Fast and accurate amyloid brain PET quantification without MRI using deep neural networks.

This paper proposes a novel method for the automatic quantification of amyloid positron emission tomography (PET) using the deep learning (DL)-based spatial normalization (SN) of PET images, which does not require magnetic resonance imaging (MRI) or computed tomography images of the same patient. The accuracy of the method was evaluated for three different amyloid PET radiotracers compared to MRI-parcellation-based PET quantification using FreeSurfer. Methods: A deep neural network model used for the SN of amyloid PET images was trained using 994 multicenter amyloid PET images (367 18 F-Flutemetamol and 627 18 F-Florbetaben) and the corresponding 3D MRIs of patients with Alzheimer's disease or mild cognitive impairment, and cognitively normal subjects. For comparison, PET SN was also conducted using the SPM12 program (SPM-based SN). The accuracy of DL- and SPM-based SN and standardized uptake value ratio (SUVR) quantification relative to the FreeSurfer-based estimation in individual brain spaces was evaluated using 148 other amyloid PET images (64 18 F-Flutemetamol and 84 18 F-Florbetaben). Additional external validation was performed using an unseen independent external dataset (30 18 F-Flutemetamol, 67 18 F-Florbetaben, and 39 18 F-Florbetapir). Results: Quantification results using the proposed DL-based method showed stronger correlations with the FreeSurfer estimates than SPM-based SN using MRI did. For example, the slope, y-intercept and R 2 values between SPM and FreeSurfer for the global cortex were 0.869, 0.113, and 0.946, respectively. In contrast, the slope, y-intercept, and R 2 values between the proposed DL-based method and FreeSurfer were 1.019, -0.016, and 0.986, respectively. The external validation study also demonstrated better performance of the proposed method without MR images than that of SPM with MRI. In most brain regions, the proposed method outperformed the SPM SN in terms of linear regression parameters and intraclass correlation coefficients. Conclusion: We evaluated a novel DL-based SN method, which allows quantitative analysis of amyloid brain PET images without structural MRI. The quantification results using the proposed method showed a strong correlation with MRI-parcellation-based quantification using FreeSurfer for all clinical amyloid radiotracers. Therefore, the proposed method will be useful for investigating Alzheimer's disease and related brain disorders using amyloid PET scans.