Development of automated 3D knee bone segmentation with inhomogeneity correction for deformable approach in magnetic resonance imaging

Dongyoun Kim, Jiyoung Lee, Joon Shik Yoon, Kwang Jae Lee, Kwanghee Won

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Osteoarthritis(OA) analysis is one of essential task in health issues. 3D Magnetic Resonance Imaging (MRI) segmentation plays an important role in a highly accurate knee osteoarthritis diagnosis. 3D segmentation knee MRI is challenging task because of complex knee structure, low contrast, noise, and bias field inherent in MRI. Deformable model is one of the most intensively model-based approaches for computer-aided medical image analysis. However, most of deformable models require prior shape and training processing for segmentation [1]. In this paper, we propose a deformable model-based approach with automatic initial point selection to segment knee bones from 3D MRI containing intensity inhomogeneity. This approach does not require manual initial point selection and training phase so that large amount of human resource and time can be saved. Preprocessing performs inhomogeneity correction and extracts voxels of interest in order to prevent leakage the boundary of target objective. The proposed deformable approach is devised by modifying boundary information of a hybrid deformable model [2] to morphological operation. Automated selection of initial point is motivated by 3D multi-edge overlapping technique in the [3] method. Experimental results are demonstrated 3D model comparing with other recent methods of knee bone segmentation [27,28] and 2D slices on both synthetic image with inhomogeneity correction or not. Our approach compared against a hand-segmented ground truth from experts. we achieved an average dice similarity coefficient of 0.951, sensitivity of 0.927, specificity of 0.999, average symmetric surface distance of 1.16 mm, and root mean square symmetric surface of 2.01mm. The result shows that our proposed approach is useful performing simple and accurate bone segmentation for diagnosis.

Original languageEnglish
Title of host publicationProceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018
PublisherAssociation for Computing Machinery, Inc
Pages285-290
Number of pages6
ISBN (Electronic)9781450358859
DOIs
Publication statusPublished - 2018 Oct 9
Event2018 Conference Research in Adaptive and Convergent Systems, RACS 2018 - Honolulu, United States
Duration: 2018 Oct 92018 Oct 12

Other

Other2018 Conference Research in Adaptive and Convergent Systems, RACS 2018
CountryUnited States
CityHonolulu
Period18/10/918/10/12

Fingerprint

Magnetic resonance
Bone
Imaging techniques
Image analysis
Health
Personnel
Magnetic Resonance Imaging
Processing

Keywords

  • 3D deformable approach
  • Automated initial point
  • Bias correction
  • Knee 3D MRI
  • Knee bone segmentation

ASJC Scopus subject areas

  • Computer Science(all)
  • Control and Systems Engineering

Cite this

Kim, D., Lee, J., Yoon, J. S., Lee, K. J., & Won, K. (2018). Development of automated 3D knee bone segmentation with inhomogeneity correction for deformable approach in magnetic resonance imaging. In Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018 (pp. 285-290). Association for Computing Machinery, Inc. https://doi.org/10.1145/3264746.3264776

Development of automated 3D knee bone segmentation with inhomogeneity correction for deformable approach in magnetic resonance imaging. / Kim, Dongyoun; Lee, Jiyoung; Yoon, Joon Shik; Lee, Kwang Jae; Won, Kwanghee.

Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018. Association for Computing Machinery, Inc, 2018. p. 285-290.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, D, Lee, J, Yoon, JS, Lee, KJ & Won, K 2018, Development of automated 3D knee bone segmentation with inhomogeneity correction for deformable approach in magnetic resonance imaging. in Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018. Association for Computing Machinery, Inc, pp. 285-290, 2018 Conference Research in Adaptive and Convergent Systems, RACS 2018, Honolulu, United States, 18/10/9. https://doi.org/10.1145/3264746.3264776
Kim D, Lee J, Yoon JS, Lee KJ, Won K. Development of automated 3D knee bone segmentation with inhomogeneity correction for deformable approach in magnetic resonance imaging. In Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018. Association for Computing Machinery, Inc. 2018. p. 285-290 https://doi.org/10.1145/3264746.3264776
Kim, Dongyoun ; Lee, Jiyoung ; Yoon, Joon Shik ; Lee, Kwang Jae ; Won, Kwanghee. / Development of automated 3D knee bone segmentation with inhomogeneity correction for deformable approach in magnetic resonance imaging. Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018. Association for Computing Machinery, Inc, 2018. pp. 285-290
@inproceedings{9046d546936a4e9b800e1040d5b8d0fb,
title = "Development of automated 3D knee bone segmentation with inhomogeneity correction for deformable approach in magnetic resonance imaging",
abstract = "Osteoarthritis(OA) analysis is one of essential task in health issues. 3D Magnetic Resonance Imaging (MRI) segmentation plays an important role in a highly accurate knee osteoarthritis diagnosis. 3D segmentation knee MRI is challenging task because of complex knee structure, low contrast, noise, and bias field inherent in MRI. Deformable model is one of the most intensively model-based approaches for computer-aided medical image analysis. However, most of deformable models require prior shape and training processing for segmentation [1]. In this paper, we propose a deformable model-based approach with automatic initial point selection to segment knee bones from 3D MRI containing intensity inhomogeneity. This approach does not require manual initial point selection and training phase so that large amount of human resource and time can be saved. Preprocessing performs inhomogeneity correction and extracts voxels of interest in order to prevent leakage the boundary of target objective. The proposed deformable approach is devised by modifying boundary information of a hybrid deformable model [2] to morphological operation. Automated selection of initial point is motivated by 3D multi-edge overlapping technique in the [3] method. Experimental results are demonstrated 3D model comparing with other recent methods of knee bone segmentation [27,28] and 2D slices on both synthetic image with inhomogeneity correction or not. Our approach compared against a hand-segmented ground truth from experts. we achieved an average dice similarity coefficient of 0.951, sensitivity of 0.927, specificity of 0.999, average symmetric surface distance of 1.16 mm, and root mean square symmetric surface of 2.01mm. The result shows that our proposed approach is useful performing simple and accurate bone segmentation for diagnosis.",
keywords = "3D deformable approach, Automated initial point, Bias correction, Knee 3D MRI, Knee bone segmentation",
author = "Dongyoun Kim and Jiyoung Lee and Yoon, {Joon Shik} and Lee, {Kwang Jae} and Kwanghee Won",
year = "2018",
month = "10",
day = "9",
doi = "10.1145/3264746.3264776",
language = "English",
pages = "285--290",
booktitle = "Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Development of automated 3D knee bone segmentation with inhomogeneity correction for deformable approach in magnetic resonance imaging

