Authors:
Nils Frohwitter
1
;
2
;
Alessa Hering
3
;
Ralf Möller
1
;
2
and
Mattis Hartwig
1
;
4
Affiliations:
1
German Research Center for Artificial Intelligence, 23562 Lübeck, Germany
;
2
Institute of Information Systems, University of Lübeck, 23562 Lübeck, Germany
;
3
Fraunhofer MEVIS, Institute for Digital Medicine, 23562 Lübeck, Germany
;
4
singularIT GmbH, 04109 Leipzig, Germany
Keyword(s):
Image-to-Image Translation, Image Synthesis, Image Registration.
Abstract:
Radiation therapy often requires a computed tomography (CT) for treatment planning and an additional magnetic resonance (MR) imaging prior to the treatment for adaptation. With two different images from the same scene, multi-modal image registration is needed to align areas of interest in both images. One idea to improve the registration process is to perform an image synthesis that converts one image mode into another mode prior to the registration. In this paper, we address the research needed to perform a thorough evaluation of the synthesis step on overall registration performance using different well-known registration methods of the Advanced Normalization Tools (ANTs) framework. Given abdominal images, we use CycleGAN for synthesis and compare the registration performance to the one without synthesis by using four different well-known registration methods. We show that good image synthesizing results lead to an average improvement in all registration methods, biggest improvemen
t being achieved for the ‘Symmetric Normalization’ method with 8% (measured with Dice-score). The overall best registration method with prior synthesis is ‘Symmetric Normalization and Rigid’. Furthermore, we show that the images with bad synthetic results lead to worse registration, thus suggesting the correlation between synthesizing quality and registration performance.
(More)