Design Of Automated Computer Aided Classification Of Brain Tumor Using Deep Learning

Liow, Jia Geok (2018) Design Of Automated Computer Aided Classification Of Brain Tumor Using Deep Learning. Project Report. UTeM, Melaka, Malaysia. (Submitted)

Text (24 Pages) Design Of Automated Computer Aided Classification Of Brain Tumor Using Deep Learning.pdf - Submitted Version Download (562kB)

Abstract

In this recent years, health issues have inescapably become the center of attention from many researchers. A brain tumor is now a leading cause of death among medically certified deaths. Brain image diagnosis is manually examined by the neurologist. It is time-consuming and may lead to errors. The general idea of this project is to analyse the brain tumor based on the Magnetic Resonance Imaging (MRI) of medical images. The design of this system is aimed at classifying the MRI samples. The system uses computer-based procedures to classify the type of tumor to the malignant, benign or normal brain using Tensor flow in MRI images of different patients. A promising method to perform the design is through a deep learning process. Deep learning is currently a well-known and superior method in the pattern recognition field. The performance measure for detection would be false acceptance rate (FAR), Equal Error Rate (EER) and false rejection rate (FRR). A framework's FAR commonly is expressed as the proportion of the number of false acknowledgments partitioned by the quantity of distinguishing proof endeavors. A framework's FRR commonly is expressed as the proportion of the number of false dismissals separated by the number of ID endeavors. EER is a biometric security framework calculation used to foreordain the edge esteems for its false dismissal rate and its false acknowledgment rate. At the point when the rates are equivalent, the regular esteem is alluded to as the 'equivalent mistake rate'. The lower the EER esteem, the higher the precision of the biometric framework would be. The samples are already available coming from a standard database. A comparison will be done between different methods for classification of a brain tumor.

Actions (login required)

View Item