Noise reduction of diffusion tensor images by sparse representation and dictionary learning

BackgroundThe low quality of diffusion tensor image (DTI) could affect the accuracy of oncology diagnosis.MethodsWe present a novel sparse representation based denoising method for three dimensional DTI by learning adaptive dictionary with the context redundancy between neighbor slices. In this study, the context redundancy among the adjacent slices of the diffusion weighted imaging volumes is utilized to train sparsifying dictionaries. Therefore, higher redundancy could be achieved for better description of image with lower computation complexity. The optimization problem is solved efficiently using an iterative block-coordinate relaxation method.ResultsThe effectiveness of our proposed method has been assessed on both simulated and real experimental DTI datasets. Qualitative and quantitative evaluations demonstrate the performance of the proposed method on the simulated data. The experiments on real datasets with different b-values also show the effectiveness of the proposed method for noise reduction of DTI.ConclusionsThe proposed approach well removes the noise in the DTI, which has high potential to be applied for clinical oncology applications.

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

[2]  Nicholas Ayache,et al.  Clinical DT-MRI estimation, smoothing and fiber tracking with Log-Euclidean metrics , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

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

[4]  Santiago Aja-Fernández,et al.  DWI filtering using joint information for DTI and HARDI , 2010, Medical Image Anal..

[5]  Pierrick Coupé,et al.  Non-Local Means Variants for Denoising of Diffusion-Weighted and Diffusion Tensor MRI , 2007, MICCAI.

[6]  Emma Pickwell-MacPherson,et al.  Frequency-Wavelet Domain Deconvolution for terahertz reflection imaging and spectroscopy. , 2010, Optics express.

[7]  Youyong Kong,et al.  Discriminative Clustering and Feature Selection for Brain MRI Segmentation , 2015, IEEE Signal Processing Letters.

[8]  Daoqiang Zhang,et al.  Group-constrained sparse fMRI connectivity modeling for mild cognitive impairment identification , 2013, Brain Structure and Function.

[9]  Jaimie M. Henderson,et al.  Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention , 2006 .

[10]  Qionghai Dai,et al.  Low-Rank Structure Learning via Nonconvex Heuristic Recovery , 2010, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Stefan Klöppel,et al.  Impact of the control for corrupted diffusion tensor imaging data in comparisons at the group level: an application in Huntington disease , 2014, Biomedical engineering online.

[12]  Qionghai Dai,et al.  Noisy Depth Maps Fusion for Multiview Stereo Via Matrix Completion , 2012, IEEE Journal of Selected Topics in Signal Processing.

[13]  P. Croisille,et al.  Denoising human cardiac diffusion tensor magnetic resonance images using sparse representation combined with segmentation , 2009, Physics in medicine and biology.

[14]  Hao Huang,et al.  Three-dimensional anatomical characterization of the developing mouse brain by diffusion tensor microimaging , 2003, NeuroImage.

[15]  Rabab Kreidieh Ward,et al.  Compressed Sensing Based Real-Time Dynamic MRI Reconstruction , 2012, IEEE Transactions on Medical Imaging.

[16]  Jianhua Ma,et al.  Nonlocal Prior Bayesian Tomographic Reconstruction , 2008, Journal of Mathematical Imaging and Vision.

[17]  Asger Hobolth,et al.  Bayesian regularization of diffusion tensor images. , 2006, Biostatistics.

[18]  Nir A. Sochen,et al.  Fast Invariant Riemannian DT-MRI Regularization , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[19]  W. Baaré,et al.  An ex vivo imaging pipeline for producing high‐quality and high‐resolution diffusion‐weighted imaging datasets , 2011, Human brain mapping.

[20]  Youyong Kong,et al.  Sparse Coding-Inspired Optimal Trading System for HFT Industry , 2015, IEEE Transactions on Industrial Informatics.

[21]  Shang-Hong Lai,et al.  Learning component-level sparse representation using histogram information for image classification , 2011, 2011 International Conference on Computer Vision.

[22]  Lin Shi,et al.  Adaptive Distance Metric Learning for Diffusion Tensor Image Segmentation , 2014, PloS one.

[23]  Yoram Bresler,et al.  MR Image Reconstruction From Highly Undersampled k-Space Data by Dictionary Learning , 2011, IEEE Transactions on Medical Imaging.

[24]  Norbert Schuff,et al.  Denoising diffusion-weighted MR magnitude image sequences using low rank and edge constraints , 2012, 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI).

[25]  M. Berger,et al.  Quantifying accuracy and precision of diffusion MR tractography of the corticospinal tract in brain tumors. , 2014, Journal of neurosurgery.

[26]  F. Ståhlberg,et al.  Denoising of complex MRI data by wavelet‐domain filtering: Application to high‐b‐value diffusion‐weighted imaging , 2006, Magnetic resonance in medicine.

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

[28]  Christine Toumoulin,et al.  Thoracic low-dose CT image processing using an artifact suppressed large-scale nonlocal means , 2012, Physics in medicine and biology.

[29]  D Wang,et al.  Variation in Anisotropy and Diffusivity along the Medulla Oblongata and the Whole Spinal Cord in Adolescent Idiopathic Scoliosis: A Pilot Study Using Diffusion Tensor Imaging , 2014, American Journal of Neuroradiology.

[30]  Neil A. Thacker,et al.  Multicomponent MR Image Denoising , 2009, Int. J. Biomed. Imaging.