This paper is published in Volume-10, Issue-1, 2024
Area
Brain Tumor Detection
Author
Nishant Kumar Singh, Dr. pushpneel verma
Org/Univ
Bhagwant University, Ajmer, Rajasthan, India
Pub. Date
22 February, 2024
Paper ID
V10I1-1187
Publisher
Keywords
Magnetic Resonance Image, Brain Tumor Segmentation, Deep Learning

Citationsacebook

IEEE
Nishant Kumar Singh, Dr. pushpneel verma. Analysis of Brain Tumor Detection and Segmentation Using Enhanced Deep Learning Algorithm Kernel CNN with M-SVM, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Nishant Kumar Singh, Dr. pushpneel verma (2024). Analysis of Brain Tumor Detection and Segmentation Using Enhanced Deep Learning Algorithm Kernel CNN with M-SVM. International Journal of Advance Research, Ideas and Innovations in Technology, 10(1) www.IJARIIT.com.

MLA
Nishant Kumar Singh, Dr. pushpneel verma. "Analysis of Brain Tumor Detection and Segmentation Using Enhanced Deep Learning Algorithm Kernel CNN with M-SVM." International Journal of Advance Research, Ideas and Innovations in Technology 10.1 (2024). www.IJARIIT.com.

Abstract

The prevalence of brain tumors necessitates the development of accurate and efficient diagnostic tools. This study presents an innovative approach to brain tumor detection and segmentation by leveraging an enhanced deep learning algorithm, specifically a Kernel Convolutional Neural Network (CNN) coupled with a Modified Support Vector Machine (M-SVM). The proposed method aims to improve both the sensitivity and specificity of brain tumor detection while enhancing the precision of tumor boundary delineation. The study begins with the preprocessing of magnetic resonance imaging (MRI) data, including normalization and noise reduction, to optimize the input for the subsequent deep learning model. The Kernel CNN is designed to extract hierarchical features from the MRI images, capturing intricate patterns indicative of tumor presence. The integration of a kernelized approach enhances the model's ability to discern complex relationships within the data, thereby improving overall detection accuracy. In addition to tumor detection, the study introduces a novel segmentation strategy based on a Modified Support Vector Machine (M-SVM). The M-SVM algorithm refines the results obtained from the CNN, facilitating precise delineation of tumor boundaries. This two-step approach not only enhances the accuracy of tumor localization but also provides valuable information for subsequent medical interventions. To evaluate the proposed methodology, extensive experiments are conducted using benchmark datasets, and the results are compared with existing state-of-the-art techniques. Quantitative metrics such as sensitivity, specificity, precision, and Dice coefficient are employed to assess the performance of the model. The findings demonstrate that the proposed Kernel CNN with M-SVM outperforms conventional methods, showcasing its efficacy in both tumor detection and segmentation tasks. In conclusion, this research presents a robust and advanced framework for brain tumor analysis, offering a promising avenue for accurate diagnosis and treatment planning. The synergy between deep learning and support vector machines, coupled with the innovative use of kernelization, underscores the potential of this approach in contributing to the ongoing efforts to improve brain tumor diagnostics and patient outcomes