Ingmar Voigt, D. Vitanovski, Razvan Ioan Ionasec, A. Tsymbal, B. Georgescu, K. Zhou, D. Huber, N. Navab, J. Hornegger, D. Comaniciu Learning discriminative distance functions for valve retrieval and improved decision support in valvular heart disease SPIE Medical Imaging, 2010, San Diego, USA, February 2010 (bib)
	Disorders of the heart valves constitute as a considerable health problem and often require surgical intervention. Recently various approaches were published seeking to overcome the shortcomings of current clinical practice,1, 2 that still relies on manually performed measurements for performance assessment. Clinical decisions are still based on generic information from clinical guidelines and publications and personal experience of clinicians. We present a framework for retrieval and decision support using learning based discriminative distance functions and visualization of patient similarity with relative neighborhood graphs3, 4 based on shape and derived features. Alongside we propose several applications, including interventional suitability and prediction of outcomes in valves, which are geared to enrich the available source for clinical decision finding and assist its process. Initial experimental results of classification based applications, which are shape-based diagnosis and suitability for intervention, on a set of 63 and 50 valves models are as high as 93% and 91% respectively.
	This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each authors copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.