MRI-free amyloid PET quantification using a deep learning model and white matter reference.
Authors
Affiliations (7)
Affiliations (7)
- Department of Biomedical Informatics, Hallym University Chuncheon Sacred Heart Hospital, Chuncheon-si, Republic of Korea.
- Artificial Intelligence Research Center, Hallym University Sacred Heart Hospital, Chuncheon-si, Republic of Korea.
- Department of Nuclear Medicine, College of Medicine, Hallym University, Hallym University Sacred Heart Hospital, Anyang-si, Republic of Korea.
- Department of Neurology, Hallym University Sacred Heart Hospital, Anyang-si, Republic of Korea.
- Department of Anesthesiology and Pain Medicine, Hallym University College of Medicine, Chuncheon-si, Republic of Korea.
- Department of Neurology, Hallym University College of Medicine, Chuncheon-si, Republic of Korea.
- Department of Nuclear Medicine, Hallym University College of Medicine, Hallym University Chuncheon Sacred Heart Hospital, Chuncheon, Republic of Korea.
Abstract
BackgroundAccurate quantification of standardized uptake value ratio (SUVR) in amyloid PET is essential for Alzheimer's disease (AD) diagnosis but typically requires MRI-based segmentation due to subtle uptake differences between gray and white matter.ObjectiveThis study aimed to develop and validate a 3-dimensional deep learning model capable of segmenting these tissues directly from PET images to enable MRI-free SUVR quantification for AD diagnosis.MethodsThis retrospective study included 385 participants who underwent brain amyloid PET and MRI. After excluding 12 data-corrupted cases, 373 subjects were divided into training (n = 318) and test (n = 55) sets. External validation used 625 PET/CT scans from the Alzheimer's Disease Neuroimaging Initiative. Model performance was assessed using Dice coefficients and intersection over union. PET-based SUVRs derived from model-generated masks were compared with MRI-based SUVRs using Spearman correlation, and their diagnostic utility was evaluated by group differences and receiver operating characteristic analysis.ResultsThe model achieved high Dice coefficients for grey matter (GM; 0.785 internal, 0.743 external) and white matter (WM; 0.838 internal, 0.803 external). PET/CT-based SUVR values strongly correlated with MRI references (Spearman's ρ ≥ 0.98, p < 0.001). PET/CT-derived SUVR<sub>GM</sub> and SUVR<sub>GM/WM</sub> predicted amyloid status (AUC 0.86 and 0.85, respectively) and cognitive impairment (AUC 0.78).ConclusionsDeep learning-based amyloid PET segmentation enables accurate MRI-free quantification of gray and white matter SUVRs. This approach simplifies clinical workflow while maintaining diagnostic performance comparable to MRI-based methods for AD diagnosis.