Low-dose CBCT reconstruction via 3D dictionary learning

Dictionary based regularization has shown its potential to improve the low-dose computed tomography (CT) imaging quality. In this paper, we developed a 3D dictionary learning (3D-DL) regularization approach for low-dose cone-beam computed tomography (CBCT) reconstruction. A 3D dictionary learned from standard-dose CT volumes database is used to build the prior term, and an alternating minimization scheme is developed to minimize the objective function. The reconstructed image and its sparse representation are updated alternately in the iterative process. We evaluated the performance of the proposed method using both low-dose and sparse-view CBCT datasets. Qualitative and quantitative results show that the proposed method can lead to a promising improvement of reconstruction quality.

[1]  Jing Wang,et al.  Iterative CBCT reconstruction using Hessian penalty , 2015, Physics in medicine and biology.

[2]  Leslie Ying,et al.  Sparsity-based PET image reconstruction using MRI learned dictionaries , 2014, 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI).

[3]  E. Sidky,et al.  Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization , 2008, Physics in medicine and biology.

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

[5]  L. Feldkamp,et al.  Practical cone-beam algorithm , 1984 .

[6]  Jovan G. Brankov,et al.  Learning based prior for analyzer-based phase contrast image reconstruction , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[7]  Michael Elad,et al.  Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries , 2006, IEEE Transactions on Image Processing.

[8]  Huazhong Shu,et al.  Artifact Suppressed Dictionary Learning for Low-Dose CT Image Processing , 2014, IEEE Transactions on Medical Imaging.

[9]  Xuanqin Mou,et al.  Dictionary learning based low-dose x-ray CT reconstruction using a balancing principle , 2014, Optics & Photonics - Optical Engineering + Applications.

[10]  J. Coatrieux,et al.  Improving abdomen tumor low-dose CT images using a fast dictionary learning based processing , 2013, Physics in medicine and biology.

[11]  A. Kak,et al.  Simultaneous Algebraic Reconstruction Technique (SART): A Superior Implementation of the Art Algorithm , 1984, Ultrasonic imaging.

[12]  Lei Zhang,et al.  Low-Dose X-ray CT Reconstruction via Dictionary Learning , 2012, IEEE Transactions on Medical Imaging.

[13]  B. Movsas,et al.  Dose delivered from Varian's CBCT to patients receiving IMRT for prostate cancer , 2007, Physics in medicine and biology.

[14]  Michael Elad,et al.  Applications of Sparse Representation and Compressive Sensing , 2010, Proc. IEEE.

[15]  J. Wong,et al.  Flat-panel cone-beam computed tomography for image-guided radiation therapy. , 2002, International journal of radiation oncology, biology, physics.

[16]  Tom Goldstein,et al.  The Split Bregman Method for L1-Regularized Problems , 2009, SIAM J. Imaging Sci..

[17]  Jeffrey A. Fessler,et al.  Statistical image reconstruction for polyenergetic X-ray computed tomography , 2002, IEEE Transactions on Medical Imaging.