Statistical framework for model-based image retrieval in medical applications

Abstract

Recently, research in the field of content-based image retrieval has attracted a lot of attention. Nevertheless, most existing methods cannot be easily applied to medical image databases, as global image descriptions based on color, texture, or shape do not supply sufficient semantics for medical applications. The concept for content-based image retrieval in medical applications (IRMA) is therefore based on the separation of the following processing steps: categorization of the entire image; registration with respect to proto- types; extraction and query-dependent selection of local features; hierarchical blob representation including object identification; and finally, image retrieval. Within the first step of processing, images are classified according to image modality, body orientation, ana- tomic region, and biological system. The statistical classifier for the anatomic region is based on Gaussian kernel densities within a probabilistic framework for multiobject recognition. Special empha- sis is placed on invariance, employing a probabilistic model of vari- ability based on tangent distance and an image distortion model. The performance of the classifier is evaluated using a set of 1617 radiographs from daily routine, where the error rate of 8.0% in this six-class problem is an excellent result, taking into account the dif- ficulty of the task. The computed posterior probabilities are further- more used in the subsequent steps of the retrieval process. © 2003