Automatic anatomy recognition via multi-object-oriented active shape models

Abstract

The computerized assistive process of recognizing, delineating and quantifying organs and tissue regions in medical images, occurring automatically during clinical image interpretation, is called automatic anatomic recognition (AAR). This paper studies the feasibility of developing an AAR system in clinical radiology. The anatomy recognition method described here consists of three components: (a) oriented active shape modeling (OASM); (b) multi object generalization of OASM; (c) object recognition strategies. (b) and (c) are novel and depend heavily on the idea of OASM, presented previously in this conference. The delineation of an object boundary is done in OASM via a two level dynamic programming algorithm wherein the first level finds optimal location for the landmarks and the second level finds optimal oriented boundary segments between successive landmarks. This algorithm is generalized to multiple objects by including a model for each object and assigning a cost structure specific to each object in the spirit of live wire. The object recognition strategy attempts to find that pose vector (consisting of translation, rotation, and a scale component) for the multi object model that yields the smallest total boundary cost for all objects. The evaluation results on a routine clinical abdominal CT data set indicate the following: (1) High recognition accuracy can be achieved without fail by including a large number of objects which are spread out in the body region; (2) An overall delineation accuracy of TPVF>97%, FPVF<0.2% was achieved, suggesting the feasibility of AAR.