Z-Index Parameterization (ZIP) for Volumetric CT Image Reconstruction via 3D Dictionary Learning

Ti Bai, Hao Yan, Xun Jia, Steve Jiang, Ge Wang, Xuanqin Mou

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Despite the rapid developments of x-ray cone-beam CT (CBCT), image noise still remains a major issue for the low dose CBCT. To suppress the noise effectively while retain the structures well for low dose CBCT image, in this work, a sparse constraint based on the 3D dictionary is incorporated into a regularized iterative reconstruction framework, defining the 3DDL method. In addition, by analyzing the sparsity level curve associated with different regularization parameters, a new adaptive parameter selection strategy is proposed to facilitate our 3DDL method. To justify the proposed method, we first analyze the distributions of the representation coefficients associated with the 3D dictionary and the conventional 2D dictionary to compare their efficiencies in representing volumetric images. Then, multiple real data experiments are conducted for performance validation. Based on these results, we found: (1) the 3D dictionary based sparse coefficients have three orders narrower Laplacian distribution compared to the 2D dictionary, suggesting the higher representation efficiencies of the 3D dictionary; (2) the sparsity level curve demonstrates a clear Z-shape, and hence referred to as Z-curve in this paper; (3) the parameter associated with the maximum curvature point of the Z-curve suggests a nice parameter choice, which could be adaptively located with the proposed Z-index parameterization (ZIP) method; (4) the proposed 3DDL algorithm equipped with the ZIP method could deliver reconstructions with the lowest root mean squared errors (RMSE) and the highest structural similarity (SSIM) index compared to the competing methods; (5) similar noise performance as the regular dose FDK reconstruction regarding the standard deviation metric could be achieved with the proposed method using 1/2 / 1/4 / 1/8 dose level projections. The contrast-noise ratio (CNR) is improved by ~ 2.5/3.5 times with respect to two different cases under the 1/8 dose level compared to the low dose FDK reconstruction. The proposed method is expected to reduce the radiation dose by a factor of 8 for CBCT, considering the voted strongly discriminated low contrast tissues.

Original languageEnglish (US)
JournalIEEE Transactions on Medical Imaging
DOIs
StateAccepted/In press - Oct 4 2017

Fingerprint

Computer-Assisted Image Processing
Glossaries
Parameterization
Image reconstruction
Learning
Cones
Cone-Beam Computed Tomography
Noise
Efficiency
Dosimetry
Tissue
X rays
X-Rays
Radiation
Experiments

Keywords

  • Computed tomography
  • cone-beam CT
  • Dictionaries
  • Dictionary learning
  • Image reconstruction
  • Machine learning
  • Matching pursuit algorithms
  • noise suppression
  • regularization parameter
  • sparse representation
  • Three-dimensional displays
  • Two dimensional displays

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Z-Index Parameterization (ZIP) for Volumetric CT Image Reconstruction via 3D Dictionary Learning. / Bai, Ti; Yan, Hao; Jia, Xun; Jiang, Steve; Wang, Ge; Mou, Xuanqin.

In: IEEE Transactions on Medical Imaging, 04.10.2017.

Research output: Contribution to journalArticle

@article{aade8eea7ac64c74b197bf24858f7a48,
title = "Z-Index Parameterization (ZIP) for Volumetric CT Image Reconstruction via 3D Dictionary Learning",
abstract = "Despite the rapid developments of x-ray cone-beam CT (CBCT), image noise still remains a major issue for the low dose CBCT. To suppress the noise effectively while retain the structures well for low dose CBCT image, in this work, a sparse constraint based on the 3D dictionary is incorporated into a regularized iterative reconstruction framework, defining the 3DDL method. In addition, by analyzing the sparsity level curve associated with different regularization parameters, a new adaptive parameter selection strategy is proposed to facilitate our 3DDL method. To justify the proposed method, we first analyze the distributions of the representation coefficients associated with the 3D dictionary and the conventional 2D dictionary to compare their efficiencies in representing volumetric images. Then, multiple real data experiments are conducted for performance validation. Based on these results, we found: (1) the 3D dictionary based sparse coefficients have three orders narrower Laplacian distribution compared to the 2D dictionary, suggesting the higher representation efficiencies of the 3D dictionary; (2) the sparsity level curve demonstrates a clear Z-shape, and hence referred to as Z-curve in this paper; (3) the parameter associated with the maximum curvature point of the Z-curve suggests a nice parameter choice, which could be adaptively located with the proposed Z-index parameterization (ZIP) method; (4) the proposed 3DDL algorithm equipped with the ZIP method could deliver reconstructions with the lowest root mean squared errors (RMSE) and the highest structural similarity (SSIM) index compared to the competing methods; (5) similar noise performance as the regular dose FDK reconstruction regarding the standard deviation metric could be achieved with the proposed method using 1/2 / 1/4 / 1/8 dose level projections. The contrast-noise ratio (CNR) is improved by ~ 2.5/3.5 times with respect to two different cases under the 1/8 dose level compared to the low dose FDK reconstruction. The proposed method is expected to reduce the radiation dose by a factor of 8 for CBCT, considering the voted strongly discriminated low contrast tissues.",
keywords = "Computed tomography, cone-beam CT, Dictionaries, Dictionary learning, Image reconstruction, Machine learning, Matching pursuit algorithms, noise suppression, regularization parameter, sparse representation, Three-dimensional displays, Two dimensional displays",
author = "Ti Bai and Hao Yan and Xun Jia and Steve Jiang and Ge Wang and Xuanqin Mou",
year = "2017",
month = "10",
day = "4",
doi = "10.1109/TMI.2017.2759819",
language = "English (US)",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Z-Index Parameterization (ZIP) for Volumetric CT Image Reconstruction via 3D Dictionary Learning

