An application framework for rapid prototyping of clinically applicable software assistants

Abstract

Computer assistance for clinical diagnosis support and treatment planning are continuously growing fields that have gained importance in several medical disciplines. Although a variety of algorithms are available today, only few are routinely applied for diagnosis support and treatment planning. We propose a hierarchical framework that allows for flexible and efficient development of clinically valuable software prototypes and for systematic evaluation of image processing methods in a research setting. A modular plug-in concept separates algorithmic and framework developments. Several basic components for data-, user-, and workflow-management provide a skeleton that can be customized by both application developer and user. Standardized interfaces allow the communication between both frame and application. Dedicated assistance is provided for an efficient radiological workflow integration. A flexible and simple handling of image processing and visualization algorithms within a modular programming interface is offered through an integration into a visual programming and rapid prototyping platform (MeVisLab). The capabilities of our framework are presented by means of exemplary prototypes, that are currently used in clinical practice.