Performance Analysis of Machine Learning Classifiers for Brain Tumor MR Images
Journal Title: Sir Syed University Reseacrh Journal of Engineering and Technology - Year 2018, Vol 8, Issue
Abstract
Brain cancer has remained one of the key causes of deaths in people of all ages. One way to survival amongst patients is to correctly diagnose cancer in its early stages. Recently machine learning has become a very important tool in medical image classification. Our approach is to examine and compare various machine learning classification algorithms that help in brain tumor classification of Magnetic Resonance (MR) images. We have compared Artificial Neural Network (ANN), K-nearest Neighbor (KNN), Decision Tree (DT), Support Vector Machine (SVM) and Naïve Bayes (NB) classifiers to determine the accuracy of each classifier and find the best amongst them for classification of cancerous and noncancerous brain MR images. We have used 86 MR images and extracted a large number of features for each image. Since the equal number of images, have been used thus there is no suspicion of results being biased. For our data set the most accurate results were provided by ANN. It was found that ANN provides better results for medium to large database of Brain MR Images.
Authors and Affiliations
Lubna Farhi, Razia Zia, Zain Anwar Ali
Keywords
Related Articles
- EP ID EP432889
- DOI -
- Views 160
- Downloads 0
Maximum Likelihood Decoder for Variable Length Codes
Variable Length Codes (VLC) are used to transfer same amount of digital information in relatively short period of time. In variable length coding, the characters with higher probability of occurrence are assigned shorter...
Deployment of Sensors to Optimize the Network Coverage Using Genetic Algorithm
Wireless Sensor Networks (WSNs) are commonly used in various pervasive applications. Wireless communication is the fastest growing segment of the communication industry that has captured attention of the media and imagin...
Tackling Demolition Waste – An en route to Sustainable Development
In Pakistan, construction and demolition waste (CDW) is generated in voluminous amount each year. CDW is widely ill-handled and ultimately fed to landfills causing harm to the already alarming environmental conditions. I...
RF Based Wireless Fire Security System for Hospitals
Wireless Fire Security System increases the secu-rity against fire as compared to conventional fire security systems. Conventional fire security systems are wired and they usually contain smoke detectors and control pane...
Fluid Dispenser Prototype: A Time Based Approach
In today's era when precise, accurate and time efficient systems are in great demand, automated techniques supersede manual practices. As a need of time, we introduce a wireless, automated, cost effective, yet reliable a...