New Methods of Feature Extraction and Alignment with Biomedical Applications
University Kiel, Germany
Place: 3105 Engineering
Host: Anil Jain
Abstract: Thanks to the fast development of new technologies, it is now possible to obtain large-scale biological and medical data in a high-throughput fashion. The vast amount of data not only opens a door of new concepts such as personalized therapy and early diagnosis of diseases (e.g. cancer), but also raises many challenging questions, such as how to extract useful information from data robustly and efficiently in a quantitative manner and how to figure out the functioning principles of biological systems based on the measurements of possibly interacting sub-systems.
In this talk I would like to address two problems in the context of developing and applying new signal processing techniques in biomedical research: 1. Efficient feature extraction using new steerable filters; 2. Reducing feature variation for better cancer-related biomarker discovery from mass spectrometry data. In the first part, I will focus on extracting local orientation information from images. This is still a difficult task even when we apply the newest idea of steerable filter. By attacking this problem from the standpoint of the sampling theory, we propose a novel set of filters based on Gaussian functions both in 2-D and 3-D space. The new filters achieve the lower bound of the uncertainty principle and provide higher orientation resolution yet with lower computational complexity than current steerable filters. Comparisons with related approaches and different applications such as facial analysis are shown.
The second part of the talk is about building mutual correspondence among features from multiple mass spectrometry data sets for the purpose of cancer-related biomarker discovery. The key point is to find a standard template from multiple feature sets (which are influenced by noise as well as biological and experimental variations) for matching purpose. After reviewing current methods, I will introduce a new approach based on the concept of diffusion and scale space representation. Then, I will validate our new approach using two different methods and compare our method with current methods. I will finish the talk by discussing some research topics planned for the future.
Biography: Weichuan Yu received his Ph.D. degree in Computer Vision and Image Analysis from University Kiel, Germany in 2001. He was a postdoctoral associate at Yale University from 2001 to 2004. Currently, he is a research faculty member in the Center for Statistical Genomics and Proteomics at Yale University. He is interested in computational analysis problems with biological and medical applications. He has published papers on a variety of topics including bioinformatics, computational biology, biomedical imaging, signal processing, pattern recognition and computer vision. He was the recipient of the DAAD (German Academic Exchange Center) Fellowship.