• Home
  • Search
  • Synthesizing CT images from MR images with deep learning: model generalization for different datasets through transfer learning
  • Cite Icon25
  • https://doi.org/10.1088/2057-1976/abe3a7Copy DOI Icon

Synthesizing CT images from MR images with deep learning: model generalization for different datasets through transfer learning

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

Background and purpose. Replacing CT imaging with MR imaging for MR-only radiotherapy has sparked the interest of many scientists and is being increasingly adopted in radiation oncology. Although many studies have focused on generating CT images from MR images, only models on data with the same dataset were tested. Therefore, how well the trained model will work for data from different hospitals and MR protocols is still unknown. In this study, we addressed the model generalization problem for the MR-to-CT conversion task. Materials and methods. Brain T2 MR and corresponding CT images were collected from SZSPH (source domain dataset), brain T1-FLAIR, T1-POST MR, and corresponding CT images were collected from The University of Texas Southwestern (UTSW) (target domain dataset). To investigate the model’s generalizability ability, four potential solutions were proposed: source model, target model, combined model, and adapted model. All models were trained using the CycleGAN network. The source model was trained with a source domain dataset from scratch and tested with a target domain dataset. The target model was trained with a target domain dataset and tested with a target domain dataset. The combined model was trained with both source domain and target domain datasets, and tested with the target domain dataset. The adapted model used a transfer learning strategy to train a CycleGAN model with a source domain dataset and retrain the pre-trained model with a target domain dataset. MAE, RMSE, PSNR, and SSIM were used to quantitatively evaluate model performance on a target domain dataset. Results. The adapted model achieved best quantitative results of 74.56 ± 8.61, 193.18 ± 17.98, 28.30 ± 0.83, and 0.84 ± 0.01 for MAE, RMSE, PSNR, and SSIM using the T1-FLAIR dataset and 74.89 ± 15.64, 195.73 ± 31.29, 27.72 ± 1.43, and 0.83 ± 0.04 for MAE, RMSE, PSNR, and SSIM using the T1-POST dataset. The source model had the poorest performance. Conclusions. This work indicates high generalization ability to generate synthetic CT images from small training datasets of MR images using pre-trained CycleGAN. The quantitative results of the test data, including different scanning protocols and different acquisition centers, indicated the proof of this concept.

Similar Papers
  • Research Article
  • Citations21

Source free unsupervised domain adaptation for electro-mechanical actuator fault diagnosis

  • Feb 24, 2023
  • Chinese Journal of Aeronautics
  • Jianyu Wang +2
  • Book Chapter
  • Citations5

Transferring Near Infrared Spectroscopic Calibration Model Across Different Harvested Seasons Using Joint Distribution Adaptation

  • Jan 01, 2022
  • Nur Aisyah Syafinaz Suarin +1
  • Conference Article

Construction of General Representation Model and Cross-domain Migration Method Based on Multi-modal Comparative Learning

  • Sep 27, 2025
  • Qianhui Yu +6
  • Conference Article
  • Citations2

A parameter based transfer learning fault diagnosis method under different working conditions

  • Oct 22, 2021
  • Xue Lei +3
  • PDF
  • Research Article
  • Citations6

Transfer Learning for LiDAR-Based Lane Marking Detection and Intensity Profile Generation

  • Jun 04, 2021
  • Geomatics
  • Ankit Patel +5
  • Research Article
  • Citations16

MDTGAN: Multi domain generative adversarial transfer learning network for traffic data imputation

  • Jun 25, 2024
  • Expert Systems With Applications
  • Jie Fang +3
  • Conference Article
  • Citations8

TCLD-Net: A Transfer Learning Internet Encrypted Traffic Classification Scheme Based on Convolution Neural Network and Long Short-Term Memory Network

  • Oct 15, 2021
  • Xinyi Hu +3
  • PDF
  • Research Article
  • Citations17

Research on sentiment analysis method of opinion mining based on multi-model fusion transfer learning

  • Oct 11, 2023
  • Journal of Big Data
  • Zhongnan Zhao +2
  • Research Article
  • Citations39

Deep Learning Domain Adaptation for Electro-Mechanical Actuator Fault Diagnosis Under Variable Driving Waveforms

  • Jun 01, 2022
  • IEEE Sensors Journal
  • Jianyu Wang +3
  • Research Article
  • Citations5

EasyDAM_V3: Automatic Fruit Labeling Based on Optimal Source Domain Selection and Data Synthesis via a Knowledge Graph.

  • Jan 01, 2023
  • Plant phenomics (Washington, D.C.)
  • Wenli Zhang +4
  • Research Article
  • Citations4

A systematic study on transfer learning: Automatically identifying empty camera trap images using deep convolutional neural networks

  • Feb 17, 2024
  • Ecological Informatics
  • Deng-Qi Yang +13
  • Research Article

Attack detection in internet of things networks with deep learning using deep transfer learning method

  • Jul 01, 2025
  • Computer Science and Information Technologies
  • Riki Abdillah Hasanuddin +1
  • Research Article
  • Citations21

Domain adaptation for semantic role labeling of clinical text.

  • Jun 10, 2015
  • Journal of the American Medical Informatics Association
  • Yaoyun Zhang +4
  • Conference Article
  • Citations27

An Inductive Transfer Learning Approach using Cycle-consistent Adversarial Domain Adaptation with Application to Brain Tumor Segmentation

  • Nov 13, 2019
  • Yuta Tokuoka +2
  • Research Article
  • Citations12

H-net: Unsupervised domain adaptation person re-identification network based on hierarchy

  • Aug 01, 2022
  • Image and Vision Computing
  • Deqiang Cheng +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.