• Home
  • Search
  • Bony structure enhanced synthetic CT generation using Dixon sequences for pelvis MR-only radiotherapy.
  • Cite Icon11
  • https://doi.org/10.1002/mp.16556Copy DOI Icon

Bony structure enhanced synthetic CT generation using Dixon sequences for pelvis MR-only radiotherapy.

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

MRI-only radiotherapy planning (MROP) is beneficial to patients by avoiding MRI/CT registration errors, simplifying the radiation treatment simulation workflow and reducing exposure to ionizing radiation. MRI is the primary imaging modality for soft tissue delineation. Treatment planning CTs (i.e., CT simulation scan) are redundant if a synthetic CT (sCT) can be generated from the MRI to provide the patient positioning and electron density information. Unsupervised deep learning (DL) models like CycleGAN are widely used in MR-to-sCT conversion, when paired patient CT and MR image datasets are not available for model training. However, compared to supervised DL models, they cannot guarantee anatomic consistency, especially around bone. The purpose of this work was to improve the sCT accuracy generated from MRI around bone for MROP. To generate more reliable bony structures on sCT images, we proposed to add bony structure constraints in the unsupervised CycleGAN model's loss function and leverage Dixon constructed fat and in-phase (IP) MR images. Dixon images provide better bone contrast than T2-weighted images as inputs to a modified multi-channel CycleGAN. A private dataset with a total of 31 prostate cancer patients were used for training (20) and testing (11). We compared model performance with and without bony structure constraints using single- and multi-channel inputs. Among all the models, multi-channel CycleGAN with bony structure constraints had the lowest mean absolute error, both inside the bone and whole body (50.7 and 145.2 HU). This approach also resulted in the highest Dice similarity coefficient (0.88) of all bony structures compared with the planning CT. Modified multi-channel CycleGAN with bony structure constraints, taking Dixon-constructed fat and IP images as inputs, can generate clinically suitable sCT images in both bone and soft tissue. The generated sCT images have the potential to be used for accurate dose calculation and patient positioning in MROP radiation therapy.

Similar Papers
  • Research Article
  • Citations260

Dose evaluation of fast synthetic-CT generation using a generative adversarial network for general pelvis MR-only radiotherapy

  • Sep 01, 2018
  • Physics in Medicine & Biology
  • Matteo Maspero +7
  • Dissertation

Dose evaluation of a deep learning-based synthetic CT generation in head and neck cancer for photon and proton therapy

  • Jan 01, 2023
  • Ailada Kuibumrung
  • Research Article
  • Citations2

End-to-end validation of fiducial tracking accuracy in robotic radiosurgery using MRI-only simulation imaging.

  • Dec 06, 2023
  • Medical Physics
  • Kamal Singhrao +4
  • Research Article
  • Citations24

Compensation cycle consistent generative adversarial networks (Comp-GAN) for synthetic CT generation from MR scans with truncated anatomy.

  • Feb 04, 2023
  • Medical physics
  • Yao Zhao +9
  • Research Article
  • Citations6

Automated hallucination detection for synthetic CT images used in MR-only radiotherapy workflows

  • Feb 25, 2025
  • Physics in Medicine & Biology
  • Abdul K Parchur +4
  • PDF
  • Research Article
  • Citations3

Contouring practices and artefact management within a synthetic CT-based radiotherapy workflow for the central nervous system

  • Feb 29, 2024
  • Radiation Oncology
  • Elia Rossi +5
  • PDF
  • Research Article
  • Citations51

Clinical validation of a commercially available deep learning software for synthetic CT generation for brain

  • Apr 07, 2021
  • Radiation Oncology
  • Minna Lerner +5
  • Research Article
  • Citations4

Generating synthetic CT images from unpaired head and neck CBCT images and validating the importance of detailed nasal cavity acquisition through simulations.

  • Feb 01, 2025
  • Computers in biology and medicine
  • Susie Ryu +3
  • PDF
  • Research Article
  • Citations137

Comparison of CBCT based synthetic CT methods suitable for proton dose calculations in adaptive proton therapy

  • Apr 27, 2020
  • Physics in Medicine & Biology
  • Adrian Thummerer +9
  • Conference Article
  • Citations4

PET attenuation correction (AC) using non-AC PET-based synthetic CT

  • Mar 16, 2020
  • Medical Imaging 2020: Physics of Medical Imaging
  • Yang Lei +8
  • Research Article
  • Citations4

Clinical implementation of deep learning-based synthetic CT for MRI-only volumetric modulated arc therapy in head and neck and pelvic cancer patients

  • Nov 12, 2025
  • Radiation Oncology (London, England)
  • Pareena Earwong +8
  • Research Article
  • Citations6

Daily proton dose re-calculation on deep-learning corrected cone-beam computed tomography scans.

  • Aug 01, 2025
  • Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology
  • Casper Dueholm Vestergaard +6
  • Research Article

Quantitative Analysis of the Impact of Various iCBCTs on the Image Quality of Lung Adaptive Radiotherapy

  • Jul 30, 2025
  • Zhongguo yi liao qi xie za zhi = Chinese journal of medical instrumentation
  • Ruifeng Zhao +2
  • Research Article
  • Citations50

Improving generalization in MR-to-CT synthesis in radiotherapy by using an augmented cycle generative adversarial network with unpaired data.

  • Apr 24, 2021
  • Medical physics
  • Kévin N D Brou Boni +4
  • Research Article
  • Citations11

Indirect deformable image registration using synthetic image generated by unsupervised deep learning

  • Jun 21, 2024
  • Image and Vision Computing
  • Cédric Hémon +9
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.