Content based retrieval of interstitial lung disease patterns using spatial distribution of intensity, gradient magnitude and gradient direction

Abstract

Today the enormous growth of medical images and scarcity of experienced pulmonologists and radiologists has led to the necessity of an efficient content-based image retrieval system capable of retrieve lung images similar to a given query image. This paper presents a promising texture-based image retrieval technique for interstitial lung disease categorisation by analysing the spatial distribution of intensity, along with its gradient magnitude and direction. The strengths of textural features derived from all different combinations of intensity, gradient magnitude and gradient direction are analysed. It is observed that both the magnitude and direction of intensity gradient contains significant textural information. Texture features can be substantially enriched by combining the features extracted from intensity, magnitude and direction of the intensity gradient as compared to that obtained from intensity alone. This approach is invariant to orientation of the texture and shape of the region of interest (ROI). The technique is simple, and is applicable to several other pattern recognition problems.