Enhancing diagnosis of Parkinson's Disease through a deep learning-based multiclass interpretation of DaTscan SPECT images.
Authors
Affiliations (8)
Affiliations (8)
- Doctoral Program in Science, Technology, Environment and Mathematics, National Chung Cheng University, Chiayi, Taiwan; Department of Earth and Environmental Sciences, National Chung Cheng University, Chiayi, Taiwan.
- Department of Nuclear Medicine, Ditmanson Medical Foundation Chia-Yi Christian Hospital, Chiayi, Taiwan.
- Department of Chinese Medicine, Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Chiayi, Taiwan.
- Department of Mechanical Engineering, National Chung Cheng University, Chiayi, Taiwan; Department of Computer Science Engineering, School of Engineering and Technology, Sanjivani University, Kopargaon, Maharashtra, India; Department of Biomedical Engineering, Chennai Institute of Technology, Chennai, Tamilnadu, India.
- Department of Radiology, Ditmanson Medical Foundation Chia-Yi Christian Hospital, Chiayi, Taiwan.
- Department of Radiology, University of Iowa Healthcare, Iowa City, Iowa, United States.
- Department of Mechanical Engineering, National Chung Cheng University, Chiayi, Taiwan.
- Department of Earth and Environmental Sciences, National Chung Cheng University, Chiayi, Taiwan. Electronic address: [email protected].
Abstract
Early and accurate diagnosis of Parkinson's disease (PD) remains challenging due to clinical overlap with other parkinsonian syndromes. DaTscan single-photon emission computed tomography (SPECT) is widely used during diagnosis; however, a subset of clinically diagnosed patients presents scans without evidence of dopaminergic deficit (SWEDD), creating diagnostic ambiguity. This study developed and validated a deep learning (DL)-based multiclass framework to distinguish PD, SWEDD, and normal controls using DaTscan SPECT images. DaTscan images from the Parkinson's Progression Markers Initiative (PPMI) were used for model development, with external validation performed using an independent cohort from Chiayi Christian Hospital. AlexNet, EfficientNet-B0, and Vision Transformer (ViT) architectures were trained and evaluated using accuracy, precision, recall, and F1-score. The best-performing model was integrated into an automated diagnostic tool, the Parkinson's Disease Detector App. EfficientNet-B0 achieved the highest accuracy for three-class classification on the PPMI dataset (94.2%), outperforming ViT (92.0%) and AlexNet (89.5%). External validation demonstrated strong generalizability (accuracy 92.4%, F1-score 95.8%). The diagnostic app achieved 90.6% accuracy in distinguishing PD and SWEDD from controls. The proposed DL framework enables accurate multiclass classification of DaTscan SPECT images and shows promise as an objective adjunct for PD diagnosis. Multicenter validation is warranted.