Medical Image Classification at Tel Aviv and Bar Ilan Universities

Uri Avni; Jacob Goldberger; Hayit Greenspan

doi:10.1007/978-3-642-15181-1_23

Medical Image Classification at Tel Aviv and Bar Ilan Universities

Uri Avni, Jacob Goldberger, Hayit Greenspan

Department of Bio-Medical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

We present an efficient and accurate image categorization system, applied to medical image databases within the ImageCLEF medical annotation task. The methodology is based on local representation of the image content, using a bag--of--visual--words approach. We explore the effect of different parameters on system performance, and show best results using dense sampling of simple features with spatial content in multiple scales, combined with a nonlinear kernel based Support Vector Machine classifier. The system was ranked first in the ImageCLEF 2009 medical annotation challenge, with a total error score of 852.8.

Original language	Undefined/Unknown
Title of host publication	ImageCLEF: Experimental Evaluation in Visual Information Retrieval
Editors	Henning Müller, Paul Clough, Thomas Deselaers, Barbara Caputo
Place of Publication	Berlin, Heidelberg
Publisher	Springer Berlin Heidelberg
Pages	435-451
Number of pages	17
ISBN (Print)	978-3-642-15181-1
DOIs	https://doi.org/10.1007/978-3-642-15181-1_23
State	Published - 2010

Access to Document

10.1007/978-3-642-15181-1_23

https://doi.org/10.1007/978-3-642-15181-1_23

Cite this

@inbook{742d7413c1674b99943d6ca35bf59fd6,

title = "Medical Image Classification at Tel Aviv and Bar Ilan Universities",

abstract = "We present an efficient and accurate image categorization system, applied to medical image databases within the ImageCLEF medical annotation task. The methodology is based on local representation of the image content, using a bag--of--visual--words approach. We explore the effect of different parameters on system performance, and show best results using dense sampling of simple features with spatial content in multiple scales, combined with a nonlinear kernel based Support Vector Machine classifier. The system was ranked first in the ImageCLEF 2009 medical annotation challenge, with a total error score of 852.8.",

author = "Uri Avni and Jacob Goldberger and Hayit Greenspan",

year = "2010",

doi = "10.1007/978-3-642-15181-1_23",

language = "???core.languages.und???",

isbn = "978-3-642-15181-1",

pages = "435--451",

editor = "Henning M{\"u}ller and Paul Clough and Thomas Deselaers and Barbara Caputo",

booktitle = "ImageCLEF: Experimental Evaluation in Visual Information Retrieval",

publisher = "Springer Berlin Heidelberg",

}

Medical Image Classification at Tel Aviv and Bar Ilan Universities. / Avni, Uri; Goldberger, Jacob; Greenspan, Hayit.
ImageCLEF: Experimental Evaluation in Visual Information Retrieval. ed. / Henning Müller; Paul Clough; Thomas Deselaers; Barbara Caputo. Berlin, Heidelberg: Springer Berlin Heidelberg, 2010. p. 435-451.

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

TY - CHAP

T1 - Medical Image Classification at Tel Aviv and Bar Ilan Universities

AU - Avni, Uri

AU - Goldberger, Jacob

AU - Greenspan, Hayit

PY - 2010

Y1 - 2010

N2 - We present an efficient and accurate image categorization system, applied to medical image databases within the ImageCLEF medical annotation task. The methodology is based on local representation of the image content, using a bag--of--visual--words approach. We explore the effect of different parameters on system performance, and show best results using dense sampling of simple features with spatial content in multiple scales, combined with a nonlinear kernel based Support Vector Machine classifier. The system was ranked first in the ImageCLEF 2009 medical annotation challenge, with a total error score of 852.8.

AB - We present an efficient and accurate image categorization system, applied to medical image databases within the ImageCLEF medical annotation task. The methodology is based on local representation of the image content, using a bag--of--visual--words approach. We explore the effect of different parameters on system performance, and show best results using dense sampling of simple features with spatial content in multiple scales, combined with a nonlinear kernel based Support Vector Machine classifier. The system was ranked first in the ImageCLEF 2009 medical annotation challenge, with a total error score of 852.8.

U2 - 10.1007/978-3-642-15181-1_23

DO - 10.1007/978-3-642-15181-1_23

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.chapter???

SN - 978-3-642-15181-1

SP - 435

EP - 451

BT - ImageCLEF: Experimental Evaluation in Visual Information Retrieval

A2 - Müller, Henning

A2 - Clough, Paul

A2 - Deselaers, Thomas

A2 - Caputo, Barbara

PB - Springer Berlin Heidelberg

CY - Berlin, Heidelberg

ER -