Nucl Med Mol Imaging.  2024 Dec;58(6):354-363. 10.1007/s13139-024-00869-y.

Accurate Automated Quantification of Dopamine Transporter PET Without MRI Using Deep Learning‑based Spatial Normalization

• Kang S
• Kim D
• Shin S
• Kim Y
• Choi H
• Lee J

• KMID: 2563233
• DOI: http://doi.org/10.1007/s13139-024-00869-y

Abstract

Purpose
Dopamine transporter imaging is crucial for assessing presynaptic dopaminergic neurons in Parkinson’s disease (PD) and related parkinsonian disorders. While 18 F-FP-CIT PET offers advantages in spatial resolution and sensitivity over 123 I-β-CIT or 123 I-FP-CIT SPECT imaging, accurate quantification remains essential. This study presents a novel automatic quantification method for 18 F-FP-CIT PET images, utilizing an artificial intelligence (AI)-based robust PET spatial normalization (SN) technology that eliminates the need for anatomical images.
Methods
The proposed SN engine consists of convolutional neural networks, trained using 213 paired datasets of 18 F-FPCIT PET and 3D structural MRI. Remarkably, only PET images are required as input during inference. A cyclic training strategy enables backward deformation from template to individual space. An additional 89 paired 18 F-FP-CIT PET and 3D MRI datasets were used to evaluate the accuracy of striatal activity quantification. MRI-based PET quantification using FIRST software was also conducted for comparison. The proposed method was also validated using 135 external datasets.
Results
The proposed AI-based method successfully generated spatially normalized 18 F-FP-CIT PET images, obviating the need for CT or MRI. The striatal PET activity determined by proposed PET-only method and MRI-based PET quantification using FIRST algorithm were highly correlated, with R 2 and slope ranging 0.96–0.99 and 0.98–1.02 in both internal and external datasets.
Conclusion
Our AI-based SN method enables accurate automatic quantification of striatal activity in 18 F-FP-CIT brain PET images without MRI support. This approach holds promise for evaluating presynaptic dopaminergic function in PD and related parkinsonian disorders.

Keyword

Dopamine transporter; Parkinson’s disease ; Spatial normalization; Deep learning ; Quantification