Skip to main content

Principal component reconstruction (PCR) for cine CBCT with motion learning from 2D fluoroscopy.

Publication ,  Journal Article
Gao, H; Zhang, Y; Ren, L; Yin, F-F
Published in: Med Phys
January 2018

PURPOSE: This work aims to generate cine CT images (i.e., 4D images with high-temporal resolution) based on a novel principal component reconstruction (PCR) technique with motion learning from 2D fluoroscopic training images. METHODS: In the proposed PCR method, the matrix factorization is utilized as an explicit low-rank regularization of 4D images that are represented as a product of spatial principal components and temporal motion coefficients. The key hypothesis of PCR is that temporal coefficients from 4D images can be reasonably approximated by temporal coefficients learned from 2D fluoroscopic training projections. For this purpose, we can acquire fluoroscopic training projections for a few breathing periods at fixed gantry angles that are free from geometric distortion due to gantry rotation, that is, fluoroscopy-based motion learning. Such training projections can provide an effective characterization of the breathing motion. The temporal coefficients can be extracted from these training projections and used as priors for PCR, even though principal components from training projections are certainly not the same for these 4D images to be reconstructed. For this purpose, training data are synchronized with reconstruction data using identical real-time breathing position intervals for projection binning. In terms of image reconstruction, with a priori temporal coefficients, the data fidelity for PCR changes from nonlinear to linear, and consequently, the PCR method is robust and can be solved efficiently. PCR is formulated as a convex optimization problem with the sum of linear data fidelity with respect to spatial principal components and spatiotemporal total variation regularization imposed on 4D image phases. The solution algorithm of PCR is developed based on alternating direction method of multipliers. RESULTS: The implementation is fully parallelized on GPU with NVIDIA CUDA toolbox and each reconstruction takes about a few minutes. The proposed PCR method is validated and compared with a state-of-art method, that is, PICCS, using both simulation and experimental data with the on-board cone-beam CT setting. The results demonstrated the feasibility of PCR for cine CBCT and significantly improved reconstruction quality of PCR from PICCS for cine CBCT. CONCLUSION: With a priori estimated temporal motion coefficients using fluoroscopic training projections, the PCR method can accurately reconstruct spatial principal components, and then generate cine CT images as a product of temporal motion coefficients and spatial principal components.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Med Phys

DOI

EISSN

2473-4209

Publication Date

January 2018

Volume

45

Issue

1

Start / End Page

167 / 177

Location

United States

Related Subject Headings

  • Nuclear Medicine & Medical Imaging
  • Movement
  • Machine Learning
  • Image Processing, Computer-Assisted
  • Four-Dimensional Computed Tomography
  • Fluoroscopy
  • Cone-Beam Computed Tomography
  • Artifacts
  • 5105 Medical and biological physics
  • 4003 Biomedical engineering
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Gao, H., Zhang, Y., Ren, L., & Yin, F.-F. (2018). Principal component reconstruction (PCR) for cine CBCT with motion learning from 2D fluoroscopy. Med Phys, 45(1), 167–177. https://doi.org/10.1002/mp.12671
Gao, Hao, Yawei Zhang, Lei Ren, and Fang-Fang Yin. “Principal component reconstruction (PCR) for cine CBCT with motion learning from 2D fluoroscopy.Med Phys 45, no. 1 (January 2018): 167–77. https://doi.org/10.1002/mp.12671.
Gao H, Zhang Y, Ren L, Yin F-F. Principal component reconstruction (PCR) for cine CBCT with motion learning from 2D fluoroscopy. Med Phys. 2018 Jan;45(1):167–77.
Gao, Hao, et al. “Principal component reconstruction (PCR) for cine CBCT with motion learning from 2D fluoroscopy.Med Phys, vol. 45, no. 1, Jan. 2018, pp. 167–77. Pubmed, doi:10.1002/mp.12671.
Gao H, Zhang Y, Ren L, Yin F-F. Principal component reconstruction (PCR) for cine CBCT with motion learning from 2D fluoroscopy. Med Phys. 2018 Jan;45(1):167–177.

Published In

Med Phys

DOI

EISSN

2473-4209

Publication Date

January 2018

Volume

45

Issue

1

Start / End Page

167 / 177

Location

United States

Related Subject Headings

  • Nuclear Medicine & Medical Imaging
  • Movement
  • Machine Learning
  • Image Processing, Computer-Assisted
  • Four-Dimensional Computed Tomography
  • Fluoroscopy
  • Cone-Beam Computed Tomography
  • Artifacts
  • 5105 Medical and biological physics
  • 4003 Biomedical engineering