Hierarchical patch-based sparse representation-a new approach for resolution enhancement of 4D-CT lung data

Yu Zhang, Guorong Wu, Pew Thian Yap, Qianjin Feng, Jun Lian, Wufan Chen, Dinggang Shen

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

Four-dimensional computed tomography (4D-CT) plays an important role in lung cancer treatment because of its capability in providing a comprehensive characterization of respiratory motion for high-precision radiation therapy. However, due to the inherent high-dose exposure associated with CT, dense sampling along superior-inferior direction is often not practical, thus resulting in an inter-slice thickness that is much greater than in-plane voxel resolutions. As a consequence, artifacts such as lung vessel discontinuity and partial volume effects are often observed in 4D-CT images, which may mislead dose administration in radiation therapy. In this paper, we present a novel patch-based technique for resolution enhancement of 4D-CT images along the superior-inferior direction. Our working premise is that anatomical information that is missing in one particular phase can be recovered from other phases. Based on this assumption, we employ a hierarchical patch-based sparse representation mechanism to enhance the superior-inferior resolution of 4D-CT by reconstructing additional intermediate CT slices. Specifically, for each spatial location on an intermediate CT slice that we intend to reconstruct, we first agglomerate a dictionary of patches from images of all other phases in the 4D-CT. We then employ a sparse combination of patches from this dictionary, with guidance from neighboring (upper and lower) slices, to reconstruct a series of patches, which we progressively refine in a hierarchical fashion to reconstruct the final intermediate slices with significantly enhanced anatomical details. Our method was extensively evaluated using a public dataset. In all experiments, our method outperforms the conventional linear and cubic-spline interpolation methods in preserving image details and also in suppressing misleading artifacts, indicating that our proposed method can potentially be applied to better image-guided radiation therapy of lung cancer in the future.

Original languageEnglish
Article number6213122
Pages (from-to)1993-2005
Number of pages13
JournalIEEE Transactions on Medical Imaging
Volume31
Issue number11
DOIs
Publication statusPublished - 2012 Dec 1
Externally publishedYes

Fingerprint

Four-Dimensional Computed Tomography
Radiotherapy
Glossaries
Lung
Oncology
Splines
Artifacts
Dosimetry
Tomography
Lung Neoplasms
Interpolation
Image-Guided Radiotherapy
Sampling
Experiments

Keywords

  • Adaptive dictionary
  • four-dimensional computed tomography (4D-CT) lung data
  • hierarchical patch-based sparse representation
  • resolution enhancement

ASJC Scopus subject areas

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

Cite this

Hierarchical patch-based sparse representation-a new approach for resolution enhancement of 4D-CT lung data. / Zhang, Yu; Wu, Guorong; Yap, Pew Thian; Feng, Qianjin; Lian, Jun; Chen, Wufan; Shen, Dinggang.

In: IEEE Transactions on Medical Imaging, Vol. 31, No. 11, 6213122, 01.12.2012, p. 1993-2005.

Research output: Contribution to journalArticle

Zhang, Yu ; Wu, Guorong ; Yap, Pew Thian ; Feng, Qianjin ; Lian, Jun ; Chen, Wufan ; Shen, Dinggang. / Hierarchical patch-based sparse representation-a new approach for resolution enhancement of 4D-CT lung data. In: IEEE Transactions on Medical Imaging. 2012 ; Vol. 31, No. 11. pp. 1993-2005.
@article{7c923cf66cd94bf380585142245cfe72,
title = "Hierarchical patch-based sparse representation-a new approach for resolution enhancement of 4D-CT lung data",
abstract = "Four-dimensional computed tomography (4D-CT) plays an important role in lung cancer treatment because of its capability in providing a comprehensive characterization of respiratory motion for high-precision radiation therapy. However, due to the inherent high-dose exposure associated with CT, dense sampling along superior-inferior direction is often not practical, thus resulting in an inter-slice thickness that is much greater than in-plane voxel resolutions. As a consequence, artifacts such as lung vessel discontinuity and partial volume effects are often observed in 4D-CT images, which may mislead dose administration in radiation therapy. In this paper, we present a novel patch-based technique for resolution enhancement of 4D-CT images along the superior-inferior direction. Our working premise is that anatomical information that is missing in one particular phase can be recovered from other phases. Based on this assumption, we employ a hierarchical patch-based sparse representation mechanism to enhance the superior-inferior resolution of 4D-CT by reconstructing additional intermediate CT slices. Specifically, for each spatial location on an intermediate CT slice that we intend to reconstruct, we first agglomerate a dictionary of patches from images of all other phases in the 4D-CT. We then employ a sparse combination of patches from this dictionary, with guidance from neighboring (upper and lower) slices, to reconstruct a series of patches, which we progressively refine in a hierarchical fashion to reconstruct the final intermediate slices with significantly enhanced anatomical details. Our method was extensively evaluated using a public dataset. In all experiments, our method outperforms the conventional linear and cubic-spline interpolation methods in preserving image details and also in suppressing misleading artifacts, indicating that our proposed method can potentially be applied to better image-guided radiation therapy of lung cancer in the future.",
keywords = "Adaptive dictionary, four-dimensional computed tomography (4D-CT) lung data, hierarchical patch-based sparse representation, resolution enhancement",
author = "Yu Zhang and Guorong Wu and Yap, {Pew Thian} and Qianjin Feng and Jun Lian and Wufan Chen and Dinggang Shen",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/TMI.2012.2202245",
language = "English",
volume = "31",
pages = "1993--2005",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

