A Review on Comparative Analysis of Machine Learning and Deep Learning Models for Brain Tumor Detection
Volume: 14 - Issue: 11 - Date: 03-11-2025
Approved ISSN: 2278-1412
Published Id: IJAECESTU468 | Page No.: 106-110
Author: Kajal Gour
Co- Author: Prof Swati Khanve,Prof Nitya Khare
Abstract:-Detecting and classifying brain tumors are some of the most important things to do in medical imaging
because they directly affect how doctors plan treatment and how long patients live. People have looked into a lot of
different ways to use machine learning (ML), including preprocessing methods like homomorphic filtering,
morphological operations, and normalisation. Then, to make classification more accurate, they use feature extraction
and feature selection. These methods can work very well, but they often need a lot of work to make the features and
hyperparameters work well together. On the other hand, deep learning (DL) models like Convolutional Neural
Networks (CNN), DenseNet, and VGG16 have shown that they can automatically learn hierarchical features from raw
MRI images. This greatly improves accuracy, robustness, and generalization across different datasets. This review
offers a comparative examination of ML and DL methodologies, emphasising their techniques, advantages, and
constraints in the classification of brain tumors. The study highlights the significance of preprocessing and feature
optimisation in machine learning, while demonstrating that deep learning architectures provide a more dependable and
scalable solution for clinical applications
Key Words:-Brain Tumor Classification, Machine Learning, Deep Learning, Preprocessing, Feature Selection, CNN, VGG16, DenseNet.
Area:-Engineering
Download Paper:
Preview This Article
