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

Abstract

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.

A modern review of the uncertainties in volumetric imaging of respiratory‐induced target motion in lung radiotherapy

“…However, 4D‐CBCT faced obstacles immediately from its onset, such as poor image quality and low contrast due to undersampling streaking artifacts, remediated with long acquisition times and high radiation doses to fulfill the required projection sampling. In order to address these challenges, investigators proposed different solutions such as using prior information, compressed sensing, motion modeling, deformable registration, and a large variety of other software reconstruction techniques to alleviate the lack of sufficient projection data within each phase bin 235–285 ; optimizing the gantry acquisition protocol specific to the patient respiration and/or fiducial markers to adequately sample the patient respiration while minimizing both scan time and dose 286–300 ; and even developing 4D digital tomosynthesis to get time‐resolved motion data in the most efficient manner, albeit at the expense of full volumetric information 301–305 …”

AirNet: Fused analytical and iterative reconstruction with deep neural network regularization for sparse‐data CT

“…Inspired by compressive sensing, 1,2 a class of IR methods has been developed that utilizes hand-crafted priors or transforms for image regularization, such as total variation (TV), [3][4][5] tight frames, [6][7][8] nonlocal methods 9,10 , and low-rank models. 8,[11][12][13][14] Another class of IR methods builds upon data-driven learning from atlases, such as dictionary learning 15 and adaptive tight frames. 16 Inspired by deep learning (DL), 17,18 there have been tremendous developments recently in DL-based AR methods (e.g., Refs.…”

Dynamic gating window technique for the reduction of dosimetric error in respiratory‐gated spot‐scanning particle therapy: An initial phantom study using patient tumor trajectory data

“…Currently, it is difficult to evaluate the possible dosimetric error in advance of the treatment with enough temporal and spatial resolution. A novel technique to reconstruct cine‐4DCT[] with high‐temporal resolution may be applied to determine the gate size by evaluating the actual WEL variation according to the target location.…”