• Home
  • Search
  • Generating synthetic CTs from magnetic resonance images using generative adversarial networks.
  • Open Access IconOpen Access
  • Cite Icon303
  • https://doi.org/10.1002/mp.13047Copy DOI Icon

Generating synthetic CTs from magnetic resonance images using generative adversarial networks.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

While MR-only treatment planning using synthetic CTs (synCTs) offers potential for streamlining clinical workflow, a need exists for an efficient and automated synCT generation in the brain to facilitate near real-time MR-only planning. This work describes a novel method for generating brain synCTs based on generative adversarial networks (GANs), a deep learning model that trains two competing networks simultaneously, and compares it to a deep convolutional neural network (CNN). Post-Gadolinium T1-Weighted and CT-SIM images from fifteen brain cancer patients were retrospectively analyzed. The GAN model was developed to generate synCTs using T1-weighted MRI images as the input using a residual network (ResNet) as the generator. The discriminator is a CNN with five convolutional layers that classified the input image as real or synthetic. Fivefold cross-validation was performed to validate our model. GAN performance was compared to CNN based on mean absolute error (MAE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR) metrics between the synCT and CT images. GAN training took ~11h with a new case testing time of 5.7±0.6s. For GAN, MAEs between synCT and CT-SIM were 89.3±10.3 Hounsfield units (HU) and 41.9±8.6HU across the entire FOV and tissues, respectively. However, MAE in the bone and air was, on average, ~240-255HU. By comparison, the CNN model had an average full FOV MAE of 102.4±11.1HU. For GAN, the mean PSNR was 26.6±1.2 and SSIM was 0.83±0.03. GAN synCTs preserved details better than CNN, and regions of abnormal anatomy were well represented on GAN synCTs. We developed and validated a GAN model using a single T1-weighted MR image as the input that generates robust, high quality synCTs in seconds. Our method offers strong potential for supporting near real-time MR-only treatment planning in the brain.

Similar Papers
  • Research Article

Text Image Reconstruction and Reparation for Khmer Historical Document

  • Jun 30, 2024
  • Techno-Science Research Journal
  • Chanchen Pork +2
  • Research Article
  • Citations9

Utilizing deep learning techniques to improve image quality and noise reduction in preclinical low-dose PET images in the sinogram domain.

  • Nov 15, 2023
  • Medical Physics
  • Kishore Krishnagiri Manoj Doss +1
  • Research Article
  • Citations133

Improving CBCT quality to CT level using deep learning with generative adversarial network.

  • May 14, 2021
  • Medical physics
  • Yang Zhang +8
  • Research Article

The Comparison of GAN and CNN Models in the Innovation of Coloring Madura and Bali Batik

  • Aug 01, 2025
  • JAREE (Journal on Advanced Research in Electrical Engineering)
  • Yohan Permana +3
  • Research Article
  • Citations1

The Effectiveness of Data Augmentation for Bone Suppression in Chest Radiograph using Convolutional Neural Network

  • Aug 18, 2021
  • Austin Journal of Cancer and Clinical Research
  • Ren G +5
  • Conference Article
  • Citations3

Anomaly Detection Using Convolutional Neural Network and Generative Adversarial Network

  • Apr 11, 2023
  • SAE technical papers on CD-ROM/SAE technical paper series
  • Amritha Mohanan +4
  • Research Article
  • Citations1

Coloring Pekalongan Batik Using a Madura Dataset: A Comparative Study of GAN and Caffe-Based CNN Models

  • Oct 18, 2024
  • Teknika
  • Muhamad Machrus Ali Wahyudi +3
  • PDF
  • Research Article
  • Citations6

Optimizing Generative Adversarial Network (GAN) Models for Non-Pneumatic Tire Design

  • Sep 25, 2023
  • Applied Sciences
  • Ju Yong Seong +4
  • Research Article
  • Citations91

Pavement crack detection algorithm based on generative adversarial network and convolutional neural network under small samples

  • Apr 19, 2022
  • Measurement
  • Boqiang Xu +1
  • Research Article

Advancements in Cross-modality Imaging: A Survey of CNN and GAN Applications in Medical Imaging

  • Nov 27, 2025
  • Sri Lankan Journal of Applied Statistics
  • Khadeeja Thahir +1
  • PDF
  • Research Article
  • Citations49

Various Generative Adversarial Networks Model for Synthetic Prohibitory Sign Image Generation

  • Mar 24, 2021
  • Applied Sciences
  • Christine Dewi +3
  • Research Article
  • Citations29

Reconfigurable and Low-Complexity Accelerator for Convolutional and Generative Networks Over Finite Fields

  • Dec 01, 2020
  • IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
  • Weihong Xu +3
  • Research Article
  • Citations2

Image synthesis of effective atomic number images using a deep convolutional neural network-based generative adversarial network.

  • Oct 31, 2022
  • Reports of Practical Oncology and Radiotherapy
  • Daisuke Kawahara +3
  • Research Article
  • Citations12

Bridging the Camera Domain Gap With Image-to-Image Translation Improves Glaucoma Diagnosis.

  • Dec 22, 2023
  • Translational Vision Science & Technology
  • Shuang He +9
  • Conference Article
  • Citations1

Facial Expression Recognition Based on An Improved Data Augmentation Method and A Multichannel Convolutional Neural Network Model

  • Jul 27, 2023
  • Xiuling Wang +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.