3D Slicer as a platform for the automatic segmentation of real-time MRI data

Abstract

Recent accomplishments in the field of medical imaging methods lead to the invention of real-time magnetic resonance imaging (MRI), a method that allows the recording of movies of, for example, the pumping heart. With real-time MRI, new insights into the physiology of the human heart can be gained but the method comes with a challenge: Different from conventional MRI, real-time MRI produces many more images that physicians and researchers possibly cannot evaluate manually. An ongoing research project at the German Aerospace Center evaluates machine learning methods to allow the automatic segmentation of cardiac real-time MRI images. A part of that project is the development of a software solution that researchers and medical staff can use to access the features of the automatic segmentation. This work aims at the evaluation of available software tools and frameworks in order to find a suitable tool for the development of the mentioned software solution. To accomplish this, different tools and frameworks are compared in terms of their feature sets, extendability, development workflows and licence restrictions. The Medical Imaging Interaction Toolkit and 3D Slicer will be compared in more depth leading to the selection of 3D Slicer. To prove that 3D Slicer is suitable as a software framework for the real-time MRI software solution, an example extension is developed that implements one of the software requirements. It will be concluded that 3D Slicer can be used to both efficiently implement the requirement of the example extension and be used as the base software framework to implement the other software requirements that are not developed as part of this work.