Finding and accessing diagrams in biomedical publications.

Tobias Kuhn, Thaibinh Luong, Michael Krauthammer

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Complex relationships in biomedical publications are often communicated by diagrams such as bar and line charts, which are a very effective way of summarizing and communicating multi-faceted data sets. Given the ever-increasing amount of published data, we argue that the precise retrieval of such diagrams is of great value for answering specific and otherwise hard-to-meet information needs. To this end, we demonstrate the use of advanced image processing and classification for identifying bar and line charts by the shape and relative location of the different image elements that make up the charts. With recall and precisions of close to 90% for the detection of relevant figures, we discuss the use of this technology in an existing biomedical image search engine, and outline how it enables new forms of literature queries over biomedical relationships that are represented in these charts.

Original languageEnglish
Pages (from-to)468-474
Number of pages7
JournalAMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium
Volume2012
Publication statusPublished - 2012
Externally publishedYes

Fingerprint

Search Engine
Publications
Technology
Datasets

Cite this

@article{e468d7e6d18743bebffaab8421de3ca0,
title = "Finding and accessing diagrams in biomedical publications.",
abstract = "Complex relationships in biomedical publications are often communicated by diagrams such as bar and line charts, which are a very effective way of summarizing and communicating multi-faceted data sets. Given the ever-increasing amount of published data, we argue that the precise retrieval of such diagrams is of great value for answering specific and otherwise hard-to-meet information needs. To this end, we demonstrate the use of advanced image processing and classification for identifying bar and line charts by the shape and relative location of the different image elements that make up the charts. With recall and precisions of close to 90{\%} for the detection of relevant figures, we discuss the use of this technology in an existing biomedical image search engine, and outline how it enables new forms of literature queries over biomedical relationships that are represented in these charts.",
author = "Tobias Kuhn and Thaibinh Luong and Michael Krauthammer",
year = "2012",
language = "English",
volume = "2012",
pages = "468--474",
journal = "AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium",
issn = "1942-597X",
publisher = "American Medical Informatics Association",

}

Finding and accessing diagrams in biomedical publications. / Kuhn, Tobias; Luong, Thaibinh; Krauthammer, Michael.

In: AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium, Vol. 2012, 2012, p. 468-474.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Finding and accessing diagrams in biomedical publications.

AU - Kuhn, Tobias

AU - Luong, Thaibinh

AU - Krauthammer, Michael

PY - 2012

Y1 - 2012

N2 - Complex relationships in biomedical publications are often communicated by diagrams such as bar and line charts, which are a very effective way of summarizing and communicating multi-faceted data sets. Given the ever-increasing amount of published data, we argue that the precise retrieval of such diagrams is of great value for answering specific and otherwise hard-to-meet information needs. To this end, we demonstrate the use of advanced image processing and classification for identifying bar and line charts by the shape and relative location of the different image elements that make up the charts. With recall and precisions of close to 90% for the detection of relevant figures, we discuss the use of this technology in an existing biomedical image search engine, and outline how it enables new forms of literature queries over biomedical relationships that are represented in these charts.

AB - Complex relationships in biomedical publications are often communicated by diagrams such as bar and line charts, which are a very effective way of summarizing and communicating multi-faceted data sets. Given the ever-increasing amount of published data, we argue that the precise retrieval of such diagrams is of great value for answering specific and otherwise hard-to-meet information needs. To this end, we demonstrate the use of advanced image processing and classification for identifying bar and line charts by the shape and relative location of the different image elements that make up the charts. With recall and precisions of close to 90% for the detection of relevant figures, we discuss the use of this technology in an existing biomedical image search engine, and outline how it enables new forms of literature queries over biomedical relationships that are represented in these charts.

UR - http://www.scopus.com/inward/record.url?scp=84880780727&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880780727&partnerID=8YFLogxK

M3 - Article

VL - 2012

SP - 468

EP - 474

JO - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

JF - AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium

SN - 1942-597X

ER -