% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Lopes:276157,
author = {Lopes, Leonor and Jiao, Fangyang and Xue, Song and Pyka,
Thomas and Krieger, Korbinian and Ge, Jingjie and Xu, Qian
and Fahmi, Rachid and Spottiswoode, Bruce and Soliman, Ahmed
and Buchert, Ralph and Brendel, Matthias and Hong, Jimin and
Guan, Yihui and Bassetti, Claudio L A and Rominger, Axel and
Zuo, Chuantao and Shi, Kuangyu and Wu, Ping},
title = {{D}opaminergic {PET} to {SPECT} domain adaptation: a cycle
{GAN} translation approach.},
journal = {European journal of nuclear medicine and molecular imaging},
volume = {52},
number = {3},
issn = {1619-7070},
address = {Heidelberg [u.a.]},
publisher = {Springer-Verl.},
reportid = {DZNE-2025-00229},
pages = {851 - 863},
year = {2025},
abstract = {Dopamine transporter imaging is routinely used in
Parkinson's disease (PD) and atypical parkinsonian syndromes
(APS) diagnosis. While [11C]CFT PET is prevalent in Asia
with a large APS database, Europe relies on [123I]FP-CIT
SPECT with limited APS data. Our aim was to develop a deep
learning-based method to convert [11C]CFT PET images to
[123I]FP-CIT SPECT images, facilitating multicenter studies
and overcoming data scarcity to promote Artificial
Intelligence (AI) advancements.A CycleGAN was trained on
[11C]CFT PET (n = 602, $72\%PD)$ and [123I]FP-CIT SPECT (n =
1152, $85\%PD)$ images from PD and non-parkinsonian control
(NC) subjects. The model generated synthetic SPECT images
from a real PET test set (n = 67, $75\%PD).$ Synthetic
images were quantitatively and visually evaluated.Fréchet
Inception Distance indicated higher similarity between
synthetic and real SPECT than between synthetic SPECT and
real PET. A deep learning classification model trained on
synthetic SPECT achieved sensitivity of $97.2\%$ and
specificity of $90.0\%$ on real SPECT images. Striatal
specific binding ratios of synthetic SPECT were not
significantly different from real SPECT. The striatal
left-right differences and putamen binding ratio were
significantly different only in the PD cohort. Real PET and
real SPECT had higher contrast-to-noise ratio compared to
synthetic SPECT. Visual grading analysis scores showed no
significant differences between real and synthetic SPECT,
although reduced diagnostic performance on synthetic images
was observed.CycleGAN generated synthetic SPECT images
visually indistinguishable from real ones and retained
disease-specific information, demonstrating the feasibility
of translating [11C]CFT PET to [123I]FP-CIT SPECT. This
cross-modality synthesis could enhance further AI
classification accuracy, supporting the diagnosis of PD and
APS.},
keywords = {Humans / Tomography, Emission-Computed, Single-Photon:
methods / Positron-Emission Tomography: methods / Parkinson
Disease: diagnostic imaging / Parkinson Disease: metabolism
/ Image Processing, Computer-Assisted: methods / Male /
Female / Dopamine: metabolism / Deep Learning / Middle Aged
/ Dopamine Plasma Membrane Transport Proteins: metabolism /
Aged / Tropanes / CFT PET (Other) / Cycle GAN (Other) /
Domain adaptation (Other) / FP-CIT SPECT (Other) /
Parkinson’s disease (Other) / Dopamine (NLM Chemicals) /
Dopamine Plasma Membrane Transport Proteins (NLM Chemicals)
/ 2-carbomethoxy-8-(3-fluoropropyl)-3-(4-iodophenyl)tropane
(NLM Chemicals) / Tropanes (NLM Chemicals)},
cin = {AG Haass},
ddc = {610},
cid = {I:(DE-2719)1110007},
pnm = {352 - Disease Mechanisms (POF4-352)},
pid = {G:(DE-HGF)POF4-352},
typ = {PUB:(DE-HGF)16},
pubmed = {pmid:39557690},
doi = {10.1007/s00259-024-06961-x},
url = {https://pub.dzne.de/record/276157},
}