Overview of the ImageCLEFmed 2008 medical image retrieval task

Henning Müller, Jayashree Kalpathy-Cramer, Charles E. Kahn, William Hatt, Steven Bedrick, William (Bill) Hersh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

2008 was the fifth year for the medical image retrieval task of ImageCLEF, one of the most popular tracks within CLEF. Participation continued to increase in 2008. A total of 15 groups submitted 111 valid runs. Several requests for data access were also received after the registration deadline. The most significant change in 2008 was the use of a new database containing images from the medical literature. These images, part of the Goldminer collection, were from the RSNA journals Radiology and Radiographics. Besides the images, the figure captions and the part of the caption referring to a particular sub figure were supplied to the participants. Access to the full text articles in HTML was also provided, as was each article's Medline PMID (PubMed Identifier). An article's PMID could be used to obtain the officially assigned MeSH (Medical Subject Headings) terms. Unlike previous years, this year's collection was entirely in English, as it was obtained from English-language medical literature. However, the topics were, as in previous years, supplied in German, French, and English. The topics used in 2008 were a subset of the 85 topics used in 2005-2007. Thirty topics were made available, ten in each of three categories: visual, mixed, and semantic. As in previous years, most groups concentrated on fully automatic retrieval. However, three groups submitted a total of seven manual or interactive runs; these runs did not show a substantial increase in performance over the automatic approaches. In previous years, multi-modal combinations were the most frequent submissions. However, in 2008 only half as many mixed runs as purely textual runs were submitted. Very few fully visual runs were submitted, and the ones submitted performed poorly. This may be explained in part by the heavily semantic nature of the 2008 topics. The best MAP scores were very similar for textual and multi-modal approaches, whereas early precision performance was clearly better for the multi-modal approaches.

Original languageEnglish (US)
Title of host publicationCLEF 2001 - Working Notes for CLEF 2001 Workshop, co-located with the 5th European Conference on Digital Libraries, ECDL 2001
PublisherCEUR-WS
Volume1174
StatePublished - 2008
Event2008 Working Notes for CLEF Workshop, CLEF 2008 - Co-located with the 12th European Conference on Digital Libraries, ECDL 2008 - Aarhus, Denmark
Duration: Sep 17 2008Sep 19 2008

Other

Other2008 Working Notes for CLEF Workshop, CLEF 2008 - Co-located with the 12th European Conference on Digital Libraries, ECDL 2008
CountryDenmark
CityAarhus
Period9/17/089/19/08

Fingerprint

Image retrieval
Semantics
HTML
Radiology

Keywords

  • Image classification
  • Image retrieval
  • Medical imaging
  • Performance evaluation

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Müller, H., Kalpathy-Cramer, J., Kahn, C. E., Hatt, W., Bedrick, S., & Hersh, W. B. (2008). Overview of the ImageCLEFmed 2008 medical image retrieval task. In CLEF 2001 - Working Notes for CLEF 2001 Workshop, co-located with the 5th European Conference on Digital Libraries, ECDL 2001 (Vol. 1174). CEUR-WS.

Overview of the ImageCLEFmed 2008 medical image retrieval task. / Müller, Henning; Kalpathy-Cramer, Jayashree; Kahn, Charles E.; Hatt, William; Bedrick, Steven; Hersh, William (Bill).

CLEF 2001 - Working Notes for CLEF 2001 Workshop, co-located with the 5th European Conference on Digital Libraries, ECDL 2001. Vol. 1174 CEUR-WS, 2008.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Müller, H, Kalpathy-Cramer, J, Kahn, CE, Hatt, W, Bedrick, S & Hersh, WB 2008, Overview of the ImageCLEFmed 2008 medical image retrieval task. in CLEF 2001 - Working Notes for CLEF 2001 Workshop, co-located with the 5th European Conference on Digital Libraries, ECDL 2001. vol. 1174, CEUR-WS, 2008 Working Notes for CLEF Workshop, CLEF 2008 - Co-located with the 12th European Conference on Digital Libraries, ECDL 2008, Aarhus, Denmark, 9/17/08.
Müller H, Kalpathy-Cramer J, Kahn CE, Hatt W, Bedrick S, Hersh WB. Overview of the ImageCLEFmed 2008 medical image retrieval task. In CLEF 2001 - Working Notes for CLEF 2001 Workshop, co-located with the 5th European Conference on Digital Libraries, ECDL 2001. Vol. 1174. CEUR-WS. 2008
Müller, Henning ; Kalpathy-Cramer, Jayashree ; Kahn, Charles E. ; Hatt, William ; Bedrick, Steven ; Hersh, William (Bill). / Overview of the ImageCLEFmed 2008 medical image retrieval task. CLEF 2001 - Working Notes for CLEF 2001 Workshop, co-located with the 5th European Conference on Digital Libraries, ECDL 2001. Vol. 1174 CEUR-WS, 2008.
@inproceedings{61dc3d7a7e1640f799416a228a94bf57,
title = "Overview of the ImageCLEFmed 2008 medical image retrieval task",
abstract = "2008 was the fifth year for the medical image retrieval task of ImageCLEF, one of the most popular tracks within CLEF. Participation continued to increase in 2008. A total of 15 groups submitted 111 valid runs. Several requests for data access were also received after the registration deadline. The most significant change in 2008 was the use of a new database containing images from the medical literature. These images, part of the Goldminer collection, were from the RSNA journals Radiology and Radiographics. Besides the images, the figure captions and the part of the caption referring to a particular sub figure were supplied to the participants. Access to the full text articles in HTML was also provided, as was each article's Medline PMID (PubMed Identifier). An article's PMID could be used to obtain the officially assigned MeSH (Medical Subject Headings) terms. Unlike previous years, this year's collection was entirely in English, as it was obtained from English-language medical literature. However, the topics were, as in previous years, supplied in German, French, and English. The topics used in 2008 were a subset of the 85 topics used in 2005-2007. Thirty topics were made available, ten in each of three categories: visual, mixed, and semantic. As in previous years, most groups concentrated on fully automatic retrieval. However, three groups submitted a total of seven manual or interactive runs; these runs did not show a substantial increase in performance over the automatic approaches. In previous years, multi-modal combinations were the most frequent submissions. However, in 2008 only half as many mixed runs as purely textual runs were submitted. Very few fully visual runs were submitted, and the ones submitted performed poorly. This may be explained in part by the heavily semantic nature of the 2008 topics. The best MAP scores were very similar for textual and multi-modal approaches, whereas early precision performance was clearly better for the multi-modal approaches.",
keywords = "Image classification, Image retrieval, Medical imaging, Performance evaluation",
author = "Henning M{\"u}ller and Jayashree Kalpathy-Cramer and Kahn, {Charles E.} and William Hatt and Steven Bedrick and Hersh, {William (Bill)}",
year = "2008",
language = "English (US)",
volume = "1174",
booktitle = "CLEF 2001 - Working Notes for CLEF 2001 Workshop, co-located with the 5th European Conference on Digital Libraries, ECDL 2001",
publisher = "CEUR-WS",

