4D-AirNet: a temporally-resolved CBCT slice reconstruction method synergizing analytical and iterative method with deep learning

Four-dimensional (4D) cone-beam CT (CBCT) reconstructs temporally-resolved phases of 3D volumes often with the same amount of projection data that are meant for reconstructing a single 3D volume. 4D CBCT is a sparse-data problem that is very challenging for high-quality 4D CBCT image reconstruction. Here we develop a new method, namely 4D-AirNet, that synergizes analytical and iterative method with deep learning for high-quality temporally-resolved CBCT slice reconstruction. 4D-AirNet is an unrolling method using the optimization framework of fused analytical and iterative reconstruction (AIR), which is based on proximal forward-backward splitting (PFBS). Three different strategies are developed for 4D-AirNet: random-phase (RP), prior-guided (PG), and all-phase (AP). RP-AirNet and PG-AirNet utilize phase-by-phase training and reconstruction, while PG-AirNet also uses a prior image reconstructed with all-phase projection data. Dense connectivity is built into 4D-AirNet networks for improved reconstruction quality. In contrast, AP-AirNet trains and reconstructs all phases simultaneously. In addition, the joint regularization method of DL and conventional spatiotemporal total variation (TV) is investigated. 4D-AirNet methods were evaluated in comparison with conventional iterative (TV) and deep learning (LEARN) methods, using simulated 2D-t CBCT scans from a lung dataset with various sparse-data levels. The reconstruction results suggest 4D-AirNet methods outperform TV and LEARN, and AP-AirNet provides the best reconstruction quality overall.

[1]  Hu Chen,et al.  LEARN: Learned Experts’ Assessment-Based Reconstruction Network for Sparse-Data CT , 2017, IEEE Transactions on Medical Imaging.

[2]  Xuanqin Mou,et al.  Artifacts reduction method for phase-resolved Cone-Beam CT (CBCT) images via a prior-guided CNN , 2019, Medical Imaging.

[3]  Yang Chen,et al.  4D-CBCT Reconstruction via Motion Compensataion Learning Induced Sparse Tensor Constraint , 2019, 2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).

[4]  Geoffrey D Hugo,et al.  Data‐driven respiratory motion compensation for four‐dimensional cone‐beam computed tomography (4D‐CBCT) using groupwise deformable registration , 2018, Medical physics.

[5]  Liyuan Chen,et al.  U-net-based Deformation Vector Field Estimation for Motion-Compensated 4D-CBCT Reconstruction. , 2020, Medical physics.

[6]  Steve B. Jiang,et al.  4D Computed Tomography Reconstruction from Few-Projection Data via Temporal Non-local Regularization , 2010, MICCAI.

[7]  Fang-Fang Yin,et al.  Augmentation of CBCT Reconstructed From Under-Sampled Projections Using Deep Learning , 2019, IEEE Transactions on Medical Imaging.

[8]  Xun Jia,et al.  Four-dimensional cone beam CT reconstruction and enhancement using a temporal nonlocal means method. , 2012, Medical physics.

[9]  Simon Rit,et al.  Motion-aware temporal regularization for improved 4D cone-beam computed tomography , 2016, Physics in medicine and biology.

[10]  Fang-Fang Yin,et al.  Principal component reconstruction (PCR) for cine CBCT with motion learning from 2D fluoroscopy , 2018, Medical physics.

[11]  L. Xing,et al.  4D cone beam CT via spatiotemporal tensor framelet. , 2012, Medical physics.

[12]  Zhaoying Bian,et al.  High quality 4D cone-beam CT reconstruction using motion-compensated total variation regularization , 2017, Physics in medicine and biology.

[13]  Hao Gao.  Fast parallel algorithms for the x-ray transform and its adjoint. , 2012, Medical physics.

[14]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[15]  Hao Gao,et al.  Fused analytical and iterative reconstruction (AIR) via modified proximal forward–backward splitting: a FDK-based iterative image reconstruction example for CBCT , 2015, Physics in medicine and biology.

[16]  Xuejun Gu,et al.  Simultaneous motion estimation and image reconstruction (SMEIR) for 4D cone-beam CT , 2013, 2013 IEEE Nuclear Science Symposium and Medical Imaging Conference (2013 NSS/MIC).

[17]  Patrick L. Combettes,et al.  Signal Recovery by Proximal Forward-Backward Splitting , 2005, Multiscale Model. Simul..

[18]  Hongkai Zhao,et al.  Robust principal component analysis-based four-dimensional computed tomography , 2011, Physics in medicine and biology.

[19]  Hao Yan,et al.  A hybrid reconstruction algorithm for fast and accurate 4D cone-beam CT imaging. , 2014, Medical physics.

[20]  Jun Zhao,et al.  Reconstruction of a high-quality volumetric image and a respiratory motion model from patient CBCT projections. , 2019, Medical physics.

[21]  Jong Chul Ye,et al.  Framing U-Net via Deep Convolutional Framelets: Application to Sparse-View CT , 2017, IEEE Transactions on Medical Imaging.

[22]  K. Klingenbeck,et al.  A general framework and review of scatter correction methods in cone beam CT. Part 2: scatter estimation approaches. , 2011, Medical physics.

[23]  Yi Zhang,et al.  AirNet: Fused Analytical and Iterative Reconstruction with Deep Neural Network Regularization for Sparse-Data CT. , 2020, Medical physics.

[24]  Jie Tang,et al.  Prior image constrained compressed sensing (PICCS): a method to accurately reconstruct dynamic CT images from highly undersampled projection data sets. , 2008, Medical physics.

[25]  Mathias Unberath,et al.  Deep Learning Computed Tomography: Learning Projection-Domain Weights From Image Domain in Limited Angle Problems , 2018, IEEE Transactions on Medical Imaging.

[26]  Klaus Klingenbeck,et al.  A general framework and review of scatter correction methods in x-ray cone-beam computerized tomography. Part 1: Scatter compensation approaches. , 2011, Medical physics.

[27]  Fang-Fang Yin,et al.  A technique for estimating 4D-CBCT using prior knowledge and limited-angle projections. , 2013, Medical physics.

[28]  Lei Xing,et al.  Enhanced 4D cone-beam CT with inter-phase motion model. , 2007, Medical physics.

[29]  Manuchehr Soleimani,et al.  A general method for motion compensation in x-ray computed tomography. , 2017, Physics in medicine and biology.

[30]  Jan-Jakob Sonke,et al.  Directional sinogram interpolation for motion weighted 4D cone-beam CT reconstruction. , 2017, Physics in medicine and biology.

[31]  Xuanqin Mou,et al.  High-quality Initial Image-guided 4D CBCT Reconstruction. , 2020, Medical physics.

[32]  S. Rit,et al.  On-the-fly motion-compensated cone-beam CT using an a priori model of the respiratory motion. , 2009, Medical physics.

[33]  Stefan Sawall,et al.  Iterative 4D cardiac micro-CT image reconstruction using an adaptive spatio-temporal sparsity prior , 2012, Physics in medicine and biology.

[34]  W. Zbijewski,et al.  Motion compensation in extremity cone-beam CT using a penalized image sharpness criterion , 2017, Physics in medicine and biology.

[35]  Chun-Chien Shieh,et al.  Learning from our neighbours: a novel approach on sinogram completion using bin-sharing and deep learning to reconstruct high quality 4DCBCT , 2018, Medical Imaging.

[36]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[37]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[38]  Steve B. Jiang,et al.  Cine Cone Beam CT Reconstruction Using Low-Rank Matrix Factorization: Algorithm and a Proof-of-Principle Study , 2012, IEEE Transactions on Medical Imaging.