Sameer Antani, Ph.D. |
![]() ![]() |
Staff Scientist
National Library of Medicine
Communications Engineering Branch/MSC 3824
Bldg. 38A, Room 10S1010
8600 Rockville Pike
Bethesda, MD 20894 USA
(301) 435-3218
Dr. Sameer Antani is a Computer Scientist (Staff Scientist) with the Lister Hill National Center for Biomedical Communications, an intramural R&D division of the National Library of Medicine, at the National Institutes of Health. He conducts research on topics in content-based image retrieval, medical multimedia databases, next-generation interactive documents, and advanced multimodal medical document retrieval. He earned his Master of Engineering and PhD in Computer Science and Engineering from the Pennsylvania State University in 1998 and 2001, respectively. He earned his Bachelors degree in Computer Engineering from the University of Pune, India (Pune Institute of Computer Technology), in 1994. Dr. Antani is a member of the SPIE, IEEE and the IEEE Computer Society.
Current Projects
Biomedical Imaging: The projects include research in advanced medical image analysis, content-based image retrieval (CBIR), and multimedia medical datatbases. Goals include algorithm design, development of standalone prototype software, data collection, evaluation, and validation. Steps for enabling capability for retrieval of medically/pathologically relevant images in response to hybrid (image, text) queries include research into innovative methods for image segmentation, image compression, data transmission, visualization and collaboration with researchers with interests in natural language processing. Other research aspects include development of collaborative software that enables sharing of software and data with other researchers in a distributed computing paradigm, and building on research results to create innovative applications. I am a lead researcher in this project.
Interactive Publications (IP): Multimedia documents have been in existence for a decade or more, and in common usage they refer to entities that consist of text that links to images and video clips. More often than not, the latter media types reside in databases apart from the text, and are accessed independently of the text, often leading to a loss of context. The challenge in this project is to create a comprehensive, self-contained and platform-independent multimedia-rich “interactive publication.” By self-contained we mean the document is either one large file embedded with all media objects, or a ‘folder’ in which the files are tightly linked. This document, of either ‘embedded’ or ‘folder’ type, could contain many media objects: text, video, audio, bitmapped images, spreadsheets, presentation graphics, or animation sequences. While using such a document, the reader should be able to: (a) view any of these objects on the screen; (b) hyperlink from one object to another; (c) interact i th the objects in the sense of exercising control over them (e.g., start and stop video); and (d) reuse the media content for analysis and presentation. It is the last objective that differentiates “traditional” multimedia documents from an “interactive publication.” I am a researcher on this project and work closely with my fellow researchers and developers.
Image and Text Integration (ITI): The goal of this project is to develop robust algorithms to augment the repository of facts for informed clinical decision making with images. This research focuses on the algorithms for automatic biomedical image annotation by utility for evidence-based practice, and integration of text and image content search strategies. Dina Demner-Fushman and I lead this development combining our complementary strengths in textual searching and content-based image retrieval (CBIR).