}

TY - GEN

T1 - Overview of the ImageCLEFmed 2008 medical image retrieval task

AU - Müller, Henning

AU - Kalpathy-Cramer, Jayashree

AU - Kahn, Charles E.

AU - Hatt, William

AU - Bedrick, Steven

AU - Hersh, William (Bill)

PY - 2008

Y1 - 2008

N2 - 2008 was the fifth year for the medical image retrieval task of ImageCLEF, one of the most popular tracks within CLEF. Participation continued to increase in 2008. A total of 15 groups submitted 111 valid runs. Several requests for data access were also received after the registration deadline. The most significant change in 2008 was the use of a new database containing images from the medical literature. These images, part of the Goldminer collection, were from the RSNA journals Radiology and Radiographics. Besides the images, the figure captions and the part of the caption referring to a particular sub figure were supplied to the participants. Access to the full text articles in HTML was also provided, as was each article's Medline PMID (PubMed Identifier). An article's PMID could be used to obtain the officially assigned MeSH (Medical Subject Headings) terms. Unlike previous years, this year's collection was entirely in English, as it was obtained from English-language medical literature. However, the topics were, as in previous years, supplied in German, French, and English. The topics used in 2008 were a subset of the 85 topics used in 2005-2007. Thirty topics were made available, ten in each of three categories: visual, mixed, and semantic. As in previous years, most groups concentrated on fully automatic retrieval. However, three groups submitted a total of seven manual or interactive runs; these runs did not show a substantial increase in performance over the automatic approaches. In previous years, multi-modal combinations were the most frequent submissions. However, in 2008 only half as many mixed runs as purely textual runs were submitted. Very few fully visual runs were submitted, and the ones submitted performed poorly. This may be explained in part by the heavily semantic nature of the 2008 topics. The best MAP scores were very similar for textual and multi-modal approaches, whereas early precision performance was clearly better for the multi-modal approaches.

AB - 2008 was the fifth year for the medical image retrieval task of ImageCLEF, one of the most popular tracks within CLEF. Participation continued to increase in 2008. A total of 15 groups submitted 111 valid runs. Several requests for data access were also received after the registration deadline. The most significant change in 2008 was the use of a new database containing images from the medical literature. These images, part of the Goldminer collection, were from the RSNA journals Radiology and Radiographics. Besides the images, the figure captions and the part of the caption referring to a particular sub figure were supplied to the participants. Access to the full text articles in HTML was also provided, as was each article's Medline PMID (PubMed Identifier). An article's PMID could be used to obtain the officially assigned MeSH (Medical Subject Headings) terms. Unlike previous years, this year's collection was entirely in English, as it was obtained from English-language medical literature. However, the topics were, as in previous years, supplied in German, French, and English. The topics used in 2008 were a subset of the 85 topics used in 2005-2007. Thirty topics were made available, ten in each of three categories: visual, mixed, and semantic. As in previous years, most groups concentrated on fully automatic retrieval. However, three groups submitted a total of seven manual or interactive runs; these runs did not show a substantial increase in performance over the automatic approaches. In previous years, multi-modal combinations were the most frequent submissions. However, in 2008 only half as many mixed runs as purely textual runs were submitted. Very few fully visual runs were submitted, and the ones submitted performed poorly. This may be explained in part by the heavily semantic nature of the 2008 topics. The best MAP scores were very similar for textual and multi-modal approaches, whereas early precision performance was clearly better for the multi-modal approaches.

KW - Image classification

KW - Image retrieval

KW - Medical imaging

KW - Performance evaluation

UR - http://www.scopus.com/inward/record.url?scp=84921993001&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84921993001&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84921993001

VL - 1174

BT - CLEF 2001 - Working Notes for CLEF 2001 Workshop, co-located with the 5th European Conference on Digital Libraries, ECDL 2001

PB - CEUR-WS

ER -