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{186048,
        author = {Ms. Puttamma M S and Mr. Chiranjeevi M R},
        title = {Brain Tumor Detection and Classification Using Optimization and Transfer Learning Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {174-179},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186048},
        abstract = {All of the body's functions are coordinated by the brain. Tumors, which are abnormal growths of tissue, are well-known. Brain tumors are characterized by uncontrolled cell growth and proliferation, resulting in abnormal lumps of tissue. The tumors are classified into many types on the basis of their characteristics, origin, growth rate, and current stage of development. Traditional methods of tumor detection are often laborious, inaccurate, and unable to scale effectively for large datasets. Therefore, the autonomous detection of brain cancers using MRI is a critical aspect of computer- assisted diagnostics. This project focus on uses of machine learning (ML) algorithms are KNN, SVM, and CNN, along with a publicly available dataset, image feature extraction, data preprocessing techniques, and principal component analysis (PCA) to enhance accuracy and reduce diagnostic time. The goal is to propose algorithms that require minimal training time. Classification is essential in diagnosing and treating brain tumors; however, the variety of MR images complicates this process. In this study, we evaluate the effectiveness of popular classification algorithms on T1- weighted, T2-weighted, and FLAIR MR images. The project's focus is on a binary classification problem aimed at identifying anomalies in brain MR images. This technique involves three tiers: feature selection, feature extraction, and fusion, which are recommended for the brain image recognition models in the study. In this project, compare the model accuracy of the three proposed methodologies to detect the most effective approach. It applies on a real-world public dataset and have the potential to advance the development of more accurate methods for disease identification and classification.},
        keywords = {Deep learning, CNN, Brain MRI Image classification, image recognition, Matlab Software.},
        month = {October},
        }