Improving performance of content-based image retrieval schemes in searching for similar breast mass regions: an assessment

Abstract

This study aims to assess three methods commonly used in content-based image retrieval (CBIR) schemes and investigate the approaches to improve scheme performance. A reference database involving 3000 regions of interest (ROIs) was established. Among them, 400 ROIs were randomly selected to form a testing dataset. Three methods, namely mutual information, Pearson's correlation and a multi-feature-based k-nearest neighbor (KNN) algorithm, were applied to search for the 15 ‘the most similar’ reference ROIs to each testing ROI. The clinical relevance and visual similarity of searching results were evaluated using the areas under receiver operating characteristic (ROC) curves (AZ) and average mean square difference (MSD) of the mass boundary spiculation level ratings between testing and selected ROIs, respectively. The results showed that the AZ values were 0.893 ± 0.009, 0.606 ± 0.021 and 0.699 ± 0.026 for the use of KNN, mutual information and Pearson's correlation, respectively. The AZ values increased to 0.724 ± 0.017 and 0.787 ± 0.016 for mutual information and Pearson's correlation when using ROIs with the size adaptively adjusted based on actual mass size. The corresponding MSD values were 2.107 ± 0.718, 2.301 ± 0.733 and 2.298 ± 0.743. The study demonstrates that due to the diversity of medical images, CBIR schemes using multiple image features and mass size-based ROIs can achieve significantly improved performance.