Share Email Print
cover

Proceedings Paper

Automatic identification of ROI in figure images toward improving hybrid (text and image) biomedical document retrieval
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Biomedical images are often referenced for clinical decision support (CDS), educational purposes, and research. They appear in specialized databases or in biomedical publications and are not meaningfully retrievable using primarily textbased retrieval systems. The task of automatically finding the images in an article that are most useful for the purpose of determining relevance to a clinical situation is quite challenging. An approach is to automatically annotate images extracted from scientific publications with respect to their usefulness for CDS. As an important step toward achieving the goal, we proposed figure image analysis for localizing pointers (arrows, symbols) to extract regions of interest (ROI) that can then be used to obtain meaningful local image content. Content-based image retrieval (CBIR) techniques can then associate local image ROIs with identified biomedical concepts in figure captions for improved hybrid (text and image) retrieval of biomedical articles. In this work we present methods that make robust our previous Markov random field (MRF)-based approach for pointer recognition and ROI extraction. These include use of Active Shape Models (ASM) to overcome problems in recognizing distorted pointer shapes and a region segmentation method for ROI extraction. We measure the performance of our methods on two criteria: (i) effectiveness in recognizing pointers in images, and (ii) improved document retrieval through use of extracted ROIs. Evaluation on three test sets shows 87% accuracy in the first criterion. Further, the quality of document retrieval using local visual features and text is shown to be better than using visual features alone.

Paper Details

Date Published: 24 January 2011
PDF: 11 pages
Proc. SPIE 7874, Document Recognition and Retrieval XVIII, 78740K (24 January 2011); doi: 10.1117/12.873434
Show Author Affiliations
Daekeun You, State Univ. of New York at Buffalo (United States)
Sameer Antani, National Library of Medicine, National Institutes of Health (United States)
Dina Demner-Fushman, National Library of Medicine, National Institutes of Health (United States)
Md Mahmudur Rahman, National Library of Medicine, National Institutes of Health (United States)
Venu Govindaraju, State Univ. of New York at Buffalo (United States)
George R. Thoma, National Library of Medicine, National Institutes of Health (United States)


Published in SPIE Proceedings Vol. 7874:
Document Recognition and Retrieval XVIII
Gady Agam; Christian Viard-Gaudin, Editor(s)

© SPIE. Terms of Use
Back to Top