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

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

Chee-Chiang Chen, Pai-Jung Huang, Chih-Ying Gwo, Yue Li, Chia-Hung Wei
Copyright: © 2013 |Pages: 9
DOI: 10.4018/978-1-4666-2928-8.ch004
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

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.
Chapter Preview
Top

2. Prior Work

To incorporate relevance feedback into content-based image retrieval, two main approaches are developed: the query point movement approach and re-weighting approach. The concept behind the first approach is to modify the query that is originally submitted by the user. It is assumed that there exists at least one image which completely conveys the intentions of the user, and its high-level concept has been modeled in low-level feature space (Kushki, Androutsos, Plataniotis, & Venetsanopoulos, 2004). The query point movement approach is to move the point of the query toward the region of the feature space that contains the ideal image (Zhong, Hongjiang, Li, & Shaoping, 2003). Based on this concept, the classic Rocchio algorithm was originally developed to improve the effectiveness of information retrieval system (Rocchio, 1971). The MARS system has applied the query point movement approach as one of methods for relevance feedback (Rui, Huang, & Mehrotra, 1998). The method used in the MARS system is called 978-1-4666-2928-8.ch004.m01(term frequency-inverse document frequency), which generates pseudo-document vectors from image feature vectors and then applies the Rocchio algorithm to find the ideal point.

Complete Chapter List

Search this Book:
Reset