Noise Reduction of Diffusion Tensor Images by Sparse Representation and Dictionary Learning

Overview

Journal Biomed Eng Online

Publisher Biomed Central

Specialty Biomedical Engineering

Date 2016 Jan 14

PMID 26758740

Citations 2

Authors

Youyong Kong

Yuanjin Li

Jiasong Wu

Huazhong Shu

Affiliations

Soon will be listed here.

Abstract

Background: The low quality of diffusion tensor image (DTI) could affect the accuracy of oncology diagnosis.

Methods: We 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.

Results: The 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.

Conclusions: The proposed approach well removes the noise in the DTI, which has high potential to be applied for clinical oncology applications.

Citing Articles

Classification of breast mass lesions on dynamic contrast-enhanced magnetic resonance imaging by a computer-assisted diagnosis system based on quantitative analysis.

Yin J, Yang J, Jiang Z Oncol Lett. 2019; 17(3):2623-2630.

PMID: 30867727 PMC: 6365960. DOI: 10.3892/ol.2019.9916.

A PSO-Powell Hybrid Method to Extract Fiber Orientations from ODF.

Wu Z, Yu X, Liu Y, Hong M Comput Math Methods Med. 2018; 2018:7680164.

PMID: 29606974 PMC: 5828054. DOI: 10.1155/2018/7680164.

References

Muller H, Kassubek J, Gron G, Sprengelmeyer R, Ludolph A, Kloppel S . Impact of the control for corrupted diffusion tensor imaging data in comparisons at the group level: an application in Huntington disease. Biomed Eng Online. 2014; 13:128. PMC: 4162922. DOI: 10.1186/1475-925X-13-128. View

Elad M, Aharon M . Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans Image Process. 2006; 15(12):3736-45. DOI: 10.1109/tip.2006.881969. View

Manjon J, Thacker N, Lull J, Garcia-Marti G, Marti-Bonmati L, Robles M . Multicomponent MR Image Denoising. Int J Biomed Imaging. 2009; 2009:756897. PMC: 2771160. DOI: 10.1155/2009/756897. View

Kong Y, Wang D, Shi L, Hui S, Chu W . Adaptive distance metric learning for diffusion tensor image segmentation. PLoS One. 2014; 9(3):e92069. PMC: 3961296. DOI: 10.1371/journal.pone.0092069. View

Kong Y, Shi L, Hui S, Wang D, Deng M, Chu W . 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. AJNR Am J Neuroradiol. 2014; 35(8):1621-7. PMC: 7964454. DOI: 10.3174/ajnr.A3912. View

Deng Y, Dai Q, Liu R, Zhang Z, Hu S . Low-rank structure learning via nonconvex heuristic recovery. IEEE Trans Neural Netw Learn Syst. 2014; 24(3):383-96. DOI: 10.1109/TNNLS.2012.2235082. View

Wirestam R, Bibic A, Latt J, Brockstedt S, Stahlberg F . Denoising of complex MRI data by wavelet-domain filtering: application to high-b-value diffusion-weighted imaging. Magn Reson Med. 2006; 56(5):1114-20. DOI: 10.1002/mrm.21036. View

Mandelli M, Berger M, Bucci M, Berman J, Amirbekian B, Henry R . Quantifying accuracy and precision of diffusion MR tractography of the corticospinal tract in brain tumors. J Neurosurg. 2014; 121(2):349-58. DOI: 10.3171/2014.4.JNS131160. View

Chen Y, Yin X, Shi L, Shu H, Luo L, Coatrieux J . Improving abdomen tumor low-dose CT images using a fast dictionary learning based processing. Phys Med Biol. 2013; 58(16):5803-20. DOI: 10.1088/0031-9155/58/16/5803. View

10.

Majumdar A, Ward R, Aboulnasr T . Compressed sensing based real-time dynamic MRI reconstruction. IEEE Trans Med Imaging. 2012; 31(12):2253-66. DOI: 10.1109/TMI.2012.2215921. View

11.

Frandsen J, Hobolth A, Ostergaard L, Vestergaard-Poulsen P, Jensen E . Bayesian regularization of diffusion tensor images. Biostatistics. 2007; 8(4):784-99. DOI: 10.1093/biostatistics/kxm005. View

12.

Chen Y, Huang S, Pickwell-MacPherson E . Frequency-Wavelet Domain Deconvolution for terahertz reflection imaging and spectroscopy. Opt Express. 2010; 18(2):1177-90. DOI: 10.1364/OE.18.001177. View

13.

Ravishankar S, Bresler Y . MR image reconstruction from highly undersampled k-space data by dictionary learning. IEEE Trans Med Imaging. 2010; 30(5):1028-41. DOI: 10.1109/TMI.2010.2090538. View

14.

Zhang J, Richards L, Yarowsky P, Huang H, van Zijl P, Mori S . Three-dimensional anatomical characterization of the developing mouse brain by diffusion tensor microimaging. Neuroimage. 2003; 20(3):1639-48. DOI: 10.1016/s1053-8119(03)00410-5. View

15.

Wiest-Daessle N, Prima S, Coupe P, Morrissey S, Barillot C . Non-local means variants for denoising of diffusion-weighted and diffusion tensor MRI. Med Image Comput Comput Assist Interv. 2007; 10(Pt 2):344-51. PMC: 2129122. DOI: 10.1007/978-3-540-75759-7_42. View

16.

Bao L, Zhu Y, Liu W, Croisille P, Pu Z, Robini M . Denoising human cardiac diffusion tensor magnetic resonance images using sparse representation combined with segmentation. Phys Med Biol. 2009; 54(6):1435-56. DOI: 10.1088/0031-9155/54/6/004. View

17.

Chen Y, Shi L, Feng Q, Yang J, Shu H, Luo L . Artifact suppressed dictionary learning for low-dose CT image processing. IEEE Trans Med Imaging. 2014; 33(12):2271-92. DOI: 10.1109/TMI.2014.2336860. View

18.

Dyrby T, Baare W, Alexander D, Jelsing J, Garde E, Sogaard L . An ex vivo imaging pipeline for producing high-quality and high-resolution diffusion-weighted imaging datasets. Hum Brain Mapp. 2010; 32(4):544-63. PMC: 6870191. DOI: 10.1002/hbm.21043. View

19.

Wee C, Yap P, Zhang D, Wang L, Shen D . Group-constrained sparse fMRI connectivity modeling for mild cognitive impairment identification. Brain Struct Funct. 2013; 219(2):641-56. PMC: 3710527. DOI: 10.1007/s00429-013-0524-8. View

20.

Chen Y, Yang Z, Hu Y, Yang G, Zhu Y, Li Y . Thoracic low-dose CT image processing using an artifact suppressed large-scale nonlocal means. Phys Med Biol. 2012; 57(9):2667-88. DOI: 10.1088/0031-9155/57/9/2667. View