Literature DB >> 32587754

Daily edge deformation prediction using an unsupervised convolutional neural network model for low dose prior contour based total variation CBCT reconstruction (PCTV-CNN).

Yingxuan Chen1, Fang-Fang Yin1,2,3, Zhuoran Jiang2, Lei Ren1,2.   

Abstract

PURPOSE: Previously we developed a PCTV method to enhance the edge sharpness for low-dose CBCT reconstruction. However, the iterative deformable registration method used for deforming edges from planning-CT to on-board CBCT is time-consuming and user-dependent. This study aims to automate and accelerate PCTV reconstruction by developing an unsupervised CNN model to bypass the conventional deformable registration.
METHODS: The new method uses unsupervised CNN model for deformation prediction and PCTV reconstruction. An unsupervised CNN model with a u-net structure was used to predict deformation vector fields (DVF) to generate on-board contours for PCTV reconstruction. Paired 3D image volumes of prior CT and on-board CBCT are inputs and DVF are predicted without the need of ground truths. The model was initially trained on brain MRI images, and then fine-tuned using our lung SBRT data. This method was evaluated using lung SBRT patient data. In the intra-patient study, the first n-1 day's CBCTs are used for CNN training to predict nth day edge information (n = 2, 3, 4, 5). 45 half-fan projections covering 360˚ from nth day CBCT is used for reconstruction. In the inter-patient study, the 10 patient images including CT and first day's CBCT are used for training. Results from Edge-preserving (EPTV), PCTV and PCTV-CNN are compared.
RESULTS: The cross-correlations of the predicted edge map and the ground truth were on average 0.88 for both intra-patient and inter-patient studies. PCTV-CNN achieved comparable image quality as PCTV while automating the registration process and reducing the registration time from 1-2 min to 1.4 s.
CONCLUSION: It is feasible to use an unsupervised CNN to predict daily deformation of on-board edge information for PCTV based low-dose CBCT reconstruction. PCTV-CNN has a great potential for enhancing the edge sharpness with high efficiency for low-dose CBCT to improve the precision of on-board target localization and adaptive radiotherapy.

Entities:  

Keywords:  low dose CBCT reconstruction; prior contour based total variation (PCTV); unsupervised convolutional neural networks (CNN)

Year:  2019        PMID: 32587754      PMCID: PMC7316357          DOI: 10.1088/2057-1976/ab446b

Source DB:  PubMed          Journal:  Biomed Phys Eng Express        ISSN: 2057-1976


  31 in total

1.  Improved compressed sensing-based cone-beam CT reconstruction using adaptive prior image constraints.

Authors:  Ho Lee; Lei Xing; Ran Davidi; Ruijiang Li; Jianguo Qian; Rena Lee
Journal:  Phys Med Biol       Date:  2012-03-30       Impact factor: 3.609

2.  Towards the clinical implementation of iterative low-dose cone-beam CT reconstruction in image-guided radiation therapy: cone/ring artifact correction and multiple GPU implementation.

Authors:  Hao Yan; Xiaoyu Wang; Feng Shi; Ti Bai; Michael Folkerts; Laura Cervino; Steve B Jiang; Xun Jia
Journal:  Med Phys       Date:  2014-11       Impact factor: 4.071

3.  Digital mammographic tumor classification using transfer learning from deep convolutional neural networks.

Authors:  Benjamin Q Huynh; Hui Li; Maryellen L Giger
Journal:  J Med Imaging (Bellingham)       Date:  2016-08-22

4.  Low-dose CT reconstruction via edge-preserving total variation regularization.

Authors:  Zhen Tian; Xun Jia; Kehong Yuan; Tinsu Pan; Steve B Jiang
Journal:  Phys Med Biol       Date:  2011-08-22       Impact factor: 3.609

5.  A comprehensive study on the relationship between the image quality and imaging dose in low-dose cone beam CT.

Authors:  Hao Yan; Laura Cervino; Xun Jia; Steve B Jiang
Journal:  Phys Med Biol       Date:  2012-04-07       Impact factor: 3.609

6.  The management of respiratory motion in radiation oncology report of AAPM Task Group 76.

Authors:  Paul J Keall; Gig S Mageras; James M Balter; Richard S Emery; Kenneth M Forster; Steve B Jiang; Jeffrey M Kapatoes; Daniel A Low; Martin J Murphy; Brad R Murray; Chester R Ramsey; Marcel B Van Herk; S Sastry Vedam; John W Wong; Ellen Yorke
Journal:  Med Phys       Date:  2006-10       Impact factor: 4.071

7.  The diaphragm as an anatomic surrogate for lung tumor motion.

Authors:  Laura I Cerviño; Alvin K Y Chao; Ajay Sandhu; Steve B Jiang
Journal:  Phys Med Biol       Date:  2009-05-15       Impact factor: 3.609

8.  Adaptive-weighted total variation minimization for sparse data toward low-dose x-ray computed tomography image reconstruction.

Authors:  Yan Liu; Jianhua Ma; Yi Fan; Zhengrong Liang
Journal:  Phys Med Biol       Date:  2012-11-15       Impact factor: 3.609

9.  Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization.

Authors:  Emil Y Sidky; Xiaochuan Pan
Journal:  Phys Med Biol       Date:  2008-08-13       Impact factor: 3.609

10.  Iterative image reconstruction for sparse-view CT using normal-dose image induced total variation prior.

Authors:  Jing Huang; Yunwan Zhang; Jianhua Ma; Dong Zeng; Zhaoying Bian; Shanzhou Niu; Qianjin Feng; Zhengrong Liang; Wufan Chen
Journal:  PLoS One       Date:  2013-11-18       Impact factor: 3.240

View more
  1 in total

1.  Respiratory deformation registration in 4D-CT/cone beam CT using deep learning.

Authors:  Xinzhi Teng; Yingxuan Chen; Yawei Zhang; Lei Ren
Journal:  Quant Imaging Med Surg       Date:  2021-02
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.