A unified learning framework for content based medical image retrieval using a statistical model

This paper presents a unified learning framework for heterogeneous medical image retrieval based on a Full Range Autoregressive Model (FRAR) with the Bayesian approach (BA). Using the unified framework, the color autocorrelogram, edge orientation autocorrelogram (EOAC) and micro-texture information of medical images are extracted. The EOAC is constructed in HSV color space, to circumvent the loss of edges due to spectral and chromatic variations. The proposed system employed adaptive binary tree based support vector machine (ABTSVM) for efficient and fast classification of medical images in feature vector space. The Manhattan distance measure of order one is used in the proposed system to perform a similarity measure in the classified and indexed feature vector space. The precision and recall (PR) method is used as a measure of performance in the proposed system. Short-term based relevance feedback (RF) mechanism is also adopted to reduce the semantic gap. The Experimental results reveal that the retrieval performance of the proposed system for heterogeneous medical image database is better than the existing systems at low computational and storage cost.