EUVIMEDAtrasti EUVIMED
Open access · CC BY 4.0

Generation of synthetic CT from MRI for MRI‐based attenuation correction of brain PET images using radiomics and machine learning

Amin Hoseinipourasl, Gholam-Ali Hossein-Zadeh, Peyman Sheikhzadeh, Hossein Arabalibeik, Shaghayegh Karimi Alavijeh, Habib Zaidi, Mohammad Reza Ay

Medical Physics · 2025

DOI: 10.1002/mp.17867 ↗

At a glance

Journal article in Medical Physics, 2025. Written by Amin Hoseinipourasl and 6 co-authors. Institution: Research Center for Molecular and Cellular Imaging (RCMCI), Advanced Medical Technologies and Equipment Institute (AMTEI), Tehran University of Medic…. Major MEDLINE topics: Machine Learning, Magnetic Resonance Imaging, Brain, Image Processing, Computer-Assisted. Cited 4 times so far (Crossref); 46 references. The full text is freely available (open access, CC BY 4.0). Funded by: Tehran University of Medical Sciences, National Brain Mapping Laboratory (NBML), Swiss National Science Foundation.

SantraukaSubjectsBibliografiniai duomenysCiteRelated studies

Abstract (original language)

Background

Accurate quantitative PET imaging in neurological studies requires proper attenuation correction. MRI‐guided attenuation correction in PET/MRI remains challenging owing to the lack of direct relationship between MRI intensities and linear attenuation coefficients.

Purpose

This study aims at generating accurate patient‐specific synthetic CT volumes, attenuation maps, and attenuation correction factor (ACF) sinograms with continuous values utilizing a combination of machine learning algorithms, image processing techniques, and voxel‐based radiomics feature extraction approaches.

Methods

Brain MR images of ten healthy volunteers were acquired using IR‐pointwise encoding time reduction with radial acquisition (IR‐PETRA) and VIBE‐Dixon techniques. synthetic CT (SCT) images, attenuation maps, and attenuation correction factors (ACFs) were generated using the LightGBM, a fast and accurate machine learning algorithm, from the radiomics‐based and image processing‐based feature maps of MR images. Additionally, ultra‐low‐dose CT images of the same volunteers were acquired and served as the standard of reference for evaluation. The SCT images, attenuation maps, and ACF sinograms were assessed using qualitative and quantitative evaluation metrics and compared against their corresponding reference images, attenuation maps, and ACF sinograms.

Results

The voxel‐wise and volume‐wise comparison between synthetic and reference CT images yielded an average mean absolute error of 60.75 ± 8.8 HUs, an average structural similarity index of 0.88 ± 0.02, and an average peak signal‐to‐noise ratio of 32.83 ± 2.74 dB. Additionally, we compared MRI‐based attenuation maps and ACF sinograms with their CT‐based counterparts, revealing average normalized mean absolute errors of 1.48% and 1.33%, respectively.

Conclusion

Quantitative assessments indicated higher correlations and similarities between LightGBM‐synthesized CT and Reference CT images. Moreover, the cross‐validation results showed the possibility of producing accurate SCT images, MRI‐based attenuation maps, and ACF sinograms. This might spur the implementation of MRI‐based attenuation correction on PET/MRI and dedicated brain PET scanners with lower computational time using CPU‐based processors.

Subjects

MeSH terms (MEDLINE)

Machine LearningMagnetic Resonance ImagingBrainImage Processing, Computer-AssistedTomography, X-Ray ComputedPositron-Emission TomographyHumansAdultMaleFemaleRadiomics

Author keywords

PET/MRIattenuation correctionmachine learningradiomicssynthetic CT

Authors and institutions

  • Research Center for Molecular and Cellular Imaging (RCMCI), Advanced Medical Technologies and Equipment Institute (AMTEI), Tehran University of Medical Sciences (TUMS), Tehran, Iran.
  • Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran.
  • School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran.
  • Nuclear Medicine Department, IKHC, Faculty of Medicine, Tehran University of Medical Science, Tehran, Iran.
  • Research Center for Biomedical Technologies and Robotics, Tehran University of Medical Sciences, IK Hospital Complex, Tehran, Iran.
  • Division of Nuclear Medicine & Molecular Imaging, Geneva University Hospital, Geneva, Switzerland.

Funding

  • Tehran University of Medical Sciences
  • National Brain Mapping Laboratory (NBML)
  • Swiss National Science Foundation
  • Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung

Cite

APA

Hoseinipourasl, A., Hossein-Zadeh, G. A., Sheikhzadeh, P., Arabalibeik, H., Alavijeh, S. K., Zaidi, H., & Ay, M. R. (2025). Generation of synthetic CT from MRI for MRI‐based attenuation correction of brain PET images using radiomics and machine learning. Medical Physics. https://doi.org/10.1002/mp.17867

Vancouver

Hoseinipourasl A, Hossein-Zadeh GA, Sheikhzadeh P, Arabalibeik H, Alavijeh SK, Zaidi H, et al. Generation of synthetic CT from MRI for MRI‐based attenuation correction of brain PET images using radiomics and machine learning. Medical Physics. 2025. doi:10.1002/mp.17867

BibTeX
@article{Hoseinipourasl2025,
  author = {Hoseinipourasl, Amin and Hossein-Zadeh, Gholam-Ali and Sheikhzadeh, Peyman and Arabalibeik, Hossein and Alavijeh, Shaghayegh Karimi and Zaidi, Habib and Ay, Mohammad Reza},
  title = {Generation of synthetic CT from MRI for MRI‐based attenuation correction of brain PET images using radiomics and machine learning},
  journal = {Medical Physics},
  year = {2025},
  doi = {10.1002/mp.17867}
}
Start for free →