Automated bone segmentation from dental CBCT images using patch-based sparse representation and convex optimization

Li Wang, Ken Chung Chen, Yaozong Gao, Feng Shi, Shu Liao, Gang Li, Steve G F Shen, Jin Yan, Philip K M Lee, Ben Chow, Nancy X. Liu, James J. Xia, Dinggang Shen

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

Purpose: Cone-beam computed tomography (CBCT) is an increasingly utilized imaging modality for the diagnosis and treatment planning of the patients with craniomaxillofacial (CMF) deformities. Accurate segmentation of CBCT image is an essential step to generate three-dimensional (3D) models for the diagnosis and treatment planning of the patients with CMF deformities. However, due to the poor image quality, including very low signal-to-noise ratio and the widespread image artifacts such as noise, beam hardening, and inhomogeneity, it is challenging to segment the CBCT images. In this paper, the authors present a new automatic segmentation method to address these problems. Methods: To segment CBCT images, the authors propose a new method for fully automated CBCT segmentation by using patch-based sparse representation to (1) segment bony structures from the soft tissues and (2) further separate the mandible from the maxilla. Specifically, a region-specific registration strategy is first proposed to warp all the atlases to the current testing subject and then a sparse-based label propagation strategy is employed to estimate a patient-specific atlas from all aligned atlases. Finally, the patient-specific atlas is integrated into amaximum a posteriori probability-based convex segmentation framework for accurate segmentation. Results: The proposed method has been evaluated on a dataset with 15 CBCT images. The effectiveness of the proposed region-specific registration strategy and patient-specific atlas has been validated by comparing with the traditional registration strategy and population-based atlas. The experimental results show that the proposed method achieves the best segmentation accuracy by comparison with other state-of-the-art segmentation methods. Conclusions: The authors have proposed a new CBCT segmentation method by using patch-based sparse representation and convex optimization, which can achieve considerably accurate segmentation results in CBCT segmentation based on 15 patients.

Original languageEnglish
Article number043503
JournalMedical Physics
Volume41
Issue number4
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Cone-Beam Computed Tomography
Atlases
Tooth
Bone and Bones
Maxilla
Signal-To-Noise Ratio
Mandible
Artifacts
Noise
Therapeutics

Keywords

  • atlas-based segmentation
  • CBCT
  • convex optimization
  • elastic net
  • patient-specific atlas
  • sparse representation

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

Automated bone segmentation from dental CBCT images using patch-based sparse representation and convex optimization. / Wang, Li; Chen, Ken Chung; Gao, Yaozong; Shi, Feng; Liao, Shu; Li, Gang; Shen, Steve G F; Yan, Jin; Lee, Philip K M; Chow, Ben; Liu, Nancy X.; Xia, James J.; Shen, Dinggang.

In: Medical Physics, Vol. 41, No. 4, 043503, 01.01.2014.

Research output: Contribution to journalArticle

Wang, L, Chen, KC, Gao, Y, Shi, F, Liao, S, Li, G, Shen, SGF, Yan, J, Lee, PKM, Chow, B, Liu, NX, Xia, JJ & Shen, D 2014, 'Automated bone segmentation from dental CBCT images using patch-based sparse representation and convex optimization', Medical Physics, vol. 41, no. 4, 043503. https://doi.org/10.1118/1.4868455
Wang, Li ; Chen, Ken Chung ; Gao, Yaozong ; Shi, Feng ; Liao, Shu ; Li, Gang ; Shen, Steve G F ; Yan, Jin ; Lee, Philip K M ; Chow, Ben ; Liu, Nancy X. ; Xia, James J. ; Shen, Dinggang. / Automated bone segmentation from dental CBCT images using patch-based sparse representation and convex optimization. In: Medical Physics. 2014 ; Vol. 41, No. 4.
@article{7e0b242d07294565b5d6981a2e78d160,
title = "Automated bone segmentation from dental CBCT images using patch-based sparse representation and convex optimization",
abstract = "Purpose: Cone-beam computed tomography (CBCT) is an increasingly utilized imaging modality for the diagnosis and treatment planning of the patients with craniomaxillofacial (CMF) deformities. Accurate segmentation of CBCT image is an essential step to generate three-dimensional (3D) models for the diagnosis and treatment planning of the patients with CMF deformities. However, due to the poor image quality, including very low signal-to-noise ratio and the widespread image artifacts such as noise, beam hardening, and inhomogeneity, it is challenging to segment the CBCT images. In this paper, the authors present a new automatic segmentation method to address these problems. Methods: To segment CBCT images, the authors propose a new method for fully automated CBCT segmentation by using patch-based sparse representation to (1) segment bony structures from the soft tissues and (2) further separate the mandible from the maxilla. Specifically, a region-specific registration strategy is first proposed to warp all the atlases to the current testing subject and then a sparse-based label propagation strategy is employed to estimate a patient-specific atlas from all aligned atlases. Finally, the patient-specific atlas is integrated into amaximum a posteriori probability-based convex segmentation framework for accurate segmentation. Results: The proposed method has been evaluated on a dataset with 15 CBCT images. The effectiveness of the proposed region-specific registration strategy and patient-specific atlas has been validated by comparing with the traditional registration strategy and population-based atlas. The experimental results show that the proposed method achieves the best segmentation accuracy by comparison with other state-of-the-art segmentation methods. Conclusions: The authors have proposed a new CBCT segmentation method by using patch-based sparse representation and convex optimization, which can achieve considerably accurate segmentation results in CBCT segmentation based on 15 patients.",
keywords = "atlas-based segmentation, CBCT, convex optimization, elastic net, patient-specific atlas, sparse representation",
author = "Li Wang and Chen, {Ken Chung} and Yaozong Gao and Feng Shi and Shu Liao and Gang Li and Shen, {Steve G F} and Jin Yan and Lee, {Philip K M} and Ben Chow and Liu, {Nancy X.} and Xia, {James J.} and Dinggang Shen",
year = "2014",
month = "1",
day = "1",
doi = "10.1118/1.4868455",
language = "English",
volume = "41",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "4",

