Home / Current Issue / Paper 1711921
Deep Learning-Based Multiclass Classification of Brain Tumors from MRI Images: A CNN Approach
Subject area: Science,Engineering and Technology · Area of research: Healthcare
DOI: https://doi.org/10.64388/IREV9I5-1711921
Abstract
Brain tumor classification using MRI scans is important for early diagnosis and clinical management. This study presents a deep learning-based approach using convolutional neural networks (CNNs) to automatically classify brain MRI images into four distinct categories: glioma, meningioma, pituitary tumor, and no tumor. The proposed methodology employs both custom CNN architectures and transfer learning to enhance performance. Experiments were conducted on a curated dataset comprising 3,500 labeled MRI images, ensuring balanced representation across all classes. Model performance was evaluated using standard metrics including accuracy, precision, recall, and F1-score. The results demonstrate an overall classification accuracy exceeding 90%, with robust performance across all tumor classes. This work illustrates the effectiveness of deep learning for multiclass brain tumor classification and underscores its potential as an efficient, reliable tool for aiding clinical decision-making.
Keywords
Brain Tumor Classification, MRI, Deep Learning, Convolutional Neural Networks, Multiclass Prediction, Transfer Learning, Medical Imaging, Glioma, Meningioma, Pituitary, Automatic Diagnosis
How to cite this paper
@article{1711921,
author = {Harshita Rajoria, Sneha Kachhap, Vinisha, Priya},
title = {Deep Learning-Based Multiclass Classification of Brain Tumors from MRI Images: A CNN Approach},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {5},
pages = {574-583},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1711921.pdf},
abstract = {Brain tumor classification using MRI scans is important for early diagnosis and clinical management. This study presents a deep learning-based approach using convolutional neural networks (CNNs) to automatically classify brain MRI images into four distinct categories: glioma, meningioma, pituitary tumor, and no tumor. The proposed methodology employs both custom CNN architectures and transfer learning to enhance performance. Experiments were conducted on a curated dataset comprising 3,500 labeled MRI images, ensuring balanced representation across all classes. Model performance was evaluated using standard metrics including accuracy, precision, recall, and F1-score. The results demonstrate an overall classification accuracy exceeding 90%, with robust performance across all tumor classes. This work illustrates the effectiveness of deep learning for multiclass brain tumor classification and underscores its potential as an efficient, reliable tool for aiding clinical decision-making.},
keywords = {Brain Tumor Classification, MRI, Deep Learning, Convolutional Neural Networks, Multiclass Prediction, Transfer Learning, Medical Imaging, Glioma, Meningioma, Pituitary, Automatic Diagnosis},
month = {November},
doi = {https://doi.org/10.64388/IREV9I5-1711921}
}