Overview of the ImageCLEF 2012 medical image retrieval and classiFIcation tasks

Henning Müller, Alba G Seco De Herrera, Jayashree Kalpathy-Cramer, Dina Demner Fushman, Sameer Antani, Ivan Eggel

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

26 Citations (Scopus)

Abstract

The ninth edition of the ImageCLEF medical image retrieval and classification tasks was organized in 2012. A subset of the open access collection of PubMed Central was used as the database in 2012, using a larger number of over 300'000 images than in 2011. As in previous years, there were three subtasks: modality classification, image{based and case{based retrieval. A new hierarchy for article figures was created for the modality classifi- cation task. The modality detection could be one of the most important filters to limit the search and focus the results sets. The goal of the image{based and the case{based retrieval tasks were similar compared to 2011 adding mainly complexity. The number of groups submitting runs has remained stable at 17, with the number of submitted runs remaining roughly the same with 202 (207 in 2011). Of these, 122 were image{based retrieval runs, 37 were case{based runs while the remaining 43 were modality classification runs. Depending on the exact nature of the task, visual, textual or multimodal approaches performed better.

Original languageEnglish (US)
Title of host publicationCLEF 2012 - Working Notes for CLEF 2012 Conference
PublisherCEUR-WS
Volume1178
StatePublished - 2012
Externally publishedYes
Event2012 Cross Language Evaluation Forum Conference, CLEF 2012 - Rome, Italy
Duration: Sep 17 2012Sep 20 2012

Other

Other2012 Cross Language Evaluation Forum Conference, CLEF 2012
CountryItaly
CityRome
Period9/17/129/20/12

Fingerprint

Image classification
Image retrieval

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Müller, H., De Herrera, A. G. S., Kalpathy-Cramer, J., Fushman, D. D., Antani, S., & Eggel, I. (2012). Overview of the ImageCLEF 2012 medical image retrieval and classiFIcation tasks. In CLEF 2012 - Working Notes for CLEF 2012 Conference (Vol. 1178). CEUR-WS.

Overview of the ImageCLEF 2012 medical image retrieval and classiFIcation tasks. / Müller, Henning; De Herrera, Alba G Seco; Kalpathy-Cramer, Jayashree; Fushman, Dina Demner; Antani, Sameer; Eggel, Ivan.

CLEF 2012 - Working Notes for CLEF 2012 Conference. Vol. 1178 CEUR-WS, 2012.

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

Müller, H, De Herrera, AGS, Kalpathy-Cramer, J, Fushman, DD, Antani, S & Eggel, I 2012, Overview of the ImageCLEF 2012 medical image retrieval and classiFIcation tasks. in CLEF 2012 - Working Notes for CLEF 2012 Conference. vol. 1178, CEUR-WS, 2012 Cross Language Evaluation Forum Conference, CLEF 2012, Rome, Italy, 9/17/12.
Müller H, De Herrera AGS, Kalpathy-Cramer J, Fushman DD, Antani S, Eggel I. Overview of the ImageCLEF 2012 medical image retrieval and classiFIcation tasks. In CLEF 2012 - Working Notes for CLEF 2012 Conference. Vol. 1178. CEUR-WS. 2012
Müller, Henning ; De Herrera, Alba G Seco ; Kalpathy-Cramer, Jayashree ; Fushman, Dina Demner ; Antani, Sameer ; Eggel, Ivan. / Overview of the ImageCLEF 2012 medical image retrieval and classiFIcation tasks. CLEF 2012 - Working Notes for CLEF 2012 Conference. Vol. 1178 CEUR-WS, 2012.
@inproceedings{63f422bfd43e46d4856aa1c027c14f7d,
title = "Overview of the ImageCLEF 2012 medical image retrieval and classiFIcation tasks",
abstract = "The ninth edition of the ImageCLEF medical image retrieval and classification tasks was organized in 2012. A subset of the open access collection of PubMed Central was used as the database in 2012, using a larger number of over 300'000 images than in 2011. As in previous years, there were three subtasks: modality classification, image{based and case{based retrieval. A new hierarchy for article figures was created for the modality classifi- cation task. The modality detection could be one of the most important filters to limit the search and focus the results sets. The goal of the image{based and the case{based retrieval tasks were similar compared to 2011 adding mainly complexity. The number of groups submitting runs has remained stable at 17, with the number of submitted runs remaining roughly the same with 202 (207 in 2011). Of these, 122 were image{based retrieval runs, 37 were case{based runs while the remaining 43 were modality classification runs. Depending on the exact nature of the task, visual, textual or multimodal approaches performed better.",
author = "Henning M{\"u}ller and {De Herrera}, {Alba G Seco} and Jayashree Kalpathy-Cramer and Fushman, {Dina Demner} and Sameer Antani and Ivan Eggel",
year = "2012",
language = "English (US)",
volume = "1178",
booktitle = "CLEF 2012 - Working Notes for CLEF 2012 Conference",
publisher = "CEUR-WS",

}

TY - GEN

T1 - Overview of the ImageCLEF 2012 medical image retrieval and classiFIcation tasks

AU - Müller, Henning

AU - De Herrera, Alba G Seco

AU - Kalpathy-Cramer, Jayashree

AU - Fushman, Dina Demner

AU - Antani, Sameer

AU - Eggel, Ivan

PY - 2012

Y1 - 2012

N2 - The ninth edition of the ImageCLEF medical image retrieval and classification tasks was organized in 2012. A subset of the open access collection of PubMed Central was used as the database in 2012, using a larger number of over 300'000 images than in 2011. As in previous years, there were three subtasks: modality classification, image{based and case{based retrieval. A new hierarchy for article figures was created for the modality classifi- cation task. The modality detection could be one of the most important filters to limit the search and focus the results sets. The goal of the image{based and the case{based retrieval tasks were similar compared to 2011 adding mainly complexity. The number of groups submitting runs has remained stable at 17, with the number of submitted runs remaining roughly the same with 202 (207 in 2011). Of these, 122 were image{based retrieval runs, 37 were case{based runs while the remaining 43 were modality classification runs. Depending on the exact nature of the task, visual, textual or multimodal approaches performed better.

AB - The ninth edition of the ImageCLEF medical image retrieval and classification tasks was organized in 2012. A subset of the open access collection of PubMed Central was used as the database in 2012, using a larger number of over 300'000 images than in 2011. As in previous years, there were three subtasks: modality classification, image{based and case{based retrieval. A new hierarchy for article figures was created for the modality classifi- cation task. The modality detection could be one of the most important filters to limit the search and focus the results sets. The goal of the image{based and the case{based retrieval tasks were similar compared to 2011 adding mainly complexity. The number of groups submitting runs has remained stable at 17, with the number of submitted runs remaining roughly the same with 202 (207 in 2011). Of these, 122 were image{based retrieval runs, 37 were case{based runs while the remaining 43 were modality classification runs. Depending on the exact nature of the task, visual, textual or multimodal approaches performed better.

UR - http://www.scopus.com/inward/record.url?scp=84922051482&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922051482&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84922051482

VL - 1178

BT - CLEF 2012 - Working Notes for CLEF 2012 Conference

PB - CEUR-WS

ER -