Improved MRI-based Pseudo-CT Synthesis via Segmentation Guided Attention Networks

Gurbandurdy Dovletov, Duc Duy Pham, Josef Pauli, Marcel Gratz, Marcel Gratz, Harald H. Quick, Harald H. Quick

2022

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.

Paper Citation

in Harvard Style

Dovletov G., Pham D., Pauli J., Gratz M. and Quick H. (2022). Improved MRI-based Pseudo-CT Synthesis via Segmentation Guided Attention Networks. In Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 2: BIOIMAGING; ISBN 978-989-758-552-4, SciTePress, pages 131-140. DOI: 10.5220/0010849200003123

in Bibtex Style

@conference{bioimaging22,
author={Gurbandurdy Dovletov and Duc Duy Pham and Josef Pauli and Marcel Gratz and Harald H. Quick},
title={Improved MRI-based Pseudo-CT Synthesis via Segmentation Guided Attention Networks},
booktitle={Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 2: BIOIMAGING},
year={2022},
pages={131-140},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010849200003123},
isbn={978-989-758-552-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 2: BIOIMAGING
TI - Improved MRI-based Pseudo-CT Synthesis via Segmentation Guided Attention Networks
SN - 978-989-758-552-4
AU - Dovletov G.
AU - Pham D.
AU - Pauli J.
AU - Gratz M.
AU - Quick H.
PY - 2022
SP - 131
EP - 140
DO - 10.5220/0010849200003123
PB - SciTePress