}

TY - JOUR

T1 - Automated bone segmentation from dental CBCT images using patch-based sparse representation and convex optimization

AU - Wang, Li

AU - Chen, Ken Chung

AU - Gao, Yaozong

AU - Shi, Feng

AU - Liao, Shu

AU - Li, Gang

AU - Shen, Steve G F

AU - Yan, Jin

AU - Lee, Philip K M

AU - Chow, Ben

AU - Liu, Nancy X.

AU - Xia, James J.

AU - Shen, Dinggang

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Purpose: Cone-beam computed tomography (CBCT) is an increasingly utilized imaging modality for the diagnosis and treatment planning of the patients with craniomaxillofacial (CMF) deformities. Accurate segmentation of CBCT image is an essential step to generate three-dimensional (3D) models for the diagnosis and treatment planning of the patients with CMF deformities. However, due to the poor image quality, including very low signal-to-noise ratio and the widespread image artifacts such as noise, beam hardening, and inhomogeneity, it is challenging to segment the CBCT images. In this paper, the authors present a new automatic segmentation method to address these problems. Methods: To segment CBCT images, the authors propose a new method for fully automated CBCT segmentation by using patch-based sparse representation to (1) segment bony structures from the soft tissues and (2) further separate the mandible from the maxilla. Specifically, a region-specific registration strategy is first proposed to warp all the atlases to the current testing subject and then a sparse-based label propagation strategy is employed to estimate a patient-specific atlas from all aligned atlases. Finally, the patient-specific atlas is integrated into amaximum a posteriori probability-based convex segmentation framework for accurate segmentation. Results: The proposed method has been evaluated on a dataset with 15 CBCT images. The effectiveness of the proposed region-specific registration strategy and patient-specific atlas has been validated by comparing with the traditional registration strategy and population-based atlas. The experimental results show that the proposed method achieves the best segmentation accuracy by comparison with other state-of-the-art segmentation methods. Conclusions: The authors have proposed a new CBCT segmentation method by using patch-based sparse representation and convex optimization, which can achieve considerably accurate segmentation results in CBCT segmentation based on 15 patients.

AB - Purpose: Cone-beam computed tomography (CBCT) is an increasingly utilized imaging modality for the diagnosis and treatment planning of the patients with craniomaxillofacial (CMF) deformities. Accurate segmentation of CBCT image is an essential step to generate three-dimensional (3D) models for the diagnosis and treatment planning of the patients with CMF deformities. However, due to the poor image quality, including very low signal-to-noise ratio and the widespread image artifacts such as noise, beam hardening, and inhomogeneity, it is challenging to segment the CBCT images. In this paper, the authors present a new automatic segmentation method to address these problems. Methods: To segment CBCT images, the authors propose a new method for fully automated CBCT segmentation by using patch-based sparse representation to (1) segment bony structures from the soft tissues and (2) further separate the mandible from the maxilla. Specifically, a region-specific registration strategy is first proposed to warp all the atlases to the current testing subject and then a sparse-based label propagation strategy is employed to estimate a patient-specific atlas from all aligned atlases. Finally, the patient-specific atlas is integrated into amaximum a posteriori probability-based convex segmentation framework for accurate segmentation. Results: The proposed method has been evaluated on a dataset with 15 CBCT images. The effectiveness of the proposed region-specific registration strategy and patient-specific atlas has been validated by comparing with the traditional registration strategy and population-based atlas. The experimental results show that the proposed method achieves the best segmentation accuracy by comparison with other state-of-the-art segmentation methods. Conclusions: The authors have proposed a new CBCT segmentation method by using patch-based sparse representation and convex optimization, which can achieve considerably accurate segmentation results in CBCT segmentation based on 15 patients.

KW - atlas-based segmentation

KW - CBCT

KW - convex optimization

KW - elastic net

KW - patient-specific atlas

KW - sparse representation

UR - http://www.scopus.com/inward/record.url?scp=84897039890&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897039890&partnerID=8YFLogxK

U2 - 10.1118/1.4868455

DO - 10.1118/1.4868455

M3 - Article

C2 - 24694160

AN - SCOPUS:84897039890

VL - 41

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 4

M1 - 043503

ER -