HYBRID DEEP LEARNING MODELS FOR BRAIN TUMOR DETECTION AND SEVERITY ASSESSMENT

A Nithya Rani; JIJI K KARUNAKARAN

doi:10.36948/ijfmr.2025.v07i02.40293

HYBRID DEEP LEARNING MODELS FOR BRAIN TUMOR DETECTION AND SEVERITY ASSESSMENT

Author(s)	Dr. Ms. A Nithya Rani, Ms. JIJI K KARUNAKARAN
Country	India
Abstract	Abstract— Brain tumor detection is crucial in medical imaging, significantly impacting treatment planning and patient outcomes. Traditional methods often struggle with the complex and heterogeneous nature of brain tumors. This paper introduces a novel hybrid deep learning approach, combining U-Net, ResNet- 101, Generative Adversarial Networks, and Vision Transformers to enhance diagnostic accuracy, model generalization, improve the detection and severity classification of brain tumors. By integrating these state-of-the-art models, the system aims to provide precise tumor segmentation, robust feature extraction, enhanced generalization through data augmentation, and a comprehensive severity assessment, addressing key challenges in brain tumor imaging. U-Net is employed for precise tumor segmentation, while ResNet-101 provides deep feature extraction. GANs augment the dataset, improving robustness and generalization, and ViT captures long-range dependencies in images. These models are integrated using an ensemble learning approach, optimized through a genetic algorithm to assign optimal weights to each model's predictions. The ensemble model effectively captures both global and local features, significantly improving classification accuracy, precision, recall, and score compared to individual models
Keywords	Brain Tumor, U-Net, ResNet-101, Generative Adversarial Networks
Field	Computer Applications
Published In	Volume 7, Issue 2, March-April 2025
Published On	2025-04-29
DOI	https://doi.org/10.36948/ijfmr.2025.v07i02.40293
Short DOI	https://doi.org/g9g74m

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 2 Cover Page Vol 7 Isu 1 Cover Page Vol 6 Isu 6

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

HYBRID DEEP LEARNING MODELS FOR BRAIN TUMOR DETECTION AND SEVERITY ASSESSMENT

Share this