Robust Initialization of Active Shape Models for Lung Segmentation in CT Scans: A Feature-Based Atlas Approach

Model-based segmentation methods have the advantage of incorporating a priori shape information into the segmentation process but suffer from the drawback that the model must be initialized sufficiently close to the target. We propose a novel approach for initializing an active shape model (ASM) and...

Full description

Saved in:
Bibliographic Details
Main Authors: Gurman Gill, Matthew Toews, Reinhard R. Beichel
Format: Article
Language:English
Published: Wiley 2014-01-01
Series:International Journal of Biomedical Imaging
Online Access:http://dx.doi.org/10.1155/2014/479154
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850110269315874816
author Gurman Gill
Matthew Toews
Reinhard R. Beichel
author_facet Gurman Gill
Matthew Toews
Reinhard R. Beichel
author_sort Gurman Gill
collection DOAJ
description Model-based segmentation methods have the advantage of incorporating a priori shape information into the segmentation process but suffer from the drawback that the model must be initialized sufficiently close to the target. We propose a novel approach for initializing an active shape model (ASM) and apply it to 3D lung segmentation in CT scans. Our method constructs an atlas consisting of a set of representative lung features and an average lung shape. The ASM pose parameters are found by transforming the average lung shape based on an affine transform computed from matching features between the new image and representative lung features. Our evaluation on a diverse set of 190 images showed an average dice coefficient of 0.746 ± 0.068 for initialization and 0.974 ± 0.017 for subsequent segmentation, based on an independent reference standard. The mean absolute surface distance error was 0.948 ± 1.537 mm. The initialization as well as segmentation results showed a statistically significant improvement compared to four other approaches. The proposed initialization method can be generalized to other applications employing ASM-based segmentation.
format Article
id doaj-art-45891e23638747fc878148e7df4cd9ec
institution OA Journals
issn 1687-4188
1687-4196
language English
publishDate 2014-01-01
publisher Wiley
record_format Article
series International Journal of Biomedical Imaging
spelling doaj-art-45891e23638747fc878148e7df4cd9ec2025-08-20T02:37:52ZengWileyInternational Journal of Biomedical Imaging1687-41881687-41962014-01-01201410.1155/2014/479154479154Robust Initialization of Active Shape Models for Lung Segmentation in CT Scans: A Feature-Based Atlas ApproachGurman Gill0Matthew Toews1Reinhard R. Beichel2Department of Electrical and Computer Engineering, The University of Iowa, Iowa City, IA 52242, USABrigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USADepartment of Electrical and Computer Engineering, The University of Iowa, Iowa City, IA 52242, USAModel-based segmentation methods have the advantage of incorporating a priori shape information into the segmentation process but suffer from the drawback that the model must be initialized sufficiently close to the target. We propose a novel approach for initializing an active shape model (ASM) and apply it to 3D lung segmentation in CT scans. Our method constructs an atlas consisting of a set of representative lung features and an average lung shape. The ASM pose parameters are found by transforming the average lung shape based on an affine transform computed from matching features between the new image and representative lung features. Our evaluation on a diverse set of 190 images showed an average dice coefficient of 0.746 ± 0.068 for initialization and 0.974 ± 0.017 for subsequent segmentation, based on an independent reference standard. The mean absolute surface distance error was 0.948 ± 1.537 mm. The initialization as well as segmentation results showed a statistically significant improvement compared to four other approaches. The proposed initialization method can be generalized to other applications employing ASM-based segmentation.http://dx.doi.org/10.1155/2014/479154
spellingShingle Gurman Gill
Matthew Toews
Reinhard R. Beichel
Robust Initialization of Active Shape Models for Lung Segmentation in CT Scans: A Feature-Based Atlas Approach
International Journal of Biomedical Imaging
title Robust Initialization of Active Shape Models for Lung Segmentation in CT Scans: A Feature-Based Atlas Approach
title_full Robust Initialization of Active Shape Models for Lung Segmentation in CT Scans: A Feature-Based Atlas Approach
title_fullStr Robust Initialization of Active Shape Models for Lung Segmentation in CT Scans: A Feature-Based Atlas Approach
title_full_unstemmed Robust Initialization of Active Shape Models for Lung Segmentation in CT Scans: A Feature-Based Atlas Approach
title_short Robust Initialization of Active Shape Models for Lung Segmentation in CT Scans: A Feature-Based Atlas Approach
title_sort robust initialization of active shape models for lung segmentation in ct scans a feature based atlas approach
url http://dx.doi.org/10.1155/2014/479154
work_keys_str_mv AT gurmangill robustinitializationofactiveshapemodelsforlungsegmentationinctscansafeaturebasedatlasapproach
AT matthewtoews robustinitializationofactiveshapemodelsforlungsegmentationinctscansafeaturebasedatlasapproach
AT reinhardrbeichel robustinitializationofactiveshapemodelsforlungsegmentationinctscansafeaturebasedatlasapproach