CNEL Alumnus: Rui Yan


Former student webpage:
About Me

I am a PhD candidate under the guidance of Dr. Principe, with my master and bachelar got in 2003 and 1999, at University of Florida and Beijing University of Posts and Telecommunications, respectively.
 
My Research Interests

I am in the area of signal and image processing for medical imaging, where my special interest is at signal processing in competitive learning, multiple models, and space representation, image processing in complexity and quality measure and MRI images. Right now we are making progress in three distinct areas, which are phased-array MRI image reconstruction, functional region mapping of fMRI images and objective image complexity meausre.
 
Research Goals

We have multiple research goals with parallel achievements, where they are image reconstruction of phased-array magnetic
resonance imaging (MRI), fMRI imaging, and image complexity measure, respectively.

Magnetic Resonance Imaging~(MRI) is an imaging technique using radiofrequency waves in
a strong magnetic field mostly for inner human body examination. This method can
provide images with better quality than regular x-rays and CAT scans for soft-tissue structure
inside body. Thus it is widely used as a noninvasive diagnostic tool by the medical
community for detecting coronary arteries, brain diseases, and strokes, etc. in the past
few decades.

In the last decade, MRI imaging is subdivided into two main categories. One technique to image time-varying
processes of the image series, is called functional MRI (fMRI). It gives functional
regions of the different external stimulus inside the brain. Therefore fMRI
provides a method to understand the connection between brain structures and their functions.
We are interested in the not only the spatial pixel distribution but also the temporal response
for such pixels given the alcohol stimulus.

Another research aspect focus on fast imaging method with multiple receiver coils. The increased equipment
complexity increases the signal-to-noise-ratio~(SNR) by approximately combining the coil images from the
different coils. Thus for a certain SNR image quality level, phased-array imaging techniques can dramatically
reduce the scanning time, which has the benefits of reducing the motion artifacts of image. However, the
prevalent sum-of-squares~(SoS) reconstruction has some disadvantage. In our research, an adaptive signal processing
framework is applied to phased array MRI. The advantage of this method is that there's no need for prior assumption
for any distribution and no need to estimate the coil sensitivities and the spatial anisotropy of the coils is estimated
from image pixels.

Image complexity is an interesting topic which is used in texture extraction. Recently it also absorbs
interest in fMRI research. However, it is still an open problem since no exact mathematical definition
exists for this problem. The reason lies that image complexity is more a subjective measure other than a
objective statistical measure. It is actually a system identification problem where the inner system which
has the visual complexity effect still needs further research. We are interested in proposing a mathematical
description of the image complexity problem.
Picture
Links

 
CNEL Papers
Dissertation
1Rui Yan,"COMPETITIVE MIXTURE OF LOCAL LINEAR EXPERTS FOR MAGNETIC RESONANCE IMAGING", May 2006, University of Florida.(author PDF)
 
Journal Papers
1R. Yan, D. Erdogmus, E.G. Larsson, D. M. Peterson, J.C. Principe, J.R. Fitzsimmons, "Competitive Mixture of Local Linear Experts for Phased-Array Magnetic Resonance Imaging," Trans. on Medical Imaging. (Submitted)
2R. Yan, S-P Kim, G. He, D. Erdogmus, Y. Rao, Y. Liu, "Separating Spatial and Temporal Activation Patterns in fMRI using Nonnegative Matrix Factorization," NeuroComputing. (Submitted)
3D. Erdogmus, R. Yan , E.G. Larsson, J.C. Principe, J.R. Fitzsimmons, "Image Construction Methods for Phased Array Magnetic Resonance Imaging", Journal of Magnetic Resonance Imaging, Vol. 20, No. N/A, pp. 306-314, Aug. 2004 (author PDF)
4D. Erdogmus, E.G. Larsson, R. Yan, J.C. Principe, J.R. Fitzsimmons, "Asymptotic SNR-Performance of Some Image Combination Techniques for Phased-Array MRI", Signal Processing, Vol. 84, No. 6, pp. 997-1003, 2004 (author PDF)
5D. Erdogmus, E.G. Larsson, R. Yan, Jose C. Principe, J.R. Fitzsimmons, "Measuring the Signal-to-Noise-Ratio in Magnetic Resonance Imaging: A Caveat", Signal Processing, Vol. 84, No. 6, pp. 1035-1040, 2004 (author PDF)
6Erik G. Larsson, Deniz Erdogmus, Rui Yan, Jose C. Principe, Jeffrey R. Fitzsimmons, "SNR-optimality of Sum-of-Squares Reconstruction for Phased-Array Magnetic Resonance Imaging", Journal of Magnetic Resonance, Vol. 163, No. 1, pp. 121-123, Jan. 2003 (author PDF)
 
Conference Papers
1R. Yan, G. He, D. Erdogmus, S-P Kim, J.C. Principe, Y. Liu, "Separating Spatial and Temporal Activation Patterns in fMRI Using Competitive Subspace Projection," Intl. Conf. on Acoustics, Speech, and Signal Processing.(Submitted)
2J. Fitzsimmons, R. Yan, D. Erdogmus, "MRI Image Reconstruction via Homomorphic Signal Processing," Intl. Conf. on Acoustics, Speech, and Signal Processing.(Submitted)
3D. Erdogmus, R. Yan, E.G. Larsson, J.C. Principe, J.R. Fitzsimmons, "MIXTURE OF COMPETITIVE LINEAR MODELS FOR PHASED-ARRAY MAGNETIC," Intl. Conf. on Acoustics, Speech, and Signal Processing.(Accepted) (author PDF)
4R. Yan, D. Erdogmus, E.G. Larsson, J.C. Principe, J.R. Fitzsimmons, "Image Combination for High-Field Phased-Array MRI", Intl. Conf. on Acoustics, Speech, and Signal Processing, pp. 1-4, Apr. 2003 (author PDF)
 

Copyright Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

People

Research

Publications

Courses

Communications

Search CNEL