İ.Ş. Yetik; "Automated Prostate Cancer Localization with..."
  • FENS
  • İ.Ş. Yetik; "Automated Prostate Cancer Localization with..."

You are here

Faculty of Engineering and Natural Sciences


Automated Prostate Cancer Localization with Multispectral MRI: Challenges and Solutions İmam Şamil Yetik
    Medical Imaging Research Center
Illinois Institute of Technology 


Prostate cancer is one of the main causes of death for men in the United States. The disease has also severe side effects such us urinary and sexual dysfunctions. Fortunately, the survival rate for early-diagnosed patients is relatively high. Therefore, in vivo imaging plays an important role in the treatment by guiding biopsy, radiotherapy, and surgery. Recently, high-resolution multispectral magnetic resonance imaging (MRI) has been proposed as a promising alternative to the trans-rectal ultrasound (TRUS) for the detection and localization of prostate cancer. Currently, fusing the information from multispectral MR images for automated cancer localization is an active research area. In this talk, we explain the challenges of automated prostate cancer localization with multispectral MRI, and present an overview of the solutions we propose. The talk presents various construction blocks of a fully automated cancer localization method including segmentation of the prostate, reconstruction of high-quality parametric images, and advanced cancer segmentation tools such as advanced vector machines and fuzzy Markov random fields. Successful applications of the proposed methods to data sets from biopsy confirmed cancer patients are also presented as well as an outlook of prostate cancer localization with multispectral MRI.

İmam Şamil Yetik received his BS, MS, and PhD degrees from Boğaziçi University, Bilkent University, and University of Illinois at Chicago respectively. After his postdoc positions at University of Illinois at Chicago and University of California at Davis, he has joined the Medical Imaging Research Center at the Illinois Institute of Technology as an Assistant Professor. His research interests include signal and image processing techniques with applications to biomedicine. Dr. Yetik is a senior member of IEEE and authored/coauthored over 45 publications in his research area.
July 15, 2010, 14:00-15:00, FENS G029