Mammogram Retrieval: Image Selection Strategy of Relevance Feedback for Locating Similar Lesions

Authors:
Chia-Hung Wei;Yue Li;Chee-Chiang Chen;Pai-Jung Huang;Chih-Ying Gwo
Affiliations:
Ching Yun University, Taiwan;Nankai University, China;Tungs' Taichung MetroHarbor Hospital, Taiwan;Tungs' Taichung MetroHarbor Hospital, Chi Mei Foundation Hospital, Taipei Medical University Hospital, and Taipei Medical University, Taiwan;Ching Yun University, Taiwan
Venue:
International Journal of Digital Library Systems
Year:
2011

Citing 7
Cited 0

Support vector machine active learning for image retrieval

MULTIMEDIA '01 Proceedings of the ninth ACM international conference on Multimedia
MindReader: Querying Databases Through Multiple Examples

VLDB '98 Proceedings of the 24rd International Conference on Very Large Data Bases
Challenges of Image and Video Retrieval

CIVR '02 Proceedings of the International Conference on Image and Video Retrieval
Calcification descriptor and relevance feedback learning algorithms for content-based mammogram retrieval

IWDM'06 Proceedings of the 8th international conference on Digital Mammography
The Bayesian image retrieval system, PicHunter: theory, implementation, and psychophysical experiments

IEEE Transactions on Image Processing
Relevance feedback in content-based image retrieval: Bayesian framework, feature subspaces, and progressive learning

IEEE Transactions on Image Processing
Query feedback for interactive image retrieval

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

Content-based image retrieval CBIR has been proposed by the medical community for inclusion in picture archiving and communication systems PACS. In CBIR, relevance feedback is developed for bridging the semantic gap and improving the effectiveness of image retrieval systems. With relevance feedback, CBIR systems can return refined search results using a learning algorithm and selection strategy. In this study, as the retrieving process proceeds further, the proposed learning algorithm can reduce the influence of the original query point and increase the significance of the centroid of the clusters comprising the features of those relevant images identified in the most recent round of search. The proposed selection strategy is used to find a good starting point and select a set of images at each round to show that search result and ask for the user's feedback. In addition, a benchmark is proposed to measure the learning ability to explain the retrieval performance as relevance feedback is incorporated in CBIR systems. The performance evaluation shows that the average precision rate of the proposed scheme was 0.98 and the learning ability reach to 7.17 through the five rounds of relevance feedback.