Statistical Iterative CBCT Reconstruction Based on Neural Network

Binbin Chen, Kai Xiang, Zaiwen Gong, Jing Wang, Shan Tan

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Cone-beam computed tomography (CBCT) plays an important role in radiation therapy. Statistical iterative reconstruction (SIR) algorithms with specially designed penalty terms provide good performance for low-dose CBCT imaging. Among others, the total variation (TV) penalty is the current state-of-the-art in removing noises and preserving edges, but one of its well-known limitations is its staircase effect. Recently, various penalty terms with higher order differential operators were proposed to replace the TV penalty to avoid the staircase effect, at the cost of slightly blurring object edges. We developed a novel SIR algorithm using a neural network for CBCT reconstruction. We used a data-driven method to learn the "potential regularization term" rather than design a penalty term manually. This approach converts the problem of designing a penalty term in the traditional statistical iterative framework to designing and training a suitable neural network for CBCT reconstruction. We proposed using transfer learning to overcome the data deficiency problem and an iterative deblurring approach specially designed for the CBCT iterative reconstruction process during which the noise level and resolution of the reconstructed images may change. Through experiments conducted on two physical phantoms, two simulation digital phantoms, and patient data, we demonstrated the excellent performance of the proposed network-based SIR for CBCT reconstruction, both visually and quantitatively. Our proposed method can overcome the staircase effect, preserve both edges and regions with smooth intensity transition, and provide reconstruction results at high resolution and low noise level.

Original languageEnglish (US)
Pages (from-to)1511-1521
Number of pages11
JournalIEEE Transactions on Medical Imaging
Volume37
Issue number6
DOIs
StatePublished - Jun 1 2018

Fingerprint

Cone-Beam Computed Tomography
Tomography
Cones
Neural networks
Noise
Radiotherapy
Imaging techniques
Experiments

Keywords

  • CBCT
  • image reconstruction
  • neural network
  • regularization term

ASJC Scopus subject areas

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

Cite this

Statistical Iterative CBCT Reconstruction Based on Neural Network. / Chen, Binbin; Xiang, Kai; Gong, Zaiwen; Wang, Jing; Tan, Shan.

In: IEEE Transactions on Medical Imaging, Vol. 37, No. 6, 01.06.2018, p. 1511-1521.

Research output: Contribution to journalArticle

Chen, Binbin ; Xiang, Kai ; Gong, Zaiwen ; Wang, Jing ; Tan, Shan. / Statistical Iterative CBCT Reconstruction Based on Neural Network. In: IEEE Transactions on Medical Imaging. 2018 ; Vol. 37, No. 6. pp. 1511-1521.
@article{2ca973c01e54478fa290850ae875ec38,
title = "Statistical Iterative CBCT Reconstruction Based on Neural Network",
abstract = "Cone-beam computed tomography (CBCT) plays an important role in radiation therapy. Statistical iterative reconstruction (SIR) algorithms with specially designed penalty terms provide good performance for low-dose CBCT imaging. Among others, the total variation (TV) penalty is the current state-of-the-art in removing noises and preserving edges, but one of its well-known limitations is its staircase effect. Recently, various penalty terms with higher order differential operators were proposed to replace the TV penalty to avoid the staircase effect, at the cost of slightly blurring object edges. We developed a novel SIR algorithm using a neural network for CBCT reconstruction. We used a data-driven method to learn the {"}potential regularization term{"} rather than design a penalty term manually. This approach converts the problem of designing a penalty term in the traditional statistical iterative framework to designing and training a suitable neural network for CBCT reconstruction. We proposed using transfer learning to overcome the data deficiency problem and an iterative deblurring approach specially designed for the CBCT iterative reconstruction process during which the noise level and resolution of the reconstructed images may change. Through experiments conducted on two physical phantoms, two simulation digital phantoms, and patient data, we demonstrated the excellent performance of the proposed network-based SIR for CBCT reconstruction, both visually and quantitatively. Our proposed method can overcome the staircase effect, preserve both edges and regions with smooth intensity transition, and provide reconstruction results at high resolution and low noise level.",
keywords = "CBCT, image reconstruction, neural network, regularization term",
author = "Binbin Chen and Kai Xiang and Zaiwen Gong and Jing Wang and Shan Tan",
year = "2018",
month = "6",
day = "1",
doi = "10.1109/TMI.2018.2829896",
language = "English (US)",
volume = "37",
pages = "1511--1521",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Statistical Iterative CBCT Reconstruction Based on Neural Network

