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{184596,
        author = {Akshay S.M and Adarsh G.P and Shreyas B gowda and Skanda S.P and Mrs.Hemalatha B M},
        title = {Brain Tumor Detection Using Convolutional Neural Network},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {2917-2923},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184596},
        abstract = {Man, brain tumors are no joke they’re still one of the top reasons people die from cancer, all over the globe. Pretty grim, honestly. Early and precise detection plays a vital role in improving treatment outcomes and survival rates. Traditional methods of diagnosis, which rely on manual examination of brain scans, are often time-consuming, depend heavily on expert knowledge, and may lead to errors. With the rise of artificial intelligence (AI) and deep learning, new opportunities have emerged to assist doctors by providing faster, more reliable, and consistent diagnostic support.
This research presents a detailed study on the use of deep learning, particularly Convolutional Neural Networks (CNNs), for detecting brain tumors. The work focuses on the VGG16 model, a widely used CNN architecture, to classify tumors using brain CT scan images. The dataset employed consists of thousands of CT scans that were carefully pre- processed to enhance image clarity and extract meaningful features. The VGG16 model, originally trained on the large- scale ImageNet dataset, was fine-tuned for this specific medical application.
So, VGG16 basically crushed it nailed crazy high accuracy, sensitivity, all that jazz when it came to telling tumors apart from non-tumors. Blew those old-school machine learning methods outta the water, honestly. Makes you wonder why anyone still bothers with the classics. The point is, deep learning isn’t just a buzzword; it actually cuts down on those “oops” moments humans make and speeds up the whole diagnosis thing.
But hold on, there’s more to it than just the numbers. This study pokes at the bigger picture, like, what happens if hospitals actually roll out this deep learning stuff for real? Kinda wild to think about how that could shake up the way doctors work.},
        keywords = {U-Net Architecture, Glioma, Tumor Segmentation, Brain Tumor Classification, Transfer Learning, Medical Image Analysis, Vision Transformers (ViT), Generative Adversarial Networks (GANs), Federated Learning, Explainable AI (XAI), Hybrid Deep Learning Models, 3D CNN, Medical Data Augmentation, AI in Healthcare, Tumor Localization, Model Generalization, Residual Networks, Data Annotation Challenges, Ethical AI, Lightweight Models, Clinical Deployment.},
        month = {September},
        }