The role of the deep convolutional neural network as an aid to interpreting brain [18F]DOPA PET/CT in the diagnosis of Parkinson's disease.

OBJECTIVES: To test the performance of a 3D convolutional neural network (CNN) in analysing brain [18F]DOPA PET/CT in order to identify patients with nigro-striatal neurodegeneration. We evaluated the robustness of the 3D CNN by testing it against a manual regional analysis of the striata by using a striatal-to-occipital ratio (SOR). METHODS: We analyzed patients who had undergone [18F]DOPA PET/CT from 2016 to 2018. Two examiners interpreted PET/CT images as positive or negative. Only patients with at least 2 years of follow-up and an ascertained neurological diagnosis were included. A 3D CNN was developed to evaluate [18F]DOPA PET/CT and refine the diagnosis of movement disorder. This system required training and testing, which were carried out on 2/3 and 1/3 of patients, respectively. A regional analysis was also conducted by drawing region of interest on T1-weighted 3D MRI scans, on which the [18F]DOPA PET images were first co-registered. RESULTS: Ninety-eight patients were enrolled: 43 presented nigro-striatal degeneration and 55 negative cases used as controls. After training on 69 patients, the diagnostic performance of the 3D CNN was then calculated in 29 patients. Sensitivity, specificity, negative predictive value, positive predictive value and accuracy were 100%, 89%, 100%, 85% and 93%, respectively. When we compared the 3D CNN results with the SOR analysis, we found that the two patients falsely classified as positive by the 3D CNN procedure showed SOR values ≤ 5th percentile of the negative cases' distribution. CONCLUSIONS: 3D CNNs are able to interpret [18F]DOPA PET/CT properly, revealing patients affected by Parkinson's disease. KEY POINTS: • [18F]DOPA PET/CT is a sensitive diagnostic tool to identify patients with nigro-striatal neurodegeneration. • A semiquantitative evaluation of the images allows a more confident interpretation of the PET findings. • 3D convolutional neural network allows an accurate interpretation of 18F-DOPA PET/CT images, revealing patients affected by Parkinson's disease.

A Multimodal Imaging Approach Demonstrates Reduced Midbrain Functional Network Connectivity Is Associated With Freezing of Gait in Parkinson's Disease.

Background: The pathophysiological mechanisms underlying freezing of gait (FOG) are poorly defined. MRI studies in FOG showed a distinct pattern of cortical atrophy and decreased functional connectivity (FC) within motor and cognitive networks. Furthermore, reduced rs-FC within midbrain, frontal, and temporal areas has been also described. This study investigated the patterns of whole-brain FC alterations within midbrain inter-connected regions in PD-FOG patients, and whether these patterns are linked to midbrain structural damage using a multi-modal imaging approach, combing structural and functional imaging techniques. Methods: Thirty three PD patients (16 PD-FOG, 17 PD noFOG), and 21 sex- and age-matched healthy controls (HCs) were prospectively enrolled. All subjects underwent MRI scan at 1.5T, whereas only PD patients underwent clinical and cognitive assessment. Grey matter (GM) integrity was measured using voxel-based morphometry (VBM). VBM findings served as basis to localize midbrain damage, and were further used as a seed region for investigating whole-brain FC alterations using rs-fMRI. Results: In rs-fMRI, patients with PD and FOG demonstrated significant decrease of midbrain-cortical FC levels in the R PCG, right postcentral, and supramarginal gyri compared to controls and the middle cingulate compared to noFOG group. Based on the regression analysis, MOCA, UPDRS-III total score, and FOG severity scores were associated with FC levels in several frontal, parietal and temporal regions. Discussion: The present results suggest that midbrain structural damage as well as decreased FC within the brainstem functional network might contribute to FOG occurrence in PD patients.