The purpose of this project is to develop and validate a Deep Learning (DL) FDG PET imaging algorithm able to identify patients with any neurodegenerative diseases (Alzheimer's Disease (AD), Frontotemporal Degeneration (FTD) or Dementia with Lewy Bodies (DLB)) among patients with Mild Cognitive Impairment (MCI). A 3D Convolutional neural network was trained using images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The ADNI dataset used for the model training and testing consisted of 822 subjects (472 AD and 350 MCI). The validation was performed on an independent dataset from La Fe University and Polytechnic Hospital. This dataset contained 90 subjects with MCI, 71 of them developed a neurodegenerative disease (64 AD, 4 FTD and 3 DLB) while 19 did not associate any neurodegenerative disease. The model had 79% accuracy, 88% sensitivity and 71% specificity in the identification of patients with neurodegenerative diseases tested on the 10% ADNI dataset, achieving an area under the receiver operating characteristic curve (AUC) of 0.90. On the external validation, the model preserved 80% balanced accuracy, 75% sensitivity, 84% specificity and 0.86 AUC. This binary classifier model based on FDG PET images allows the early prediction of neurodegenerative diseases in MCI patients in standard clinical settings with an overall 80% classification balanced accuracy.

Purpose The purpose of this project is to develop and externally validate a Deep Learning (DL) FDG PET imaging algorithm able to identify patients with Alzheimer's Disease (AD), Frontotemporal Degeneration (FTD) and Dementia with Lewy Bodies (DLB) among a group of patients with Mild Cognitive Impairment (MCI). Methods A 3D Convolutional neural network, trained using images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, was implemented. The ADNI dataset used for training and testing the model consisted of 822 subjects (472 AD and 350 MCI). The external validation was performed on an independent dataset from our hospital. The hospital real world dataset contains 90 subjects with MCI: 71 patients that developed a neurodegenerative disease (64 AD, 4 FTD and 3 DLB) and 19 subjects without associated neurodegenerative disease. Results The ADNI model had 79% accuracy, 88% sensitivity and 71% specificity in the identification of patients with neurodegenerative diseases tested on the 10% ADNI dataset, achieving an area under the receiver operating characteristic curve (AUC) of 0.897. When used for the external validation, the model preserved 77% accuracy, 75% sensitivity, 84% specificity and 0.860 area under the ROC curve. Conclusion This model based on FDG PET images can help the early non-invasive prediction of neurodegenerative diseases in MCI patients in standard clinical settings with an overall 77% classification accuracy.