Shuiping Gou1, Yueyue Wang2, Jiaolong Wu2, Percy Lee3, Ke Sheng3. 1. Key Lab of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi'an, Shaanxi 710071, China and Department of Radiation Oncology, University of California, Los Angeles, California 90095. 2. Key Lab of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi'an, Shaanxi 710071, China. 3. Department of Radiation Oncology, University of California, Los Angeles, California 90095.
Abstract
PURPOSE: Lung dynamic MRI (dMRI) has emerged to be an appealing tool to quantify lung motion for both planning and treatment guidance purposes. However, this modality can result in blurry images due to intrinsically low signal-to-noise ratio in the lung and spatial/temporal interpolation. The image blurring could adversely affect the image processing that depends on the availability of fine landmarks. The purpose of this study is to reduce dMRI blurring using image postprocessing. METHODS: To enhance the image quality and exploit the spatiotemporal continuity of dMRI sequences, a low-rank decomposition and dictionary learning (LDDL) method was employed to deblur lung dMRI and enhance the conspicuity of lung blood vessels. Fifty frames of continuous 2D coronal dMRI frames using a steady state free precession sequence were obtained from five subjects including two healthy volunteer and three lung cancer patients. In LDDL, the lung dMRI was decomposed into sparse and low-rank components. Dictionary learning was employed to estimate the blurring kernel based on the whole image, low-rank or sparse component of the first image in the lung MRI sequence. Deblurring was performed on the whole image sequences using deconvolution based on the estimated blur kernel. The deblurring results were quantified using an automated blood vessel extraction method based on the classification of Hessian matrix filtered images. Accuracy of automated extraction was calculated using manual segmentation of the blood vessels as the ground truth. RESULTS: In the pilot study, LDDL based on the blurring kernel estimated from the sparse component led to performance superior to the other ways of kernel estimation. LDDL consistently improved image contrast and fine feature conspicuity of the original MRI without introducing artifacts. The accuracy of automated blood vessel extraction was on average increased by 16% using manual segmentation as the ground truth. CONCLUSIONS: Image blurring in dMRI images can be effectively reduced using a low-rank decomposition and dictionary learning method using kernels estimated by the sparse component.
PURPOSE: Lung dynamic MRI (dMRI) has emerged to be an appealing tool to quantify lung motion for both planning and treatment guidance purposes. However, this modality can result in blurry images due to intrinsically low signal-to-noise ratio in the lung and spatial/temporal interpolation. The image blurring could adversely affect the image processing that depends on the availability of fine landmarks. The purpose of this study is to reduce dMRI blurring using image postprocessing. METHODS: To enhance the image quality and exploit the spatiotemporal continuity of dMRI sequences, a low-rank decomposition and dictionary learning (LDDL) method was employed to deblur lungdMRI and enhance the conspicuity of lung blood vessels. Fifty frames of continuous 2D coronal dMRI frames using a steady state free precession sequence were obtained from five subjects including two healthy volunteer and three lung cancerpatients. In LDDL, the lung dMRI was decomposed into sparse and low-rank components. Dictionary learning was employed to estimate the blurring kernel based on the whole image, low-rank or sparse component of the first image in the lung MRI sequence. Deblurring was performed on the whole image sequences using deconvolution based on the estimated blur kernel. The deblurring results were quantified using an automated blood vessel extraction method based on the classification of Hessian matrix filtered images. Accuracy of automated extraction was calculated using manual segmentation of the blood vessels as the ground truth. RESULTS: In the pilot study, LDDL based on the blurring kernel estimated from the sparse component led to performance superior to the other ways of kernel estimation. LDDL consistently improved image contrast and fine feature conspicuity of the original MRI without introducing artifacts. The accuracy of automated blood vessel extraction was on average increased by 16% using manual segmentation as the ground truth. CONCLUSIONS: Image blurring in dMRI images can be effectively reduced using a low-rank decomposition and dictionary learning method using kernels estimated by the sparse component.
Authors: Christian Plathow; Sebastian Ley; Christian Fink; Michael Puderbach; Waldemar Hosch; Astrid Schmähl; Jürgen Debus; Hans-Ulrich Kauczor Journal: Int J Radiat Oncol Biol Phys Date: 2004-07-15 Impact factor: 7.038
Authors: Mette K Stam; Sjoerd P M Crijns; Bernard A Zonnenberg; Maurits M Barendrecht; Marco van Vulpen; Jan J W Lagendijk; Bas W Raaymakers Journal: Phys Med Biol Date: 2012-10-03 Impact factor: 3.609
Authors: Erik Tryggestad; Aaron Flammang; Sarah Han-Oh; Russell Hales; Joseph Herman; Todd McNutt; Teboh Roland; Steven M Shea; John Wong Journal: Med Phys Date: 2013-05 Impact factor: 4.071
Authors: Jing Cai; Paul W Read; James M Larner; David R Jones; Stanley H Benedict; Ke Sheng Journal: Int J Radiat Oncol Biol Phys Date: 2008-11-15 Impact factor: 7.038