Automatic Craniomaxillofacial Landmark Digitization via Segmentation-Guided Partially-Joint Regression Forest Model and Multiscale Statistical Features

Jun Zhang, Yaozong Gao, Li Wang, Zhen Tang, James J. Xia, Dinggang Shen

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Objective: The goal of this paper is to automatically digitize craniomaxillofacial (CMF) landmarks efficiently and accurately from cone-beam computed tomography (CBCT) images, by addressing the challenge caused by large morphological variations across patients and image artifacts of CBCT images. Methods: We propose a segmentation-guided partially-joint regression forest (S-PRF) model to automatically digitize CMF landmarks. In this model, a regression voting strategy is first adopted to localize each landmark by aggregating evidences from context locations, thus potentially relieving the problem caused by image artifacts near the landmark. Second, CBCT image segmentation is utilized to remove uninformative voxels caused by morphological variations across patients. Third, a partially-joint model is further proposed to separately localize landmarks based on the coherence of landmark positions to improve the digitization reliability. In addition, we propose a fast vector quantization method to extract high-level multiscale statistical features to describe a voxel's appearance, which has low dimensionality, high efficiency, and is also invariant to the local inhomogeneity caused by artifacts. Results: Mean digitization errors for 15 landmarks, in comparison to the ground truth, are all less than 2 mm. Conclusion: Our model has addressed challenges of both interpatient morphological variations and imaging artifacts. Experiments on a CBCT dataset show that our approach achieves clinically acceptable accuracy for landmark digitalization. Significance: Our automatic landmark digitization method can be used clinically to reduce the labor cost and also improve digitalization consistency.

Original languageEnglish
Article number7336501
Pages (from-to)1820-1829
Number of pages10
JournalIEEE Transactions on Biomedical Engineering
Volume63
Issue number9
DOIs
Publication statusPublished - 2016 Sep 1

Fingerprint

Cone-Beam Computed Tomography
Analog to digital conversion
Statistical Models
Artifacts
Tomography
Cones
Joints
Vector quantization
Politics
Image segmentation
Personnel
Imaging techniques
Costs and Cost Analysis
Costs
Experiments

Keywords

  • Cone-beam computed tomography (CBCT)
  • fast vector quantization (VQ)
  • landmark digitization
  • partially-joint regression forest (PRF)
  • segmentation

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Automatic Craniomaxillofacial Landmark Digitization via Segmentation-Guided Partially-Joint Regression Forest Model and Multiscale Statistical Features. / Zhang, Jun; Gao, Yaozong; Wang, Li; Tang, Zhen; Xia, James J.; Shen, Dinggang.

In: IEEE Transactions on Biomedical Engineering, Vol. 63, No. 9, 7336501, 01.09.2016, p. 1820-1829.

Research output: Contribution to journalArticle

@article{fae89d68c1464507af0f79ed98e5166f,
title = "Automatic Craniomaxillofacial Landmark Digitization via Segmentation-Guided Partially-Joint Regression Forest Model and Multiscale Statistical Features",
abstract = "Objective: The goal of this paper is to automatically digitize craniomaxillofacial (CMF) landmarks efficiently and accurately from cone-beam computed tomography (CBCT) images, by addressing the challenge caused by large morphological variations across patients and image artifacts of CBCT images. Methods: We propose a segmentation-guided partially-joint regression forest (S-PRF) model to automatically digitize CMF landmarks. In this model, a regression voting strategy is first adopted to localize each landmark by aggregating evidences from context locations, thus potentially relieving the problem caused by image artifacts near the landmark. Second, CBCT image segmentation is utilized to remove uninformative voxels caused by morphological variations across patients. Third, a partially-joint model is further proposed to separately localize landmarks based on the coherence of landmark positions to improve the digitization reliability. In addition, we propose a fast vector quantization method to extract high-level multiscale statistical features to describe a voxel's appearance, which has low dimensionality, high efficiency, and is also invariant to the local inhomogeneity caused by artifacts. Results: Mean digitization errors for 15 landmarks, in comparison to the ground truth, are all less than 2 mm. Conclusion: Our model has addressed challenges of both interpatient morphological variations and imaging artifacts. Experiments on a CBCT dataset show that our approach achieves clinically acceptable accuracy for landmark digitalization. Significance: Our automatic landmark digitization method can be used clinically to reduce the labor cost and also improve digitalization consistency.",
keywords = "Cone-beam computed tomography (CBCT), fast vector quantization (VQ), landmark digitization, partially-joint regression forest (PRF), segmentation",
author = "Jun Zhang and Yaozong Gao and Li Wang and Zhen Tang and Xia, {James J.} and Dinggang Shen",
year = "2016",
month = "9",
day = "1",
doi = "10.1109/TBME.2015.2503421",
language = "English",
volume = "63",
pages = "1820--1829",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "9",