AU - Kim, Dongyoun

AU - Lee, Jiyoung

AU - Yoon, Joon Shik

AU - Lee, Kwang Jae

AU - Won, Kwanghee

PY - 2018/10/9

Y1 - 2018/10/9

N2 - Osteoarthritis(OA) analysis is one of essential task in health issues. 3D Magnetic Resonance Imaging (MRI) segmentation plays an important role in a highly accurate knee osteoarthritis diagnosis. 3D segmentation knee MRI is challenging task because of complex knee structure, low contrast, noise, and bias field inherent in MRI. Deformable model is one of the most intensively model-based approaches for computer-aided medical image analysis. However, most of deformable models require prior shape and training processing for segmentation [1]. In this paper, we propose a deformable model-based approach with automatic initial point selection to segment knee bones from 3D MRI containing intensity inhomogeneity. This approach does not require manual initial point selection and training phase so that large amount of human resource and time can be saved. Preprocessing performs inhomogeneity correction and extracts voxels of interest in order to prevent leakage the boundary of target objective. The proposed deformable approach is devised by modifying boundary information of a hybrid deformable model [2] to morphological operation. Automated selection of initial point is motivated by 3D multi-edge overlapping technique in the [3] method. Experimental results are demonstrated 3D model comparing with other recent methods of knee bone segmentation [27,28] and 2D slices on both synthetic image with inhomogeneity correction or not. Our approach compared against a hand-segmented ground truth from experts. we achieved an average dice similarity coefficient of 0.951, sensitivity of 0.927, specificity of 0.999, average symmetric surface distance of 1.16 mm, and root mean square symmetric surface of 2.01mm. The result shows that our proposed approach is useful performing simple and accurate bone segmentation for diagnosis.

AB - Osteoarthritis(OA) analysis is one of essential task in health issues. 3D Magnetic Resonance Imaging (MRI) segmentation plays an important role in a highly accurate knee osteoarthritis diagnosis. 3D segmentation knee MRI is challenging task because of complex knee structure, low contrast, noise, and bias field inherent in MRI. Deformable model is one of the most intensively model-based approaches for computer-aided medical image analysis. However, most of deformable models require prior shape and training processing for segmentation [1]. In this paper, we propose a deformable model-based approach with automatic initial point selection to segment knee bones from 3D MRI containing intensity inhomogeneity. This approach does not require manual initial point selection and training phase so that large amount of human resource and time can be saved. Preprocessing performs inhomogeneity correction and extracts voxels of interest in order to prevent leakage the boundary of target objective. The proposed deformable approach is devised by modifying boundary information of a hybrid deformable model [2] to morphological operation. Automated selection of initial point is motivated by 3D multi-edge overlapping technique in the [3] method. Experimental results are demonstrated 3D model comparing with other recent methods of knee bone segmentation [27,28] and 2D slices on both synthetic image with inhomogeneity correction or not. Our approach compared against a hand-segmented ground truth from experts. we achieved an average dice similarity coefficient of 0.951, sensitivity of 0.927, specificity of 0.999, average symmetric surface distance of 1.16 mm, and root mean square symmetric surface of 2.01mm. The result shows that our proposed approach is useful performing simple and accurate bone segmentation for diagnosis.

KW - 3D deformable approach

KW - Automated initial point

KW - Bias correction

KW - Knee 3D MRI

KW - Knee bone segmentation

UR - http://www.scopus.com/inward/record.url?scp=85056850844&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056850844&partnerID=8YFLogxK

U2 - 10.1145/3264746.3264776

DO - 10.1145/3264746.3264776

M3 - Conference contribution

AN - SCOPUS:85056850844

SP - 285

EP - 290

BT - Proceedings of the 2018 Research in Adaptive and Convergent Systems, RACS 2018

PB - Association for Computing Machinery, Inc

ER -