AU - Chen, Binbin

AU - Xiang, Kai

AU - Gong, Zaiwen

AU - Wang, Jing

AU - Tan, Shan

PY - 2018/6/1

Y1 - 2018/6/1

N2 - Cone-beam computed tomography (CBCT) plays an important role in radiation therapy. Statistical iterative reconstruction (SIR) algorithms with specially designed penalty terms provide good performance for low-dose CBCT imaging. Among others, the total variation (TV) penalty is the current state-of-the-art in removing noises and preserving edges, but one of its well-known limitations is its staircase effect. Recently, various penalty terms with higher order differential operators were proposed to replace the TV penalty to avoid the staircase effect, at the cost of slightly blurring object edges. We developed a novel SIR algorithm using a neural network for CBCT reconstruction. We used a data-driven method to learn the "potential regularization term" rather than design a penalty term manually. This approach converts the problem of designing a penalty term in the traditional statistical iterative framework to designing and training a suitable neural network for CBCT reconstruction. We proposed using transfer learning to overcome the data deficiency problem and an iterative deblurring approach specially designed for the CBCT iterative reconstruction process during which the noise level and resolution of the reconstructed images may change. Through experiments conducted on two physical phantoms, two simulation digital phantoms, and patient data, we demonstrated the excellent performance of the proposed network-based SIR for CBCT reconstruction, both visually and quantitatively. Our proposed method can overcome the staircase effect, preserve both edges and regions with smooth intensity transition, and provide reconstruction results at high resolution and low noise level.

AB - Cone-beam computed tomography (CBCT) plays an important role in radiation therapy. Statistical iterative reconstruction (SIR) algorithms with specially designed penalty terms provide good performance for low-dose CBCT imaging. Among others, the total variation (TV) penalty is the current state-of-the-art in removing noises and preserving edges, but one of its well-known limitations is its staircase effect. Recently, various penalty terms with higher order differential operators were proposed to replace the TV penalty to avoid the staircase effect, at the cost of slightly blurring object edges. We developed a novel SIR algorithm using a neural network for CBCT reconstruction. We used a data-driven method to learn the "potential regularization term" rather than design a penalty term manually. This approach converts the problem of designing a penalty term in the traditional statistical iterative framework to designing and training a suitable neural network for CBCT reconstruction. We proposed using transfer learning to overcome the data deficiency problem and an iterative deblurring approach specially designed for the CBCT iterative reconstruction process during which the noise level and resolution of the reconstructed images may change. Through experiments conducted on two physical phantoms, two simulation digital phantoms, and patient data, we demonstrated the excellent performance of the proposed network-based SIR for CBCT reconstruction, both visually and quantitatively. Our proposed method can overcome the staircase effect, preserve both edges and regions with smooth intensity transition, and provide reconstruction results at high resolution and low noise level.

KW - CBCT

KW - image reconstruction

KW - neural network

KW - regularization term

UR - http://www.scopus.com/inward/record.url?scp=85045960259&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045960259&partnerID=8YFLogxK

U2 - 10.1109/TMI.2018.2829896

DO - 10.1109/TMI.2018.2829896

M3 - Article

C2 - 29870378

AN - SCOPUS:85045960259

VL - 37

SP - 1511

EP - 1521

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 6

ER -