Content‐based retrieval of brain tumor in contrast‐enhanced MRI images using tumor margin information and learned distance metric
Authors:
- 25 October 2012
- journal article
- research article
- Published by Wiley in Medical Physics
- Vol. 39 (11) , 6929-6942
Abstract
Purpose: A content‐based image retrieval (CBIR) method for T1‐weighted contrast‐enhanced MRI (CE‐MRI) images of brain tumors is presented for diagnosis aid. The method is thoroughly evaluated on a large image dataset.Methods: Using the tumor region as a query, the authors’ CBIR system attempts to retrieve tumors of the same pathological category. Aside from commonly used features such as intensity, texture, and shape features, the authors use a margin information descriptor (MID), which is capable of describing the characteristics of tissue surrounding a tumor, for representing image contents. In addition, the authors designed a distance metric learning algorithm calledMaximum mean average Precision Projection (MPP) to maximize the smooth approximated mean average precision (mAP) to optimize retrieval performance.Results: The effectiveness of MID and MPP algorithms was evaluated using a brain CE‐MRI dataset consisting of 3108 2D scans acquired from 235 patients with three categories of brain tumors (meningioma, glioma, and pituitary tumor). By combining MID and other features, the mAP of retrieval increased by more than 6% with the learned distance metrics. The distance metric learned by MPP significantly outperformed the other two existing distance metric learning methods in terms of mAP. The CBIR system using the proposed strategies achieved a mAP of 87.3% and a precision of 89.3% when top 10 images were returned by the system. Compared with scale‐invariant feature transform, the MID, which uses the intensity profile as descriptor, achieves better retrieval performance.Conclusions: Incorporating tumor margin information represented by MID with the distance metric learned by the MPP algorithm can substantially improve the retrieval performance for brain tumors in CE‐MRI.Keywords
Funding Information
- National Science & Technology Pillar Program of China (2012BAI14B02)
- National Basic Research Program of China (2010CB732505)
This publication has 36 references indexed in Scilit:
- Similarity evaluation in a content‐based image retrieval (CBIR) CADx system for characterization of breast masses on ultrasound imagesMedical Physics, 2011
- Brain CT image database building for computer-aided diagnosis using content-based image retrievalInformation Processing & Management, 2011
- Local Structure-Based Region-of-Interest Retrieval in Brain MR ImagesIEEE Transactions on Information Technology in Biomedicine, 2010
- Medical Image Categorization and Retrieval for PACS Using the GMM-KL FrameworkIEEE Transactions on Information Technology in Biomedicine, 2007
- A Two-Level CBIR Platform with Application to Brain MRI Retrieval2005
- Image-matching as a medical diagnostic support tool (DST) for brain diseases in childrenComputerized Medical Imaging and Graphics, 2005
- A review of content-based image retrieval systems in medical applications—clinical benefits and future directionsInternational Journal of Medical Informatics, 2004
- Design and analysis of a content-based pathology image retrieval systemIEEE Transactions on Information Technology in Biomedicine, 2003
- Content-based retrieval of dynamic PET functional imagesIEEE Transactions on Information Technology in Biomedicine, 2000
- Knowledge-based image retrieval with spatial and temporal constructsIEEE Transactions on Knowledge and Data Engineering, 1998