligent techniques for MRI brain images classification. Unpublished manuscript.
Nawaz, S. A., Khan, D. M., & Qadri, S. (n.d.). Brain tumor classification based on hybrid optimized multi-features analysis using magnetic resonance imaging dataset. Unpublished manuscript.
Badža, M. M., & Barjaktarović, M. Č. (2020). Classification of brain tumors from MRI images using a convolutional neural network. Applied Sciences, 10(6), 1999. https://doi.org/10.3390/app10061999
Assam, M., Kanwal, H., Farooq, U., Shah, S. K., Mehmood, A., & Choi, G. S. (n.d.). An efficient classification of MRI brain images. Unpublished manuscript.
] Masood, M., Nazir, T., Nawaz, M., Mehmood, A., Rashid, J., Kwon, H.-Y., Mahmood, T., & Hussain, A. (n.d.). A novel deep learning method for recognition and classification of brain tumors from MRI images. Unpublished manuscript.
Shamshad, N., Sarwar, D., Almogren, A., Saleem, K., Munawar, A., Rehman, A. U., & Bharany, S. (n.d.). Enhancing brain tumor classification by a comprehensive study on transfer learning techniques and model efficiency using MRI datasets. Unpublished manuscript.
Ul Haq, E., Jianjun, H., Li, K., Ul Haq, H., & Zhang, T. (n.d.). An MRI-based deep learning approach for efficient classification of brain tumors. Unpublished manuscript.
Wang, S., Zhang, Y., Dong, Z., Du, S., Ji, G., Yan, J., Yang, J., Wang, Q., Feng, C., & Phillips, P. (n.d.). Feed-forward neural network optimized by hybridization of PSO and ABC for abnormal brain detection. Unpublished manuscript.
Hasan, A. M., Jalab, H. A., Meziane, F., Kahtan, H., & Al-Ahmad, A. S. (n.d.). Combining deep and handcrafted image features for MRI brain scan classification. Unpublished manuscript.
Perez, H., Tah, J. H. M., & Mosavi, A. (2019). Deep learning for detecting building defects using convolutional neural networks. Sensors, 19(16), 3556. https://doi.org/10.3390/s19163556
Chelghoum, R., Ikhlef, A., Hameurlaine, A., & Jacquir, S. (2020). Transfer learning using convolutional neural network architectures for brain tumor classification from MRI images. In IFIP International Conference on Artificial Intelligence Applications and Innovations (pp. 189–200). Springer. https://doi.org/10.1007/978-3-030-49161-1_16
Natha, S., Ghosal, P., Nandanwar, L., & others. (n.d.). Multi-model ensemble SETL_BMRI with AlexNet and VGG19 feature extractors for brain tumor classification. Unpublished manuscript.
Sachdeva, S., Kumar, D., Vardhan, S., & Mittal, A. (2025). Optimized deep learning for brain tumor detection: A hybrid CNN framework. Scientific Reports, 15, 04591. https://doi.org/10.1038/s41598-025-04591-0
Badža, M. M., & Barjaktarović, M. Č. (2020). Classification of brain tumors from MRI images using a convolutional neural network. Applied Sciences, 10(6), 1999. https://doi.org/10.3390/app10061999
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Bahaa Salih Mandeel, Diyaa Kareem Abd-Alhmza, Waad Saad Hindil, Manar Raad Abdalhassan, Muntadher adnan waheed
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
