Local Texture Features for Content-Based Image Retrieval of Interstitial Lung Disease Patterns on HRCT Lung Images

Abstract

Content-based image retrieval (CBIR) is a technique that may help radiologists in their daily clinical practice by providing reference images against a given subject in hand for diagnosis. Several special purpose medical CBIR systems are built for the diagnosis of interstitial lung diseases (ILDs). Texture is used as a primitive feature to build such systems due to the texture-like appearance of ILD patterns. Therefore, it is necessary to evaluate the efficacy of promising texture feature descriptors proposed recently for building the CBIR system for ILDs. This paper presents an effective and exhaustive evaluation of five such recently proposed texture feature descriptors (viz. local binary pattern (LBP), orthogonal combination of local binary pattern (OC-LBP), center-symmetric local binary pattern (CS-LBP), local neighborhood difference pattern (LNDP), and combination of LNDP and LBP) for the design and development of CBIR system for ILDs. The performance of each method is compared using the most used performance metrics such as precision, recall, and F-score. The LNDP descriptor is found to be the best performer and therefore can be considered as a descriptor for ILD patterns for the design and development of CBIR system.