Deep learning approach to cervical segmentation from routine CT images

Recently, techniques for 3D medical image segmentation have become increas ingly sophisticated. Different types of Unet-based segmentation networks per form very well in tasks where the liver, blood vessels or brain are the seg mentation targets. Yet, compared to these holistic segmentation targe...

Full description

Saved in:
Bibliographic Details
Main Author: Duan, Yiming
Other Authors: Jiang Xudong
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/168606
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-168606
record_format dspace
spelling sg-ntu-dr.10356-1686062023-07-04T16:37:11Z Deep learning approach to cervical segmentation from routine CT images Duan, Yiming Jiang Xudong School of Electrical and Electronic Engineering A*STAR Institute of Material Research and Engineering EXDJiang@ntu.edu.sg Engineering::Electrical and electronic engineering Recently, techniques for 3D medical image segmentation have become increas ingly sophisticated. Different types of Unet-based segmentation networks per form very well in tasks where the liver, blood vessels or brain are the seg mentation targets. Yet, compared to these holistic segmentation targets, another equally important class of human tissues, the bone, has a more pronounced se quential character. Traditional 3D methods are unable to learn the exact position of bone joints due to the limitation of local similarity and numbers of param eters. To address the sequential and location-dependent nature of bone segmen tation information, the dissertation proposes a pre-training model for location information, and combines 2.5D image input and labeled multi-channel coding to semantically segment 3D cervical spine CT images. This method can accu rately extract the information of bone joint location of slices and incorporate it into image features in the form of channels, which can improve the accuracy of multiple bone joint segmentation and classification. The experimental results show that this approach achieves better segmentation results in the test set. Master of Science (Computer Control and Automation) 2023-06-08T08:55:39Z 2023-06-08T08:55:39Z 2023 Thesis-Master by Coursework Duan, Y. (2023). Deep learning approach to cervical segmentation from routine CT images. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/168606 https://hdl.handle.net/10356/168606 en 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
Duan, Yiming
Deep learning approach to cervical segmentation from routine CT images
description Recently, techniques for 3D medical image segmentation have become increas ingly sophisticated. Different types of Unet-based segmentation networks per form very well in tasks where the liver, blood vessels or brain are the seg mentation targets. Yet, compared to these holistic segmentation targets, another equally important class of human tissues, the bone, has a more pronounced se quential character. Traditional 3D methods are unable to learn the exact position of bone joints due to the limitation of local similarity and numbers of param eters. To address the sequential and location-dependent nature of bone segmen tation information, the dissertation proposes a pre-training model for location information, and combines 2.5D image input and labeled multi-channel coding to semantically segment 3D cervical spine CT images. This method can accu rately extract the information of bone joint location of slices and incorporate it into image features in the form of channels, which can improve the accuracy of multiple bone joint segmentation and classification. The experimental results show that this approach achieves better segmentation results in the test set.
author2 Jiang Xudong
author_facet Jiang Xudong
Duan, Yiming
format Thesis-Master by Coursework
author Duan, Yiming
author_sort Duan, Yiming
title Deep learning approach to cervical segmentation from routine CT images
title_short Deep learning approach to cervical segmentation from routine CT images
title_full Deep learning approach to cervical segmentation from routine CT images
title_fullStr Deep learning approach to cervical segmentation from routine CT images
title_full_unstemmed Deep learning approach to cervical segmentation from routine CT images
title_sort deep learning approach to cervical segmentation from routine ct images
publisher Nanyang Technological University
publishDate 2023
url https://hdl.handle.net/10356/168606
_version_ 1772829044303200256