Paired PET‐MRI Deep Learning Model for Translating [ 11 C]PiB to [ 18 F]Florbetaben Amyloid Images
Medical Physics · 2025
DOI: 10.1002/mp.70168 ↗At a glance
Journal article in Medical Physics, 2025. Written by Cheng-Han Tsai and 5 co-authors. Institution: Department of Biomedical Engineering, National Taiwan University, Taipei, Taiwan. Major MEDLINE topics: Stilbenes, Aniline Compounds, Positron-Emission Tomography, Magnetic Resonance Imaging. 35 references. The full text is freely available (open access, CC BY 4.0). Funded by: Ministry of Education, Taiwan R.O.C., National Science and Technology Council, National Health Research Institutes.
Abstract (original language)
Background
Amyloid PET imaging has been extensively employed in the noninvasive assessment of amyloid‐beta accumulation in Alzheimer's disease. Various amyloid radiotracers are commonly used in clinical settings; however, the limited interchangeability among these radiotracers hinders the feasibility of long‐term clinical trials and multicenter comparisons. The Centiloid method was proposed for standardization, though providing a single score per image; voxel‐wise translation remains a formidable task.
Purpose
This paper proposes a U‐Net model based on a deformable convolution network (DCNv3‐based U‐Net) for []‐Pittsburgh compound B‐to‐[]‐florbetaben image translation to augment existing datasets for large‐scale model training and provide image information when inconsistencies between visual assessments and the Centiloid scale occur.
Methods
The DCNv3‐based U‐Net combined the benefits of deformable convolution that captures long‐range dependencies with efficient computation and the encoder–decoder architecture with skip connections for local–global feature learning and image synthesis.
Results
The prediction images presented increased homogeneity to other previous models, closely resembling the texture of []‐florbetaben.
Conclusions
The DCNv3‐based U‐Net demonstrated high performance in metrics measurement and statistical analyses for the PET image‐to‐image translation task. This work also justified the importance of MR images in providing structural information.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Department of Biomedical Engineering, National Taiwan University, Taipei, Taiwan.
- Department of Medical Imaging and Radiological Sciences, Chang Gung University, Taoyuan, Taiwan.
Funding
- Ministry of Education, Taiwan R.O.C.
- National Science and Technology Council
- National Health Research Institutes
Cite
APA
Tsai, C. H., Huang, S. Y., Lin, Y. N., Wang, H. W., Hsiao, I. T., & Chen, K. T. (2025). Paired PET‐MRI Deep Learning Model for Translating [ 11 C]PiB to [ 18 F]Florbetaben Amyloid Images. Medical Physics. https://doi.org/10.1002/mp.70168
Vancouver
Tsai CH, Huang SY, Lin YN, Wang HW, Hsiao IT, Chen KT. Paired PET‐MRI Deep Learning Model for Translating [ 11 C]PiB to [ 18 F]Florbetaben Amyloid Images. Medical Physics. 2025. doi:10.1002/mp.70168
BibTeX
@article{Tsai2025,
author = {Tsai, Cheng-Han and Huang, Shao-Yi and Lin, Yu-Nong and Wang, Han-Wei and Hsiao, Ing-Tsung and Chen, Kevin T},
title = {Paired PET‐MRI Deep Learning Model for Translating [ 11 C]PiB to [ 18 F]Florbetaben Amyloid Images},
journal = {Medical Physics},
year = {2025},
doi = {10.1002/mp.70168}
}
EUVIMED