S-Space College of Medicine/School of Medicine (의과대학/대학원) Psychiatry (정신과학전공) Journal Papers (저널논문_정신과학전공)
Deep learning-based amyloid PET positivity classification model in the Alzheimers disease continuum by using 2-[18F]FDG PET
- Kim, Suhong; Lee, Peter; Oh, Kyeong Taek; Byun, Min Soo; Yi, Dahyun; Lee, Jun Ho; Kim, Yu Kyeong; Ye, Byoung Seok; Yun, Mi Jin; Lee, Dong Young; Jeong, Yong
- Issue Date
- Springer Open
- EJNMMI Research. 2021 Jun 10;11(1):56
Considering the limited accessibility of amyloid position emission tomography (PET) in patients with dementia, we proposed a deep learning (DL)-based amyloid PET positivity classification model from PET images with 2-deoxy-2-[fluorine-18]fluoro-D-glucose (2-[18F]FDG).
We used 2-[18F]FDG PET datasets from the Alzheimer's Disease Neuroimaging Initiative and Korean Brain Aging Study for the Early diagnosis and prediction of Alzheimers disease for model development. Moreover, we used an independent dataset from another hospital. A 2.5-D deep learning architecture was constructed using 291 submodules and three axes images as the input. We conducted the voxel-wise analysis to assess the regions with substantial differences in glucose metabolism between the amyloid PET-positive and PET-negative participants. This facilitated an understanding of the deep model classification. In addition, we compared these regions with the classification probability from the submodules.
There were 686 out of 1433 (47.9%) and 50 out of 100 (50%) amyloid PET-positive participants in the training and internal validation datasets and the external validation datasets, respectively. With 50 times iterations of model training and validation, the model achieved an AUC of 0.811 (95% confidence interval (CI) of 0.803–0.819) and 0.798 (95% CI, 0.789–0.807) on the internal and external validation datasets, respectively. The area under the curve (AUC) was 0.860 when tested with the model with the highest value (0.864) on the external validation dataset. Moreover, it had 75.0% accuracy, 76.0% sensitivity, 74.0% specificity, and 75.0% F1-score. We found an overlap between the regions within the default mode network, thus generating high classification values.
The proposed model based on the 2-[18F]FDG PET imaging data and a DL framework might successfully classify amyloid PET positivity in clinical practice, without performing amyloid PET, which have limited accessibility.