Brain Magnetic Resonance Image Segmentation by Deep Convolutional Neural Networks: A Survey

PhD Qualifying Examination


Title: "Brain Magnetic Resonance Image Segmentation by Deep Convolutional 
Neural Networks: A Survey"

by

Miss Pei WANG


Abstract:

Quantitative analysis of brain magnetic resonance(MR) images is routine 
for diagnosing many neurological diseases, surgical planning, lesion 
quantification and brain tumor detection, which relies on accurate 
segmentation of structures of interest. In recent years, deep 
convolutional neural networks (CNNs) have shown record-shattering 
performance in various computer vision tasks, such as visual object 
recognition, detection and segmentation. These methods have also been 
utilized in medical image analysis domain for tumor segmentation, 
anatomical segmentation and classification. We present a literature review 
of CNN-based segmentation techniques for brain MR images, focusing on the 
architectures, pre-processing, data-preparation and post-processing 
strategies. The primary goal of this study is to report how different CNN 
architectures have evolved, and examining the pros and cons of the 
state-of-the-art models. Besides, this survey is intended to be a detailed 
reference of the research activity in deep CNN for brain MR images.


Date:			Wednesday, 27 June 2018

Time:                  	10:00am - 12:00nooon

Venue:                  Room 5560
                         Lifts 27/28

Committee Members:	Prof. Albert Chung (Supervisor)
 			Prof. Chiew-Lan Tai (Chairperson)
 			Prof. Long Quan
 			Dr. Pedro Sander


**** ALL are Welcome ****