Share Email Print
cover

Proceedings Paper • new

Pseudo-CT image generation from mDixon MRI images using fully convolutional neural networks
Author(s): J. V. Stadelmann; H. Schulz; U. A. van der Heide; S. Renisch
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Generating pseudo-CT images from MRI provides electron density maps for radiation therapy planning and saves additional CT scans. Fully convolutional neural networks were proposed for pseudo-CT generation. We investigated the influence of architectures and hyperparameters on the quality of the pseudo-CT images. We used fully convolutional neural networks to transform between registered MRI and CT volumes of the pelvic region: two UNet variants using transposed convolutions or bilinear upsampling, LinkNet using residual blocks and strided convolutions for downsampling, and we designed transnet to maintain tensor spatial dimensions equal to the image’s size. Different architectures revealed similar error metrics, although pseudo-CTs differ visually. Comparison of LinkNet and UNet showed that downsampling does not affect translation. Replacing transposed convolutions with bilinear upsampling improved the pseudo-CTs’ sharpness. Translation quality quickly saturates with the number of convolution layers; increasing the number of layers from 4 to 19 decreases the MAE from 44HU to 37HU. Varying the number of feature maps showed that good translation quality can be achieved with networks that are substantially narrower than those previously published. Generally, the pseudo-CT have MAE lower than 45HU, computed inside of the true CT’s body shape.

Paper Details

Date Published: 15 March 2019
PDF: 11 pages
Proc. SPIE 10953, Medical Imaging 2019: Biomedical Applications in Molecular, Structural, and Functional Imaging, 109530Z (15 March 2019); doi: 10.1117/12.2512741
Show Author Affiliations
J. V. Stadelmann, Philips Research Skolkovo (Russian Federation)
H. Schulz, Philips GmbH (Germany)
U. A. van der Heide, The Netherlands Cancer Institute (Netherlands)
S. Renisch, Philips GmbH (Germany)


Published in SPIE Proceedings Vol. 10953:
Medical Imaging 2019: Biomedical Applications in Molecular, Structural, and Functional Imaging
Barjor Gimi; Andrzej Krol, Editor(s)

© SPIE. Terms of Use
Back to Top