Multi-surface, multi-object optimal image segmentation: application in 3D knee joint imaged by MR
A novel method called LOGISMOS - Layered Optimal Graph Image Segmentation of Multiple Objects and Surfaces - for simultaneous segmentation of multiple interacting surfaces belonging to multiple interacting objects is reported. The approach is based on representation of the multiple inter-relationshi...
Main Author: | |
---|---|
Other Authors: | |
Format: | Others |
Language: | English |
Published: |
University of Iowa
2010
|
Subjects: | |
Online Access: | https://ir.uiowa.edu/etd/767 https://ir.uiowa.edu/cgi/viewcontent.cgi?article=1952&context=etd |
id |
ndltd-uiowa.edu-oai-ir.uiowa.edu-etd-1952 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-uiowa.edu-oai-ir.uiowa.edu-etd-19522019-10-13T04:26:55Z Multi-surface, multi-object optimal image segmentation: application in 3D knee joint imaged by MR Yin, Yin A novel method called LOGISMOS - Layered Optimal Graph Image Segmentation of Multiple Objects and Surfaces - for simultaneous segmentation of multiple interacting surfaces belonging to multiple interacting objects is reported. The approach is based on representation of the multiple inter-relationships in a single n-dimensional graph, followed by graph optimization that yields a globally optimal solution. Three major contributions for LOGISMOS are made and illustrated in this thesis: 1) multi-object multi-surface optimal surface detection graph design, 2) implementation of a novel and reliable cross-object surface mapping technique and 3) pattern recognition-based graph cost design. The LOGISMOS method's utility and performance are demonstrated on a knee joint bone and cartilage segmentation task. Although trained on only a small number of nine example images, this system achieved good performance as judged by Dice Similarity Coefficients (DSC) using a leave-one-out test, with DSC values of 0.84+-0.04, 0.80+-0.04 and 0.80+-0.04 for the femoral, tibial, and patellar cartilage regions, respectively. These are excellent values of DSC considering the narrow-sheet character of the cartilage regions. Similarly, very low signed mean cartilage thickness errors were observed when compared to manually-traced independent standard in 60 randomly selected 3D MR image datasets from the Osteoarthritis Initiative database - 0.11+-0.24, 0.05+-0.23, and 0.03+-0.17 mm for the femoral, tibial, and patellar cartilage thickness, respectively. The average signed surface positioning error for the 6 detected surfaces ranged from 0.04+-0.12 mm to 0.16+-0.22 mm, while the unsigned surface positioning error ranged from 0.22+-0.07 mm to 0.53+-0.14 mm. The reported LOGISMOS framework provides robust and accurate segmentation of the knee joint bone and cartilage surfaces of the femur, tibia, and patella. As a general segmentation tool, the developed framework can be applied to a broad range of multi-object multi-surface segmentation problems. Following the LOGISMOS-based cartilage segmentation, a fully automated meniscus segmentation system was build using pattern recognition technique. The leave-one-out test for the nine training images showed very good mean DSC 0.80+-0.04. The signed and unsigned surface positioning error when compared to manually-traced independent standard in the 60 randomly selected 3D MR image datasets is 0.65+-0.20 and 0.68+-0.20 mm respectively. 2010-07-01T07:00:00Z dissertation application/pdf https://ir.uiowa.edu/etd/767 https://ir.uiowa.edu/cgi/viewcontent.cgi?article=1952&context=etd Copyright 2010 Yin Yin Theses and Dissertations eng University of IowaSonka, Milan Electrical and Computer Engineering |
collection |
NDLTD |
language |
English |
format |
Others
|
sources |
NDLTD |
topic |
Electrical and Computer Engineering |
spellingShingle |
Electrical and Computer Engineering Yin, Yin Multi-surface, multi-object optimal image segmentation: application in 3D knee joint imaged by MR |
description |
A novel method called LOGISMOS - Layered Optimal Graph Image Segmentation of Multiple Objects and Surfaces - for simultaneous segmentation of multiple interacting surfaces belonging to multiple interacting objects is reported. The approach is based on representation of the multiple inter-relationships in a single n-dimensional graph, followed by graph optimization that yields a globally optimal solution.
Three major contributions for LOGISMOS are made and illustrated in this thesis: 1) multi-object multi-surface optimal surface detection graph design, 2) implementation of a novel and reliable cross-object surface mapping technique and 3) pattern recognition-based graph cost design.
The LOGISMOS method's utility and performance are demonstrated on a knee joint bone and cartilage segmentation task. Although trained on only a small number of nine example images, this system achieved good performance as judged by Dice Similarity Coefficients (DSC) using a leave-one-out test, with DSC values of 0.84+-0.04, 0.80+-0.04 and 0.80+-0.04 for the femoral, tibial, and patellar cartilage regions, respectively. These are excellent values of DSC considering the narrow-sheet character of the cartilage regions. Similarly, very low signed mean cartilage thickness errors were observed when compared to manually-traced independent standard in 60 randomly selected 3D MR image datasets from the Osteoarthritis Initiative database - 0.11+-0.24, 0.05+-0.23, and 0.03+-0.17 mm for the femoral, tibial, and patellar cartilage thickness, respectively. The average signed surface positioning error for the 6 detected surfaces ranged from 0.04+-0.12 mm to 0.16+-0.22 mm, while the unsigned surface positioning error ranged from 0.22+-0.07 mm to 0.53+-0.14 mm.
The reported LOGISMOS framework provides robust and accurate segmentation of the knee joint bone and cartilage surfaces of the femur, tibia, and patella. As a general segmentation tool, the developed framework can be applied to a broad range of multi-object multi-surface segmentation problems.
Following the LOGISMOS-based cartilage segmentation, a fully automated meniscus segmentation system was build using pattern recognition technique. The leave-one-out test for the nine training images showed very good mean DSC 0.80+-0.04. The signed and unsigned surface positioning error when compared to manually-traced independent standard in the 60 randomly selected 3D MR image datasets is 0.65+-0.20 and 0.68+-0.20 mm respectively. |
author2 |
Sonka, Milan |
author_facet |
Sonka, Milan Yin, Yin |
author |
Yin, Yin |
author_sort |
Yin, Yin |
title |
Multi-surface, multi-object optimal image segmentation: application in 3D knee joint imaged by MR |
title_short |
Multi-surface, multi-object optimal image segmentation: application in 3D knee joint imaged by MR |
title_full |
Multi-surface, multi-object optimal image segmentation: application in 3D knee joint imaged by MR |
title_fullStr |
Multi-surface, multi-object optimal image segmentation: application in 3D knee joint imaged by MR |
title_full_unstemmed |
Multi-surface, multi-object optimal image segmentation: application in 3D knee joint imaged by MR |
title_sort |
multi-surface, multi-object optimal image segmentation: application in 3d knee joint imaged by mr |
publisher |
University of Iowa |
publishDate |
2010 |
url |
https://ir.uiowa.edu/etd/767 https://ir.uiowa.edu/cgi/viewcontent.cgi?article=1952&context=etd |
work_keys_str_mv |
AT yinyin multisurfacemultiobjectoptimalimagesegmentationapplicationin3dkneejointimagedbymr |
_version_ |
1719264265040297984 |