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{194379,
        author = {Mrs. P. Syed Ali Fathima Aasia and J. Gifty Ensalata Miraclin and I. Regina and C. Ulageswari},
        title = {Hybrid CNN–KNN Model for Automated Brain Tumor Detection from MRI Images},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {4097-4103},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194379},
        abstract = {Brain tumors are among the most life-threatening neurological disorders that require early and accurate diagnosis to improve patient survival rates. Magnetic Resonance Imaging (MRI) plays a significant role in detecting abnormalities in brain tissues due to its high resolution and detailed visualization of soft tissues. However, manual examination of MRI scans by radiologists is time-consuming and prone to human error. Therefore, automated computer-aided diagnostic systems have gained increasing attention in medical image analysis. This paper proposes an automated brain tumor detection system using deep learning and machine learning techniques. 
The proposed approach utilizes a Convolutional Neural Network (CNN) for deep feature extraction from MRI images and a K-Nearest Neighbor (KNN) classifier for tumor classification. The system consists of several stages including image preprocessing, segmentation, feature extraction, and classification. Preprocessing techniques such as noise removal, normalization, and contrast enhancement are applied to improve image quality. Statistical and deep features are extracted from the segmented tumor region. The extracted features are then classified into tumor and non-tumor categories using the KNN algorithm. Experimental results demonstrate that the proposed CNN-KNN hybrid model improves classification accuracy and provides reliable tumor detection. The proposed system can assist medical professionals in early diagnosis and reduce the workload of radiologists.},
        keywords = {Brain Tumor Detection, MRI Image Processing, Convolutional Neural Network, K-Nearest Neighbor, Deep Feature Extraction, Medical Image Analysis.},
        month = {March},
        }