Skip to content

Comparison of Brain Tumor MRI Detection with Neural Networks vs. Traditional Machine Learning Models

License

Notifications You must be signed in to change notification settings

AliZ786/COMP-478

Repository files navigation

Comparison of Brain Tumor MRI Detection with Neural Networks vs. Traditional Machine Learning Models

Dataset: https://www.kaggle.com/datasets/ahmedhamada0/brain-tumor-detection?resource=download
Authors: Mohammad Ali Zahir, Marwa Khalid

Abstract

Magnetic resonance imaging (MRI) is a widely-used medical imaging technology in the healthcare industry that produces high-resolution images, which can be utilized for disease classification purposes. One limitation of MRI is its inability to differentiate between cancerous tissue and fluids due to the intricate nature of the human brain. As a result, the images obtained through the MRI need to be categorized as abnormal or normal by utilizing various image processing techniques. The purpose of this research study is to compare the effectiveness of three neural network models, namely ConvNet CNN, Multi-Layer Perceptron, ResNet50 and three traditional machine learning models – K-nearest neighbors, Support Vector Machines, and Random Forest in detecting brain tumors in MRI images.

About

Comparison of Brain Tumor MRI Detection with Neural Networks vs. Traditional Machine Learning Models

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published