Content-based image retrieval for interstitial lung diseases

Abstract

Finding similar images or reference is one way to assist radiologist during daily clinical practice for differential diagnosis of Interstitial Lung Diseases (ILDs). Content Based Image Retrieval (CBIR) system could exploit the wealth of HRCT data stored in the archive by finding similar images or reference to assist radiologists during daily clinical practice. We have designed a special purpose CBIR system (Med-IR) for Interstitial Lung Diseases (ILDs), where the user can provide one interstitial disease pattern as input and the system will retrieve few most similar patterns available in the database. Three different feature extraction techniques are implemented. A graphical interface has been developed to give a query image and to display the retrieved images. The retrieval performances of three rotation invariant texture feature sets derived using Discrete Wavelet Transform (DWT), Dual Tree Complex Wavelet Transform (DT-CWT) and DT-CWT combined with Dual Tree Rotated Complex Wavelet Frame (DT-RCWF) are compared in terms of average precision and recall for ILDs pattern. The dataset used for evaluation contains 64 images representing four ILDs pattern such as consolidation, nodular, emphysema, ground glass and normal. It is observed that feature obtained using DT-CWT and DT-CWT combined with DT-RCWT out performs the features obtained using DWT techniques.