A multi-stage semi-supervised learning approach to spine image segmentation
Spine segmentation in computed tomography (CT) images is critical for automatic analysis, especially when focusing on varied spinal regions. Despite having comprehensive annotations for normal vertebrae, the current dataset does not encompass fracture data, posing challenges for predictive modeli...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis-Master by Coursework |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/174682 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-174682 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1746822024-04-12T15:46:37Z A multi-stage semi-supervised learning approach to spine image segmentation Pan, Ruixiang Lin Zhiping School of Electrical and Electronic Engineering EZPLin@ntu.edu.sg Engineering Spine segmentation Unet Semi-supervised learning Fracture 2.5D Multi-stage Spine segmentation in computed tomography (CT) images is critical for automatic analysis, especially when focusing on varied spinal regions. Despite having comprehensive annotations for normal vertebrae, the current dataset does not encompass fracture data, posing challenges for predictive modeling. This research introduces a multi-stage 2.5D Unet-based semi-supervised learning methodology that utilizes both labeled and unlabeled datasets. The objective is to not only diminish the manual annotation workload but also to create a model proficient in processing fracture data without specific fracture dataset labeling. Due to the similarity between the vertebrae, precise segmentation is difficult, so considering a pipeline mimicking the clinical steps in examination of vertebral segmentation benefits the understanding of the vertebral bone condition by utilizing the cascade framework. The cumulative knowledge not only ensures a solid foundation for subsequent stages, but also promotes explanainability in detailed output. Considering the voluminous data in 3D CT images and GPU performance constraints, this study strategically employs 2D network training, further supplemented by 2.5D network training, to optimize model performance. Preliminary findings suggest that this approach significantly improves the model's ability to segment spine regions, especially in environments with limited equipment capabilities. Further evaluation is required to understand its full potential in various scenarios, including the presence of fractures. Master's degree 2024-04-08T00:05:36Z 2024-04-08T00:05:36Z 2023 Thesis-Master by Coursework Pan, R. (2023). A multi-stage semi-supervised learning approach to spine image segmentation. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/174682 https://hdl.handle.net/10356/174682 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 Spine segmentation Unet Semi-supervised learning Fracture 2.5D Multi-stage |
spellingShingle |
Engineering Spine segmentation Unet Semi-supervised learning Fracture 2.5D Multi-stage Pan, Ruixiang A multi-stage semi-supervised learning approach to spine image segmentation |
description |
Spine segmentation in computed tomography (CT) images is critical for automatic
analysis, especially when focusing on varied spinal regions. Despite having
comprehensive annotations for normal vertebrae, the current dataset does not
encompass fracture data, posing challenges for predictive modeling. This research
introduces a multi-stage 2.5D Unet-based semi-supervised learning methodology that
utilizes both labeled and unlabeled datasets. The objective is to not only diminish the
manual annotation workload but also to create a model proficient in processing
fracture data without specific fracture dataset labeling. Due to the similarity between
the vertebrae, precise segmentation is difficult, so considering a pipeline mimicking
the clinical steps in examination of vertebral segmentation benefits the understanding
of the vertebral bone condition by utilizing the cascade framework. The cumulative
knowledge not only ensures a solid foundation for subsequent stages, but also
promotes explanainability in detailed output. Considering the voluminous data in 3D
CT images and GPU performance constraints, this study strategically employs 2D
network training, further supplemented by 2.5D network training, to optimize model
performance. Preliminary findings suggest that this approach significantly improves
the model's ability to segment spine regions, especially in environments with limited
equipment capabilities. Further evaluation is required to understand its full potential
in various scenarios, including the presence of fractures. |
author2 |
Lin Zhiping |
author_facet |
Lin Zhiping Pan, Ruixiang |
format |
Thesis-Master by Coursework |
author |
Pan, Ruixiang |
author_sort |
Pan, Ruixiang |
title |
A multi-stage semi-supervised learning approach to spine image segmentation |
title_short |
A multi-stage semi-supervised learning approach to spine image segmentation |
title_full |
A multi-stage semi-supervised learning approach to spine image segmentation |
title_fullStr |
A multi-stage semi-supervised learning approach to spine image segmentation |
title_full_unstemmed |
A multi-stage semi-supervised learning approach to spine image segmentation |
title_sort |
multi-stage semi-supervised learning approach to spine image segmentation |
publisher |
Nanyang Technological University |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/174682 |
_version_ |
1800916133143904256 |