A New Re-Ranking Method Using Enhanced Pseudo-Relevance Feedback for Content-Based Medical Image Retrieval
Summary :
We propose a novel re-ranking method for content-based medical image retrieval based on the idea of pseudo-relevance feedback (PRF). Since the highest ranked images in original retrieval results are not always relevant, a naive PRF based re-ranking approach is not capable of producing a satisfactory result. We employ a two-step approach to address this issue. In step 1, a Pearson's correlation coefficient based similarity update method is used to re-rank the high ranked images. In step 2, after estimating a relevance probability for each of the highest ranked images, a fuzzy SVM ensemble based approach is adopted to re-rank the images. The experiments demonstrate that the proposed method outperforms two other re-ranking methods.
- Publication
- IEICE TRANSACTIONS on Information Vol.E95-D No.2 pp.694-698
- Publication Date
- 2012/02/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E95.D.694
- Type of Manuscript
- LETTER
- Category
- Image Processing and Video Processing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Yonggang HUANG, Jun ZHANG, Yongwang ZHAO, Dianfu MA, "A New Re-Ranking Method Using Enhanced Pseudo-Relevance Feedback for Content-Based Medical Image Retrieval" in IEICE TRANSACTIONS on Information,
vol. E95-D, no. 2, pp. 694-698, February 2012, doi: 10.1587/transinf.E95.D.694.
Abstract: We propose a novel re-ranking method for content-based medical image retrieval based on the idea of pseudo-relevance feedback (PRF). Since the highest ranked images in original retrieval results are not always relevant, a naive PRF based re-ranking approach is not capable of producing a satisfactory result. We employ a two-step approach to address this issue. In step 1, a Pearson's correlation coefficient based similarity update method is used to re-rank the high ranked images. In step 2, after estimating a relevance probability for each of the highest ranked images, a fuzzy SVM ensemble based approach is adopted to re-rank the images. The experiments demonstrate that the proposed method outperforms two other re-ranking methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E95.D.694/_p
Copy
@ARTICLE{e95-d_2_694,
author={Yonggang HUANG, Jun ZHANG, Yongwang ZHAO, Dianfu MA, },
journal={IEICE TRANSACTIONS on Information},
title={A New Re-Ranking Method Using Enhanced Pseudo-Relevance Feedback for Content-Based Medical Image Retrieval},
year={2012},
volume={E95-D},
number={2},
pages={694-698},
abstract={We propose a novel re-ranking method for content-based medical image retrieval based on the idea of pseudo-relevance feedback (PRF). Since the highest ranked images in original retrieval results are not always relevant, a naive PRF based re-ranking approach is not capable of producing a satisfactory result. We employ a two-step approach to address this issue. In step 1, a Pearson's correlation coefficient based similarity update method is used to re-rank the high ranked images. In step 2, after estimating a relevance probability for each of the highest ranked images, a fuzzy SVM ensemble based approach is adopted to re-rank the images. The experiments demonstrate that the proposed method outperforms two other re-ranking methods.},
keywords={},
doi={10.1587/transinf.E95.D.694},
ISSN={1745-1361},
month={February},}
Copy
TY - JOUR
TI - A New Re-Ranking Method Using Enhanced Pseudo-Relevance Feedback for Content-Based Medical Image Retrieval
T2 - IEICE TRANSACTIONS on Information
SP - 694
EP - 698
AU - Yonggang HUANG
AU - Jun ZHANG
AU - Yongwang ZHAO
AU - Dianfu MA
PY - 2012
DO - 10.1587/transinf.E95.D.694
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2012
AB - We propose a novel re-ranking method for content-based medical image retrieval based on the idea of pseudo-relevance feedback (PRF). Since the highest ranked images in original retrieval results are not always relevant, a naive PRF based re-ranking approach is not capable of producing a satisfactory result. We employ a two-step approach to address this issue. In step 1, a Pearson's correlation coefficient based similarity update method is used to re-rank the high ranked images. In step 2, after estimating a relevance probability for each of the highest ranked images, a fuzzy SVM ensemble based approach is adopted to re-rank the images. The experiments demonstrate that the proposed method outperforms two other re-ranking methods.
ER -
English
