K-SVD for HARDI denoising

Noise is an important concern in high-angular resolution diffusion imaging studies because it can lead to errors in downstream analyses of white matter structure. To address this issue, we investigate a new approach for denoising diffusion-weighted data sets based on the K-SVD algorithm. We analyze its characteristics using both simulated and biological data and compare its performance with existing methods. Our results show that K-SVD provides robust and effective noise reduction and is practical for use in high-volume applications.

• Type: Journal
• Year: 2011
• Where: ISBI
• Authors: Vishal Patel, Yonggang Shi, Paul M. Thompson, Arthur W. Toga
• Keywords: Biological Data, Diffusion Imaging, ISBI 2011, Medical Imaging, Volume Applications