TY - JOUR

T1 - Hierarchical patch-based sparse representation-a new approach for resolution enhancement of 4D-CT lung data

AU - Zhang, Yu

AU - Wu, Guorong

AU - Yap, Pew Thian

AU - Feng, Qianjin

AU - Lian, Jun

AU - Chen, Wufan

AU - Shen, Dinggang

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Four-dimensional computed tomography (4D-CT) plays an important role in lung cancer treatment because of its capability in providing a comprehensive characterization of respiratory motion for high-precision radiation therapy. However, due to the inherent high-dose exposure associated with CT, dense sampling along superior-inferior direction is often not practical, thus resulting in an inter-slice thickness that is much greater than in-plane voxel resolutions. As a consequence, artifacts such as lung vessel discontinuity and partial volume effects are often observed in 4D-CT images, which may mislead dose administration in radiation therapy. In this paper, we present a novel patch-based technique for resolution enhancement of 4D-CT images along the superior-inferior direction. Our working premise is that anatomical information that is missing in one particular phase can be recovered from other phases. Based on this assumption, we employ a hierarchical patch-based sparse representation mechanism to enhance the superior-inferior resolution of 4D-CT by reconstructing additional intermediate CT slices. Specifically, for each spatial location on an intermediate CT slice that we intend to reconstruct, we first agglomerate a dictionary of patches from images of all other phases in the 4D-CT. We then employ a sparse combination of patches from this dictionary, with guidance from neighboring (upper and lower) slices, to reconstruct a series of patches, which we progressively refine in a hierarchical fashion to reconstruct the final intermediate slices with significantly enhanced anatomical details. Our method was extensively evaluated using a public dataset. In all experiments, our method outperforms the conventional linear and cubic-spline interpolation methods in preserving image details and also in suppressing misleading artifacts, indicating that our proposed method can potentially be applied to better image-guided radiation therapy of lung cancer in the future.

AB - Four-dimensional computed tomography (4D-CT) plays an important role in lung cancer treatment because of its capability in providing a comprehensive characterization of respiratory motion for high-precision radiation therapy. However, due to the inherent high-dose exposure associated with CT, dense sampling along superior-inferior direction is often not practical, thus resulting in an inter-slice thickness that is much greater than in-plane voxel resolutions. As a consequence, artifacts such as lung vessel discontinuity and partial volume effects are often observed in 4D-CT images, which may mislead dose administration in radiation therapy. In this paper, we present a novel patch-based technique for resolution enhancement of 4D-CT images along the superior-inferior direction. Our working premise is that anatomical information that is missing in one particular phase can be recovered from other phases. Based on this assumption, we employ a hierarchical patch-based sparse representation mechanism to enhance the superior-inferior resolution of 4D-CT by reconstructing additional intermediate CT slices. Specifically, for each spatial location on an intermediate CT slice that we intend to reconstruct, we first agglomerate a dictionary of patches from images of all other phases in the 4D-CT. We then employ a sparse combination of patches from this dictionary, with guidance from neighboring (upper and lower) slices, to reconstruct a series of patches, which we progressively refine in a hierarchical fashion to reconstruct the final intermediate slices with significantly enhanced anatomical details. Our method was extensively evaluated using a public dataset. In all experiments, our method outperforms the conventional linear and cubic-spline interpolation methods in preserving image details and also in suppressing misleading artifacts, indicating that our proposed method can potentially be applied to better image-guided radiation therapy of lung cancer in the future.

KW - Adaptive dictionary

KW - four-dimensional computed tomography (4D-CT) lung data

KW - hierarchical patch-based sparse representation

KW - resolution enhancement

UR - http://www.scopus.com/inward/record.url?scp=84877301335&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877301335&partnerID=8YFLogxK

U2 - 10.1109/TMI.2012.2202245

DO - 10.1109/TMI.2012.2202245

M3 - Article

C2 - 22692897

AN - SCOPUS:84877301335

VL - 31

SP - 1993

EP - 2005

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 11

M1 - 6213122

ER -