I will start the talk with an overview of Intel Research and its activities, followed by
a more focused discussion of our work around Interactive Search Assisted Diagnosis
(ISAD).
The goal of ISAD is to enable doctors to make better decisions about a given case by
providing a selection of similar annotated cases from a large database. For instance, a
radiologist examining a suspicious mass could study labeled mammograms with similar
conditions and weigh the outcome of their biopsy results before determining whether to
recommend a biopsy. The fundamental challenge in developing ISAD is the identification of
similar cases, not simply in terms of superficial image characteristics, but in a
medically relevant sense. The talk will discuss two applications, for the diagnosis of
breast cancer and of skin cancer.
Speaker Bio：
Dr. Mei Chen is a Senior Scientist at Intel Research Pittsburgh, focusing on medical
image analysis, and large visual collection management and navigation. Prior to joining
Intel Research in 2006, she was a Research Scientist at the Media Technologies Lab in
Hewlett-Packard Laboratories from 2001-2006. While working at HP Labs, she developed
technologies for image communication under low bandwidth, video spatio-temporal
resolution enhancement, legacy film restoration, dynamic range enhancement for digital
photography, and incorporating cinematographic rules for automatic video editing. Her
technologies have been transferred to five HP products that are on the market today.
Before her career at HP Labs, she was a Member of Technical Staff at Sarnoff Corporation
from 1999-2001, where she developed techniques for creating virtual views from real
videos, and for stabilizing unintended motion in home video sequences. From 1996-1999,
during her graduate study at Carnegie Mellon University, she designed a knowledge-guided
3-D deformable registration algorithm for medical images, which automatically extracted
patterns of anatomical variations in the appearances of brain structures, and accurately
registered brain MRIs using the statistics. Dr. Chen is the author or co-author of 27
peer-reviewed technical publications, and 14 U.S. patent applications. She holds a Ph.D.
and a M.S. from the School of Computer Science in Carnegie Mellon University, and a B. S.
and M. S. from Tsinghua University in Beijing, China.
