Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{171850,
        author = {Seetha Thanooja K and Ramamurthy Ketha and Pakruddin B},
        title = {Detection of Brain Tumours from MRI Images using Convolutional Neural Networks (CNNs)},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {8},
        pages = {1225-1229},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=171850},
        abstract = {A brain tumor is an abnormal growth of the brain or other surrounding cellular structures that impairs the normal functions of the brain. A benign tumor is a non-cancer causing one while the malignant one causes the uncontrollable spread of cell which is quite harmful for an individual. Headache, seizure, cognitive disability, or sensory or motor dysfunction are common symptoms of a brain tumor, typically depending on tumor size, location, and growth rate [1].
To diagnose the ailment and determine the size of the tumor, magnetic resonance imaging (MRI) or computed tomography (CT) scans are performed. Treatments can be surgical, radiotherapic, chemotherapeutic, or targeted therapies. While some of the lesions can be treated, others remain difficult due to their aggressive behavior or their location near critical brain structures, highlights the need for ongoing research into better diagnostic targets and therapeutic strategies [2].
In this paper we present an automated approach to detect brain tumors from MRI medical images that employs Convolution Neural Networks (CNN). The research deployed the MobileNet model as a feature extractor, while it is further fine-tuned with a custom classification layer that detects the presence of tumors. As such, it is easier to model with these processed data as there can be a training, validation and test set. We apply advanced augmentation methods to ensure diversity and quality of the training set [3]. The presented solution emphasizes the potential of automated brain tumor diagnosis being performed efficiently, accurately, and in an interpretable manner that contributes towards assisting clinicians in making the best decisions [4].},
        keywords = {},
        month = {January},
        }