Biomedical Computing Information Group BCIG

 

BCIG SPEAKER EVENT: “Image Processing Projects at NLM”

Clinical Center (Building 10) Medical Board Room (Room 2C116)

ABSTRACT:

The Communications Engineering Branch of NLM’s Lister Hill Center conducts research and development in digital imaging and machine learning techniques motivated by NLM's mission-critical tasks. This talk will give an overview of ongoing projects, including: automated extraction of bibliographic data from medical articles (to build MEDLINEŽ); imaging and database tools for research into the role of Human Papillomavirus in cervical cancer (in collaboration with NCI); systems for long term preservation of digitized historic documents; content-based image indexing and retrieval (CBIR) techniques applied to spinal x-ray and uterine cervix images; NLP techniques to automatically extract outcome statements from medical articles to augment electronic health records; the design of multimedia-rich interactive publications that hold promise for a new generation of scientific publishing; animated virtual books to bring rare volumes from NLM’s historic collection electronically to the public (“Turning The Pages”).


3:30 - 5:00 pm May 14, 2009

George R. Thoma, Ph.D.
Chief, Communications Engineering Branch
Lister Hill National Center for Biomedical Communications
U.S. National Library of Medicine (NLM)

George Thoma directs and conducts research and development in digital imaging and machine learning techniques motivated by NLM's mission-critical tasks. His branch also maintains archives of large numbers of digitized spine x-rays, uterine cervix and histology images, and annotated document images that are used as ground truth data for algorithm design by the computer science and medical informatics communities worldwide.

Dr. Thoma's previous experience at General Electric, AII Systems, and the University of Pennsylvania had been in developing concepts and systems involving the application of satellites in voice and data communications, video distribution, navigation and surveillance. In the 1970s he helped design and establish satellite earth stations for medical distance learning, video conferencing, and access to remote clinics in Alaska and the northwestern U.S.

He publishes widely in the technical literature (more than 250 papers) and serves regularly as an invited speaker and session chair at various IEEE and SPIE conferences. As General Chair, he organized the 14th IEEE Symposium for Computer-Based Medical Systems held at NIH. He has lectured extensively on these topics at various conferences, seminars and workshops at institutions in this country as well as in Spain, Japan, Holland, Switzerland, U.K., Canada, Brazil, Mexico, United Arab Emirates and India, frequently as an invited speaker. He was sponsored by the U.S. Information Agency to provide technical consultation to Brazilian industrial organizations, and invited by the United Nations Development Programme to present workshops and seminars at the National Informatics Centre and the Indian Space Research Organization in India. As a representative of the Federal Government, he has served on the Maryland Governor's Task Force on High Speed Networks, and currently represents NIH on one of the Internet2 Advisory Councils.

Dr. Thoma earned a B.S. from Swarthmore College, and the M.S. and Ph.D. from the University of Pennsylvania, all in Electrical Engineering. He is a Fellow of the SPIE, the International Society for Optical Engineering. He is listed in American Men and Women of Science, Who's Who in Technology Today and similar publications. He is the recipient of the NIH Merit Award, NLM Regents Award, Federal 100 Award, among many others, including certificates of recognition from NASA and the American College of Physicians.

The Communications Engineering Branch of NLM’s Lister Hill Center conducts research and development in digital imaging and machine learning techniques motivated by NLM's mission-critical tasks. This talk will give an overview of ongoing projects, including: automated extraction of bibliographic data from medical articles (to build MEDLINEŽ); imaging and database tools for research into the role of Human Papillomavirus in cervical cancer (in collaboration with NCI); systems for long term preservation of digitized historic documents; content-based image indexing and retrieval (CBIR) techniques applied to spinal x-ray and uterine cervix images; NLP techniques to automatically extract outcome statements from medical articles to augment electronic health records; the design of multimedia-rich interactive publications that hold promise for a new generation of scientific publishing; animated virtual books to bring rare volumes from NLM’s historic collection electronically to the public (“Turning The Pages”).

Related Links