Optimization of reference library used in content-based medical image retrieval scheme.

Department of Radiology, University of Pittsburgh, 3362 Fifth Avenue, Pittsburgh, Pennsylvania 15213, USA.
Medical Physics (Impact Factor: 2.91). 12/2007; 34(11):4331-9. DOI: 10.1118/1.2795826
Source: PubMed

ABSTRACT Building an optimal image reference library is a critical step in developing the interactive computer-aided detection and diagnosis (I-CAD) systems of medical images using content-based image retrieval (CBIR) schemes. In this study, the authors conducted two experiments to investigate (1) the relationship between I-CAD performance and size of reference library and (2) a new reference selection strategy to optimize the library and improve I-CAD performance. The authors assembled a reference library that includes 3153 regions of interest (ROI) depicting either malignant masses (1592) or CAD-cued false-positive regions (1561) and an independent testing data set including 200 masses and 200 false-positive regions. A CBIR scheme using a distance-weighted K-nearest neighbor algorithm is applied to retrieve references that are considered similar to the testing sample from the library. The area under receiver operating characteristic curve (Az) is used as an index to evaluate the I-CAD performance. In the first experiment, the authors systematically increased reference library size and tested I-CAD performance. The result indicates that scheme performance improves initially from Az= 0.715 to 0.874 and then plateaus when the library size reaches approximately half of its maximum capacity. In the second experiment, based on the hypothesis that a ROI should be removed if it performs poorly compared to a group of similar ROIs in a large and diverse reference library, the authors applied a new strategy to identify "poorly effective" references. By removing 174 identified ROIs from the reference library, I-CAD performance significantly increases to Az = 0.914 (p < 0.01). The study demonstrates that increasing reference library size and removing poorly effective references can significantly improve I-CAD performance.

  • [Show abstract] [Hide abstract]
    ABSTRACT: Computer-aided detection (CADe) and computer-aided diagnosis (CADx) are emerging technologies to help radiologists interpret medical images. In screening mammography, CADe can help radiologists avoid overlooking a cancer, while CADx can help radiologists decide whether a biopsy is warranted when reading a diagnostic mammogram. Even though there is much commonality in the techniques used in CADe and CADx algorithms, there are important differences in the input data and in the output of the algorithms. In particular, CADe outputs the location of potential cancers, while CADx outputs the likelihood that a known lesion is malignant. These differences affect the metrics used to evaluate their performance. Commercial CADe systems have been developed and clinical studies of CADe have indicated the ability to increase radiologists' sensitivity by approximately 10% with a comparable increase in the recall rate. Commercial CADx systems do not exist till date, but observer study results are very compelling. CADe and CADx schemes continue to evolve in terms of accuracy and user interface. It is expected that CADe and eventually CADx will play an increasingly important role in breast imaging in the future.
    03/2010: pages 85-106;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: With the rapid growing volume of images in medical databases, development of efficient image retrieval systems to retrieve relevant or similar images to a query image has become an active research area. Despite many efforts to improve the performance of techniques for accurate image retrieval, its success in biomedicine thus far has been quite limited. This article presents an adaptive content-based image retrieval (CBIR) system for improving the performance of image retrieval in mammographic databases. In this work, the authors propose a new relevance feedback approach based on incremental learning with support vector machine (SVM) regression. Also, the authors present a new local perturbation method to further improve the performance of the proposed relevance feedback system. The approaches enable efficient online learning by adapting the current trained model to changes prompted by the user's relevance feedback, avoiding the burden of retraining the CBIR system. To demonstrate the proposed image retrieval system, the authors used two mammogram data sets: A set of 76 mammograms scored based on geometrical similarity and a larger set of 200 mammograms scored by expert radiologists based on pathological findings. The experimental results show that the proposed relevance feedback strategy improves the retrieval precision for both data sets while achieving high efficiency compared to offline SVM. For the data set of 200 mammograms, the authors obtained an average precision of 0.48 and an area under the precision-recall curve of 0.79. In addition, using the same database, the authors achieved a high pathology matching rate greater than 80% between the query and the top retrieved images after relevance feedback. Using mammographic databases, the results demonstrate that the proposed approach is more accurate than the model without using relevance feedback not only in image retrieval but also in pathology matching while maintaining its effectiveness for online relevance feedback applications.
    Medical Physics 08/2010; 37(8):4432-44. · 2.91 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Although a wide variety of Computer-Aided Diagnosis (CADx) schemes have been proposed across breast imaging modalities, and especially in mammography, research is still ongoing to meet the high performance CADx requirements. In this chapter, methodological contributions to CADx in mammography and adjunct breast imaging modalities are reviewed, as they play a major role in early detection, diagnosis and clinical management of breast cancer. At first, basic terms and definitions are provided. Then, emphasis is given to lesion content derivation, both anatomical and functional, considering only quantitative image features of micro-calcification clusters and masses across modalities. Additionally, two CADx application examples are provided. The first example investigates the effect of segmentation accuracy on micro-calcification cluster morphology derivation in X-ray mammography. The second one demonstrates the efficiency of texture analysis in quantification of enhancement kinetics, related to vascular heterogeneity, for mass classification in dynamic contrast-enhanced magnetic resonance imaging.
    12/2010: pages 329-357;

Full-text (2 Sources)

Available from
May 26, 2014