Related Experiment Video
Updated: May 11, 2026
Creating Dynamic Images of Short-lived Dopamine Fluctuations with lp-ntPET: Dopamine Movies of Cigarette Smoking
Published on: August 6, 2013
PETFormer-SCL: a supervised contrastive learning-guided CNN-transformer hybrid network for Parkinsonism
Shaoyou Wu1, Chenyang Li1, Jiaying Lu2
1Institute of Biomedical Engineering, School of Life Sciences, Shanghai University, Shanghai, 200444, China.
Purpose:
Accurate differentiation of Parkinsonism subtypes-including Parkinson's disease (PD), multiple system atrophy (MSA), and progressive supranuclear palsy (PSP)-is essential for clinical prognosis and treatment planning. However, this remains a major challenge due to overlapping symptomatology and high inter-individual variability in cerebral glucose metabolism patterns observed on fluorodeoxyglucose positron emission tomography (FDG-PET).
Methods:
To address these challenges, we propose PETFormer-SCL, a clinically informed deep learning framework that integrates convolutional neural networks (CNNs) with a channel-wise Transformer module, guided by supervised contrastive learning (SCL). This architecture is designed to enhance disease-specific feature learning while mitigating individual variability.
Results:
Trained on 945 patients and evaluated on an independent test cohort of 330 patients (1275 in total), PETFormer-SCL achieved AUCs of 0.9830, 0.9702, and 0.9565 for MSA, PD, and PSP, respectively. In addition, class activation maps (CAMs) highlighted key disease-related brain regions-including the cerebellum, midbrain, and basal ganglia-demonstrating strong alignment with known pathophysiological findings.
Conclusions:
PETFormer-SCL not only achieves high diagnostic accuracy, particularly for subtypes with overlapping phenotypes, but also enhances interpretability. These results support its potential as a reliable clinical decision-support tool for the early and differential diagnosis of Parkinsonism.