AU - Bai, Ti

AU - Yan, Hao

AU - Jia, Xun

AU - Jiang, Steve

AU - Wang, Ge

AU - Mou, Xuanqin

PY - 2017/10/4

Y1 - 2017/10/4

N2 - Despite the rapid developments of x-ray cone-beam CT (CBCT), image noise still remains a major issue for the low dose CBCT. To suppress the noise effectively while retain the structures well for low dose CBCT image, in this work, a sparse constraint based on the 3D dictionary is incorporated into a regularized iterative reconstruction framework, defining the 3DDL method. In addition, by analyzing the sparsity level curve associated with different regularization parameters, a new adaptive parameter selection strategy is proposed to facilitate our 3DDL method. To justify the proposed method, we first analyze the distributions of the representation coefficients associated with the 3D dictionary and the conventional 2D dictionary to compare their efficiencies in representing volumetric images. Then, multiple real data experiments are conducted for performance validation. Based on these results, we found: (1) the 3D dictionary based sparse coefficients have three orders narrower Laplacian distribution compared to the 2D dictionary, suggesting the higher representation efficiencies of the 3D dictionary; (2) the sparsity level curve demonstrates a clear Z-shape, and hence referred to as Z-curve in this paper; (3) the parameter associated with the maximum curvature point of the Z-curve suggests a nice parameter choice, which could be adaptively located with the proposed Z-index parameterization (ZIP) method; (4) the proposed 3DDL algorithm equipped with the ZIP method could deliver reconstructions with the lowest root mean squared errors (RMSE) and the highest structural similarity (SSIM) index compared to the competing methods; (5) similar noise performance as the regular dose FDK reconstruction regarding the standard deviation metric could be achieved with the proposed method using 1/2 / 1/4 / 1/8 dose level projections. The contrast-noise ratio (CNR) is improved by ~ 2.5/3.5 times with respect to two different cases under the 1/8 dose level compared to the low dose FDK reconstruction. The proposed method is expected to reduce the radiation dose by a factor of 8 for CBCT, considering the voted strongly discriminated low contrast tissues.

AB - Despite the rapid developments of x-ray cone-beam CT (CBCT), image noise still remains a major issue for the low dose CBCT. To suppress the noise effectively while retain the structures well for low dose CBCT image, in this work, a sparse constraint based on the 3D dictionary is incorporated into a regularized iterative reconstruction framework, defining the 3DDL method. In addition, by analyzing the sparsity level curve associated with different regularization parameters, a new adaptive parameter selection strategy is proposed to facilitate our 3DDL method. To justify the proposed method, we first analyze the distributions of the representation coefficients associated with the 3D dictionary and the conventional 2D dictionary to compare their efficiencies in representing volumetric images. Then, multiple real data experiments are conducted for performance validation. Based on these results, we found: (1) the 3D dictionary based sparse coefficients have three orders narrower Laplacian distribution compared to the 2D dictionary, suggesting the higher representation efficiencies of the 3D dictionary; (2) the sparsity level curve demonstrates a clear Z-shape, and hence referred to as Z-curve in this paper; (3) the parameter associated with the maximum curvature point of the Z-curve suggests a nice parameter choice, which could be adaptively located with the proposed Z-index parameterization (ZIP) method; (4) the proposed 3DDL algorithm equipped with the ZIP method could deliver reconstructions with the lowest root mean squared errors (RMSE) and the highest structural similarity (SSIM) index compared to the competing methods; (5) similar noise performance as the regular dose FDK reconstruction regarding the standard deviation metric could be achieved with the proposed method using 1/2 / 1/4 / 1/8 dose level projections. The contrast-noise ratio (CNR) is improved by ~ 2.5/3.5 times with respect to two different cases under the 1/8 dose level compared to the low dose FDK reconstruction. The proposed method is expected to reduce the radiation dose by a factor of 8 for CBCT, considering the voted strongly discriminated low contrast tissues.

KW - Computed tomography

KW - cone-beam CT

KW - Dictionaries

KW - Dictionary learning

KW - Image reconstruction

KW - Machine learning

KW - Matching pursuit algorithms

KW - noise suppression

KW - regularization parameter

KW - sparse representation

KW - Three-dimensional displays

KW - Two dimensional displays

UR - http://www.scopus.com/inward/record.url?scp=85031825646&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031825646&partnerID=8YFLogxK

U2 - 10.1109/TMI.2017.2759819

DO - 10.1109/TMI.2017.2759819

M3 - Article

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

ER -