Deep learning for corpus callosum segmentation

Corpus callosum (CC) has been proved to be a sensitive biomarker of some neurological diseases such as multiple sclerosis (MS) and Alzheimer’s, and magnetic resonance imaging (MRI) is currently the priority technique for quantitative diagnosis and analysis of corpus callosum, in which segmentation o...

Full description

Saved in:
Bibliographic Details
Main Author: Hua, Guokai
Other Authors: Wen Bihan
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/157187
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-157187
record_format dspace
spelling sg-ntu-dr.10356-1571872023-07-04T17:44:13Z Deep learning for corpus callosum segmentation Hua, Guokai Wen Bihan School of Electrical and Electronic Engineering bihan.wen@ntu.edu.sg Engineering::Electrical and electronic engineering Corpus callosum (CC) has been proved to be a sensitive biomarker of some neurological diseases such as multiple sclerosis (MS) and Alzheimer’s, and magnetic resonance imaging (MRI) is currently the priority technique for quantitative diagnosis and analysis of corpus callosum, in which segmentation of the CC from MRI is a vital step. During the past few years, various algorithms have been explored to fulfill the task of CC MRI segmentation. However, specific engineering knowledge and experience are still required to build such segmentation models. Furthermore, these algorithms tend to have a poor generalization ability. Therefore, a deep learning method is applied to develop a segmentation algorithm. In this dissertation, corpus callosum segmentation network (OpccNet), a CC MRI segmentation algorithm is developed, based on OpenCC, a public benchmark MRI dataset for assessing the CC segmentation algorithms. OpccNet and its extension Attention OpccNet, generated by adding attention gates to the OpccNet are trained and compared. They both produce an accurate and immediate segmentation of CC, providing an automatic segmentation of CC from MRI images with deep learning. Additionally, different augmentation methods are compared to discuss the importance of noisy data for building up a stable and reliable segmentation system in real medical applications. Master of Science (Computer Control and Automation) 2022-05-08T23:31:43Z 2022-05-08T23:31:43Z 2022 Thesis-Master by Coursework Hua, G. (2022). Deep learning for corpus callosum segmentation. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/157187 https://hdl.handle.net/10356/157187 en D-255-21221-02612 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
spellingShingle Engineering::Electrical and electronic engineering
Hua, Guokai
Deep learning for corpus callosum segmentation
description Corpus callosum (CC) has been proved to be a sensitive biomarker of some neurological diseases such as multiple sclerosis (MS) and Alzheimer’s, and magnetic resonance imaging (MRI) is currently the priority technique for quantitative diagnosis and analysis of corpus callosum, in which segmentation of the CC from MRI is a vital step. During the past few years, various algorithms have been explored to fulfill the task of CC MRI segmentation. However, specific engineering knowledge and experience are still required to build such segmentation models. Furthermore, these algorithms tend to have a poor generalization ability. Therefore, a deep learning method is applied to develop a segmentation algorithm. In this dissertation, corpus callosum segmentation network (OpccNet), a CC MRI segmentation algorithm is developed, based on OpenCC, a public benchmark MRI dataset for assessing the CC segmentation algorithms. OpccNet and its extension Attention OpccNet, generated by adding attention gates to the OpccNet are trained and compared. They both produce an accurate and immediate segmentation of CC, providing an automatic segmentation of CC from MRI images with deep learning. Additionally, different augmentation methods are compared to discuss the importance of noisy data for building up a stable and reliable segmentation system in real medical applications.
author2 Wen Bihan
author_facet Wen Bihan
Hua, Guokai
format Thesis-Master by Coursework
author Hua, Guokai
author_sort Hua, Guokai
title Deep learning for corpus callosum segmentation
title_short Deep learning for corpus callosum segmentation
title_full Deep learning for corpus callosum segmentation
title_fullStr Deep learning for corpus callosum segmentation
title_full_unstemmed Deep learning for corpus callosum segmentation
title_sort deep learning for corpus callosum segmentation
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/157187
_version_ 1772825223365656576