Authors:
Gurbandurdy Dovletov
1
;
Duc Duy Pham
1
;
Josef Pauli
1
;
Marcel Gratz
2
;
3
and
Harald H. Quick
2
;
3
Affiliations:
1
Intelligent Systems Group, Faculty of Engineering, University of Duisburg-Essen, Duisburg, Germany
;
2
High-Field and Hybrid MR Imaging, University Hospital Essen, University of Duisburg-Essen, Essen, Germany
;
3
Erwin L. Hahn Institute for MR Imaging, University of Duisburg-Essen, Essen, Germany
Keyword(s):
Image-to-Image Translation, Pseudo-CT, Attention Mechanism, U-Net, Generative Adversarial Network.
Abstract:
In this paper, we propose 2D MRI-based pseudo-CT (pCT) generation approaches that are inspired by U-Net and generative adversarial networks (GANs) and that additionally utilize coarse bone segmentation guided attention (SGA) mechanisms for better image synthesis. We first introduce and formulate SGA and its extended version (E-SGA), then we embed them into our baseline U-Net and conditional Wasserstein GAN (cWGAN) architectures. Since manual bone annotations are expensive, we derive coarse bone segmentations from CT/pCT images via thresholding and utilize them during the training phase to guide image-to-image translation attention networks. For inference, no additional segmentations are required. The performance of the proposed methods regarding the image generation quality is evaluated on the publicly available RIRE data set. Since MR and CT image pairs in this data set are not correctly aligned with each other, we also briefly describe the applied image registration procedure. The
results of our experiments are compared to baseline U-Net and conditional Wasserstein GAN implementations and demonstrate improvements for bone regions.
(More)