A framework for radiological assistant systems

Abstract

The market for health care systems supporting physicians and improving their daily routine is dynamically growing. The development of these systems makes great demands on the handling of medical knowledge like anatomical and process knowledge. In this paper a special approach for the radiological domain will be presented. Our framework includes mechanisms to store medical knowledge in different knowledge containers, whose importance is varying from application to application, and to support the execution of the processes. Three applications are introduced exemplary. We analyzed the application scenarios to find the knowledge intensive tasks, that can be supported by an assistant system. The implemented solutions are integrated in daily work of our radiological partner hospitals.

Integrating CBR into the health care organization

“…It is essential to identify the process steps in the medical workflow, where CBR-based retrieval can support knowledge intensive tasks. During the last years, research has already started and several systems supporting guidelines and dealing with the execution and analysis of organizational processes have been developed [5]. First steps heading in the direction to support the complete administrative workflow have also been performed and good representatives are Ward-in-Hand [17] and the "Communication approach" [1].…”

“…We also have developed solutions for very special problems, amongst others a system to detect breast cancer in contrast enhanced MR sequences early [5], a system to reconstruct and measure aortic aneurysms for the design of personalized endoluminal prostheses [11], and an application to detect and quantify Neurocysticercosis in CT scans of epileptic patients [12]. All these systems are used in the daily routine of our partner hospitals and clinics in Germany and Brazil, because they are connected with CyclopsDistMedDB, our transparent gateway for distributed data access in DICOM 1 format [13].…”

“…Image interpretation tasks to support diagnosis are performed by ImageCreek and SCINA. FM-Ultranet [4,5] supports ultrasonographists during interpretation of ultrasonographic scans by retrieving similar cases. ProtoISIS and MacRad classify medical images, whereas other systems classify special disease patterns like eating disorders (MNAOMIA).…”