Analyzing web log files of the health on the net HONmedia search engine to define typical image search tasks for image retrieval evaluation.

Henning Müller, Célia Boyer, Arnaud Gaudinat, William (Bill) Hersh, Antoine Geissbuhler

Research output: Chapter in Book/Report/Conference proceedingChapter

8 Citations (Scopus)

Abstract

Medical institutions produce ever-increasing amount of diverse information. The digital form makes these data available for the use on more than a single patient. Images are no exception to this. However, less is known about how medical professionals search for visual medical information and how they want to use it outside of the context of a single patient. This article analyzes ten months of usage log files of the Health on the Net (HON) medical media search engine. Key words were extracted from all queries and the most frequent terms and subjects were identified. The dataset required much pre-treatment. Problems included national character sets, spelling errors and the use of terms in several languages. The results show that media search, particularly for images, was frequently used. The most common queries were for general concepts (e.g., heart, lung). To define realistic information needs for the ImageCLEFmed challenge evaluation (Cross Language Evaluation Forum medical image retrieval), we used frequent queries that were still specific enough to at least cover two of the three axes on modality, anatomic region, and pathology. Several research groups evaluated their image retrieval algorithms based on these defined topics.

Original languageEnglish (US)
Title of host publicationMedinfo. MEDINFO
Pages1319-1323
Number of pages5
Volume12
EditionPt 2
StatePublished - 2007

Fingerprint

Search Engine
Language
Health
Pathology
Lung
Research
Therapeutics
Datasets

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Müller, H., Boyer, C., Gaudinat, A., Hersh, W. B., & Geissbuhler, A. (2007). Analyzing web log files of the health on the net HONmedia search engine to define typical image search tasks for image retrieval evaluation. In Medinfo. MEDINFO (Pt 2 ed., Vol. 12, pp. 1319-1323)

Analyzing web log files of the health on the net HONmedia search engine to define typical image search tasks for image retrieval evaluation. / Müller, Henning; Boyer, Célia; Gaudinat, Arnaud; Hersh, William (Bill); Geissbuhler, Antoine.

Medinfo. MEDINFO. Vol. 12 Pt 2. ed. 2007. p. 1319-1323.

Research output: Chapter in Book/Report/Conference proceedingChapter

Müller, H, Boyer, C, Gaudinat, A, Hersh, WB & Geissbuhler, A 2007, Analyzing web log files of the health on the net HONmedia search engine to define typical image search tasks for image retrieval evaluation. in Medinfo. MEDINFO. Pt 2 edn, vol. 12, pp. 1319-1323.
Müller H, Boyer C, Gaudinat A, Hersh WB, Geissbuhler A. Analyzing web log files of the health on the net HONmedia search engine to define typical image search tasks for image retrieval evaluation. In Medinfo. MEDINFO. Pt 2 ed. Vol. 12. 2007. p. 1319-1323
Müller, Henning ; Boyer, Célia ; Gaudinat, Arnaud ; Hersh, William (Bill) ; Geissbuhler, Antoine. / Analyzing web log files of the health on the net HONmedia search engine to define typical image search tasks for image retrieval evaluation. Medinfo. MEDINFO. Vol. 12 Pt 2. ed. 2007. pp. 1319-1323
@inbook{3d355abd60bd43a8bcee044fbb0b5f71,
title = "Analyzing web log files of the health on the net HONmedia search engine to define typical image search tasks for image retrieval evaluation.",
abstract = "Medical institutions produce ever-increasing amount of diverse information. The digital form makes these data available for the use on more than a single patient. Images are no exception to this. However, less is known about how medical professionals search for visual medical information and how they want to use it outside of the context of a single patient. This article analyzes ten months of usage log files of the Health on the Net (HON) medical media search engine. Key words were extracted from all queries and the most frequent terms and subjects were identified. The dataset required much pre-treatment. Problems included national character sets, spelling errors and the use of terms in several languages. The results show that media search, particularly for images, was frequently used. The most common queries were for general concepts (e.g., heart, lung). To define realistic information needs for the ImageCLEFmed challenge evaluation (Cross Language Evaluation Forum medical image retrieval), we used frequent queries that were still specific enough to at least cover two of the three axes on modality, anatomic region, and pathology. Several research groups evaluated their image retrieval algorithms based on these defined topics.",
author = "Henning M{\"u}ller and C{\'e}lia Boyer and Arnaud Gaudinat and Hersh, {William (Bill)} and Antoine Geissbuhler",
year = "2007",
language = "English (US)",
volume = "12",
pages = "1319--1323",
booktitle = "Medinfo. MEDINFO",
edition = "Pt 2",

}

TY - CHAP

T1 - Analyzing web log files of the health on the net HONmedia search engine to define typical image search tasks for image retrieval evaluation.

AU - Müller, Henning

AU - Boyer, Célia

AU - Gaudinat, Arnaud

AU - Hersh, William (Bill)

AU - Geissbuhler, Antoine

PY - 2007

Y1 - 2007

N2 - Medical institutions produce ever-increasing amount of diverse information. The digital form makes these data available for the use on more than a single patient. Images are no exception to this. However, less is known about how medical professionals search for visual medical information and how they want to use it outside of the context of a single patient. This article analyzes ten months of usage log files of the Health on the Net (HON) medical media search engine. Key words were extracted from all queries and the most frequent terms and subjects were identified. The dataset required much pre-treatment. Problems included national character sets, spelling errors and the use of terms in several languages. The results show that media search, particularly for images, was frequently used. The most common queries were for general concepts (e.g., heart, lung). To define realistic information needs for the ImageCLEFmed challenge evaluation (Cross Language Evaluation Forum medical image retrieval), we used frequent queries that were still specific enough to at least cover two of the three axes on modality, anatomic region, and pathology. Several research groups evaluated their image retrieval algorithms based on these defined topics.

AB - Medical institutions produce ever-increasing amount of diverse information. The digital form makes these data available for the use on more than a single patient. Images are no exception to this. However, less is known about how medical professionals search for visual medical information and how they want to use it outside of the context of a single patient. This article analyzes ten months of usage log files of the Health on the Net (HON) medical media search engine. Key words were extracted from all queries and the most frequent terms and subjects were identified. The dataset required much pre-treatment. Problems included national character sets, spelling errors and the use of terms in several languages. The results show that media search, particularly for images, was frequently used. The most common queries were for general concepts (e.g., heart, lung). To define realistic information needs for the ImageCLEFmed challenge evaluation (Cross Language Evaluation Forum medical image retrieval), we used frequent queries that were still specific enough to at least cover two of the three axes on modality, anatomic region, and pathology. Several research groups evaluated their image retrieval algorithms based on these defined topics.

UR - http://www.scopus.com/inward/record.url?scp=35748980893&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35748980893&partnerID=8YFLogxK

M3 - Chapter

C2 - 17911928

AN - SCOPUS:35748980893

VL - 12

SP - 1319

EP - 1323

BT - Medinfo. MEDINFO

ER -