DocumentCode :
987807
Title :
A Boosting Framework for Visuality-Preserving Distance Metric Learning and Its Application to Medical Image Retrieval
Author :
Yang, Liu ; Jin, Rong ; Mummert, Lily ; Sukthankar, Rahul ; Goode, Adam ; Zheng, Bin ; Hoi, Steven C H ; Satyanarayanan, Mahadev
Author_Institution :
Machine Learning Dept., Carnegie Mellon Univ., Pittsburgh, PA, USA
Volume :
32
Issue :
1
fYear :
2010
Firstpage :
30
Lastpage :
44
Abstract :
Similarity measurement is a critical component in content-based image retrieval systems, and learning a good distance metric can significantly improve retrieval performance. However, despite extensive study, there are several major shortcomings with the existing approaches for distance metric learning that can significantly affect their application to medical image retrieval. In particular, ldquosimilarityrdquo can mean very different things in image retrieval: resemblance in visual appearance (e.g., two images that look like one another) or similarity in semantic annotation (e.g., two images of tumors that look quite different yet are both malignant). Current approaches for distance metric learning typically address only one goal without consideration of the other. This is problematic for medical image retrieval where the goal is to assist doctors in decision making. In these applications, given a query image, the goal is to retrieve similar images from a reference library whose semantic annotations could provide the medical professional with greater insight into the possible interpretations of the query image. If the system were to retrieve images that did not look like the query, then users would be less likely to trust the system; on the other hand, retrieving images that appear superficially similar to the query but are semantically unrelated is undesirable because that could lead users toward an incorrect diagnosis. Hence, learning a distance metric that preserves both visual resemblance and semantic similarity is important. We emphasize that, although our study is focused on medical image retrieval, the problem addressed in this work is critical to many image retrieval systems. We present a boosting framework for distance metric learning that aims to preserve both visual and semantic similarities. The boosting framework first learns a binary representation using side information, in the form of labeled pairs, and then computes the distance as a weighted Hammi- - ng distance using the learned binary representation. A boosting algorithm is presented to efficiently learn the distance function. We evaluate the proposed algorithm on a mammographic image reference library with an interactive search-assisted decision support (ISADS) system and on the medical image data set from ImageCLEF. Our results show that the boosting framework compares favorably to state-of-the-art approaches for distance metric learning in retrieval accuracy, with much lower computational cost. Additional evaluation with the COREL collection shows that our algorithm works well for regular image data sets.
Keywords :
content-based retrieval; decision making; decision support systems; learning (artificial intelligence); mammography; medical image processing; ISADS; binary representation; boosting framework; content-based image retrieval system; decision making; interactive search-assisted decision support system; machine learning; mammographic image reference library; medical diagnosis; medical image retrieval; semantic annotation; side information; similarity measurement; visuality-preserving distance metric learning; weighted Hamming distance; Boosting; Distance Metric Learning; Image/video retrieval; Machine learning; boosting.; distance metric learning; image retrieval; Algorithms; Area Under Curve; Artificial Intelligence; Databases, Factual; Diagnostic Imaging; Image Processing, Computer-Assisted; Information Storage and Retrieval; Mammography; Medical Informatics; Principal Component Analysis; Radiography; Semantics;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/TPAMI.2008.273
Filename :
4674367
Link To Document :
بازگشت