Skip to main content

VISE Spring Seminar – Ipek Oguz, PhD

Posted by on Friday, March 15, 2019 in News.

VISE Spring Seminar
to be led by

Ipek Oguz,PhD
Assistant Professor of Computer Science
Vanderbilt University










March 28, 2019
Location: Stevenson 5326
Time: 12:25 p.m. start, 12:15 p.m. lunch

Multi-atlas medical image synthesis

Image synthesis is an important problem in medical image analysis, with many applications such as cross-modality synthesis (e.g., input: T1w, desired output: T2w) and dataset harmonization (e.g., input: Siemens T1w, desired output: ‘GE-style’ T1w). We tackle this problem using a multi-atlas intensity fusion approach, borrowing ideas from the popular multi-atlas label fusion literature. We also propose intensity and geometric bias measures in order to quantify inaccuracies of the synthesis procedure when the target image is available. We present results from applications to noise reduction (input: noisy image, output: ‘filtered’ image), automated image in-painting and abnormality detection.

Short Bio:
Dr. Ipek Oguz is an Assistant Professor in the Department of Electrical Engineering and Computer Science at Vanderbilt University. She received her Ph.D. in Computer Science at the University of North Carolina at Chapel Hill. Prior to joining Vanderbilt, she spent time in the Penn Image Computing and Science Laboratory (PICSL) and Center for Biomedical Image Computing and Analytics (CBICA) at the University of Pennsylvania as well as in the Iowa Institute for Biomedical Imaging (IIBI) at the University of Iowa. Her research is in the field of medical image analysis and specifically in the development of novel methodology for quantitative medical image analysis, with applications to neuroimaging, including Huntington’s disease and multiple sclerosis. Her technical interests include graph-based segmentation methods and longitudinal studies. She has co-authored more than 50 peer-reviewed journal and conference publications. She is a program chair for MIDL 2019 (Medical Imaging with Deep Learning) in London; in previous years, she was the organizer of DLF (Deep Learning Fails)  and SASHIMI (Simulation and Synthesis in Medical Imaging) workshops at MICCAI’2018 in Granada, and a co-chair of IPMI 2017 (Information Processing in Medical Imaging).

Tags: , , ,