}

TY - JOUR

T1 - Automatic Craniomaxillofacial Landmark Digitization via Segmentation-Guided Partially-Joint Regression Forest Model and Multiscale Statistical Features

AU - Zhang, Jun

AU - Gao, Yaozong

AU - Wang, Li

AU - Tang, Zhen

AU - Xia, James J.

AU - Shen, Dinggang

PY - 2016/9/1

Y1 - 2016/9/1

N2 - Objective: The goal of this paper is to automatically digitize craniomaxillofacial (CMF) landmarks efficiently and accurately from cone-beam computed tomography (CBCT) images, by addressing the challenge caused by large morphological variations across patients and image artifacts of CBCT images. Methods: We propose a segmentation-guided partially-joint regression forest (S-PRF) model to automatically digitize CMF landmarks. In this model, a regression voting strategy is first adopted to localize each landmark by aggregating evidences from context locations, thus potentially relieving the problem caused by image artifacts near the landmark. Second, CBCT image segmentation is utilized to remove uninformative voxels caused by morphological variations across patients. Third, a partially-joint model is further proposed to separately localize landmarks based on the coherence of landmark positions to improve the digitization reliability. In addition, we propose a fast vector quantization method to extract high-level multiscale statistical features to describe a voxel's appearance, which has low dimensionality, high efficiency, and is also invariant to the local inhomogeneity caused by artifacts. Results: Mean digitization errors for 15 landmarks, in comparison to the ground truth, are all less than 2 mm. Conclusion: Our model has addressed challenges of both interpatient morphological variations and imaging artifacts. Experiments on a CBCT dataset show that our approach achieves clinically acceptable accuracy for landmark digitalization. Significance: Our automatic landmark digitization method can be used clinically to reduce the labor cost and also improve digitalization consistency.

AB - Objective: The goal of this paper is to automatically digitize craniomaxillofacial (CMF) landmarks efficiently and accurately from cone-beam computed tomography (CBCT) images, by addressing the challenge caused by large morphological variations across patients and image artifacts of CBCT images. Methods: We propose a segmentation-guided partially-joint regression forest (S-PRF) model to automatically digitize CMF landmarks. In this model, a regression voting strategy is first adopted to localize each landmark by aggregating evidences from context locations, thus potentially relieving the problem caused by image artifacts near the landmark. Second, CBCT image segmentation is utilized to remove uninformative voxels caused by morphological variations across patients. Third, a partially-joint model is further proposed to separately localize landmarks based on the coherence of landmark positions to improve the digitization reliability. In addition, we propose a fast vector quantization method to extract high-level multiscale statistical features to describe a voxel's appearance, which has low dimensionality, high efficiency, and is also invariant to the local inhomogeneity caused by artifacts. Results: Mean digitization errors for 15 landmarks, in comparison to the ground truth, are all less than 2 mm. Conclusion: Our model has addressed challenges of both interpatient morphological variations and imaging artifacts. Experiments on a CBCT dataset show that our approach achieves clinically acceptable accuracy for landmark digitalization. Significance: Our automatic landmark digitization method can be used clinically to reduce the labor cost and also improve digitalization consistency.

KW - Cone-beam computed tomography (CBCT)

KW - fast vector quantization (VQ)

KW - landmark digitization

KW - partially-joint regression forest (PRF)

KW - segmentation

UR - http://www.scopus.com/inward/record.url?scp=84984829683&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84984829683&partnerID=8YFLogxK

U2 - 10.1109/TBME.2015.2503421

DO - 10.1109/TBME.2015.2503421

M3 - Article

C2 - 26625402

AN - SCOPUS:84984829683

VL - 63

SP - 1820

EP - 1829

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 9

M1 - 7336501

ER -