Frequency-Supervised MR-to-CT Image Synthesis
This work improves MR-to-CT synthesis for medical imaging, particularly in radiotherapy planning, but is incremental as it builds on existing deep learning methods by focusing on high-frequency enhancement.
The paper tackles the problem of generating synthetic CT images from MR images for radiotherapy planning, addressing the common limitation of poor reconstruction in high-frequency regions, and demonstrates effectiveness on a dataset of 45 MR-CT brain image pairs.
This paper strives to generate a synthetic computed tomography (CT) image from a magnetic resonance (MR) image. The synthetic CT image is valuable for radiotherapy planning when only an MR image is available. Recent approaches have made large strides in solving this challenging synthesis problem with convolutional neural networks that learn a mapping from MR inputs to CT outputs. In this paper, we find that all existing approaches share a common limitation: reconstruction breaks down in and around the high-frequency parts of CT images. To address this common limitation, we introduce frequency-supervised deep networks to explicitly enhance high-frequency MR-to-CT image reconstruction. We propose a frequency decomposition layer that learns to decompose predicted CT outputs into low- and high-frequency components, and we introduce a refinement module to improve high-frequency reconstruction through high-frequency adversarial learning. Experimental results on a new dataset with 45 pairs of 3D MR-CT brain images show the effectiveness and potential of the proposed approach. Code is available at \url{https://github.com/shizenglin/Frequency-Supervised-MR-to-CT-Image-Synthesis}.