An Object-Oriented System for 3D Medical Image Analysis

As part of a European Commission-funded research project on medical image analysis, we have developed a system aimed at solving a real clinical problem: the outlining of the target volume and organs at risk for three-dimensional conformal radiation treatment planning. The clinical requirement is to make this process less tedious and time-consuming. We show how object-oriented design techniques can be used to good effect in a collaborative project such as this, so that image segmentation and other algorithms from a number of different partners in the consortium can be integrated into one system, for comparative evaluation by the clinical partners. We describe in some detail two of these algorithms, one a straighfforward region and volume grower, in which particular attention has been paid to adapting the user interface to suit clinical needs, and the other an interactive tool using b-spline surface patches for direct three-dimensional segmentation. We report on the clinical feedback we have received, which indicates that the most technically advanced algorithms are not necessarily the most useful from a clinician's point of view. C omputer Vision in Radiology, or COVIRA, was a research project in the AIM (Advanced Infor-matics in Medicine) program of the European Commission. The main goal of COVIRA was to provide pilot application systems for multimodality image analysis in the fields of radiological diagnosis, neu-rosurgery planning, and radiation therapy planning. Based on a detailed analysis of the clinical requirements at the start of the project, computer science 4 ELLIOlT ET AL partners carried out research in areas such as image segmentation and image registration. The resulting algorithms were integrated into a number of pilot systems in order that the clinical partners could evaluate them to assess what advances had been made. Each of the three industrial partners in the project developed its own clinical pilot system incorporating the relevant computer science algorithms. Philips Medical Systems produced a pilot system for general radiological diagnosis and neurosurgery planning , evaluated at the Gregorio Maraiion Hospital in Madrid, Spain, and the Academic Hospital in Utrecht, Netherlands. Siemens Medical Engineering produced a pilot system for neuroradiological diagnosis and neurosurgery planning, evaluated at the University Hospital of Tubingen, Germany, and the University Hospital of Leuven, Belgium (near Brus-sels). The IBM UK Scientific Centre developed a pilot system for three-dimensional (3D) conformal radiation treatment planning using X-ray computed tomography (CT) and magnetic resonance images (MRI).Wopyright 1996 by International Business Machines Corporation. …