This is an international multicentre study aimed at evaluating the combined value of dopaminergic neuroimaging and clinical features in predicting future phenoconversion of idiopathic REM sleep behaviour (iRBD) subjects to overt synucleinopathy. Nine centres sent ¹²³I-FP-CIT-SPECT data of 344 iRBD patients and 256 controls for centralized analysis. ¹²³I-FP-CIT-SPECT images were semiquantified using DaTQUANT^TM, obtaining putamen and caudate specific to non-displaceable binding ratios (SBRs). The following clinical variables were also analysed: (i) Movement Disorder Society-sponsored revision of the Unified Parkinson’s Disease Rating Scale, motor section score; (ii) Mini-Mental State Examination score; (iii) constipation; and (iv) hyposmia. Kaplan-Meier survival analysis was performed to estimate conversion risk. Hazard ratios for each variable were calculated with Cox regression. A generalized logistic regression model was applied to identify the best combination of risk factors. Bayesian classifier was used to identify the baseline features predicting phenoconversion to parkinsonism or dementia. After quality check of the data, 263 iRBD patients (67.6 ± 7.3 years, 229 males) and 243 control subjects (67.2 ± 10.1 years, 110 males) were analysed. Fifty-two (20%) patients developed a synucleinopathy after average follow-up of 2 years. The best combination of risk factors was putamen dopaminergic dysfunction of the most affected hemisphere on imaging, defined as the lower value between either putamina (P < 0.000001), constipation, (P < 0.000001) and age over 70 years (P = 0.0002). Combined features obtained from the generalized logistic regression achieved a hazard ratio of 5.71 (95% confidence interval 2.85–11.43). Bayesian classifier suggested that patients with higher Mini-Mental State Examination score and lower caudate SBR asymmetry were more likely to develop parkinsonism, while patients with the opposite pattern were more likely to develop dementia. This study shows that iRBD patients older than 70 with constipation and reduced nigro-putaminal dopaminergic function are at high risk of short-term phenoconversion to an overt synucleinopathy, providing an effective stratification approach for future neuroprotective trials. Moreover, we provide cut-off values for the significant predictors of phenoconversion to be used in single subjects.

Purpose: The purpose of this study is to develop and validate a 3D deep learning model that predicts the final clinical diagnosis of Alzheimer’s disease (AD), dementia with Lewy bodies (DLB), mild cognitive impairment due to Alzheimer’s disease (MCI-AD), and cognitively normal (CN) using fluorine 18 fluorodeoxyglucose PET (18F-FDG PET) and compare model’s performance to that of multiple expert nuclear medicine physicians’ readers. Materials and methods: Retrospective 18F-FDG PET scans for AD, MCI-AD, and CN were collected from Alzheimer’s disease neuroimaging initiative (556 patients from 2005 to 2020), and CN and DLB cases were from European DLB Consortium (201 patients from 2005 to 2018). The introduced 3D convolutional neural network was trained using 90% of the data and externally tested using 10% as well as comparison to human readers on the same independent test set. The model’s performance was analyzed with sensitivity, specificity, precision, F1 score, receiver operating characteristic (ROC). The regional metabolic changes driving classification were visualized using uniform manifold approximation and projection (UMAP) and network attention. Results: The proposed model achieved area under the ROC curve of 96.2% (95% confidence interval: 90.6–100) on predicting the final diagnosis of DLB in the independent test set, 96.4% (92.7–100) in AD, 71.4% (51.6–91.2) in MCI-AD, and 94.7% (90–99.5) in CN, which in ROC space outperformed human readers performance. The network attention depicted the posterior cingulate cortex is important for each neurodegenerative disease, and the UMAP visualization of the extracted features by the proposed model demonstrates the reality of development of the given disorders. Conclusion: Using only 18F-FDG PET of the brain, a 3D deep learning model could predict the final diagnosis of the most common neurodegenerative disorders which achieved a competitive performance compared to the human readers as well as their consensus.

Several studies highlighted the role of vascular ¹⁸F-NaF uptake as a marker of ongoing calcium deposition. However, ¹⁸F-NaF accumulation often shows inconsistent co-localization with arterial plaque. Actually, calcification activity and thus ¹⁸F-NaF uptake could prevail in the earlier plaque stages. To test this hypothesis, we evaluated¹⁸F-NaF uptake in three plaque types using plaque density as a marker of calcification progression. We also tested whether attenuation weighted image reconstruction affected ¹⁸F-NaF uptake values in the different plaque stages considered. Methods: 64 oncologic patients (14 males, mean age 65.3±8.2 range 26-81) underwent ¹⁸F-NaF PET/CT. A volume of interest (VOI), was drawn on each plaque within the infra-renal aorta, to assess mean SUV and attenuation value (HU). Plaques were then divided in light (LP, HU 510). SUV was normalized for blood ¹⁸F-NaF activity, to obtain plaque target-to background ratio (TBR). In this process, several focal, non-calcified ¹⁸F-NaF uptake areas were identified (hot spots, HS). TBR was computed in HS, after iso-contour thresholding. TBR was also calculated in a non-calcified control region (CR). In 35 patients, TBR was furthermore calculated on non-attenuation-corrected (NAC) images. Results: Among plaques, average TBR was highest in LP (2.21±0.88), while it was significantly lower in MP (1.59±0.53, p<0.001) and further decreased in HP (1.14±0.37, p<0.0001 with respect to both LP and MP). CR TBR was not significantly different to the one of HP and MP (P = ns), while it was significantly lower than LP and MP (p<0.01). HS had the highest absolute TBR (3.89±1.87, p<0.0001 vs LP). Considering TBR values originated from NAC didn’t provide significant difference from AC. Conclusion: The present study is in keeping with the concept that ¹⁸F-NaF is a feasible option in imaging molecular calcium deposition in the early stages of plaque formation, when active uptake mechanism are the main determinants of calcium presence while its retention progressively decreases with increasing calcium deposition in the arterial wall. From a technical point of view, our data suggest that NAC reconstruction doesn’t significantly affect output when evaluating plaques of any thickness. Methods: 64 oncologic patients (14 males, mean age 65.3±8.2 range 26-81) underwent ¹⁸F-NaF PET/CT. A volume of interest (VOI), was drawn on each plaque within the infra-renal aorta, to assess mean SUV and attenuation value (HU). Plaques were then divided in light (LP, HU 510). SUV was normalized for blood ¹⁸F-NaF activity, to obtain plaque target-to background ratio (TBR). In this process, several focal, non-calcified ¹⁸F-NaF uptake areas were identified (hot spots, HS). TBR was computed in HS, after iso-contour thresholding. TBR was also calculated in a non-calcified control region (CR). In 35 patients, TBR was furthermore calculated on non-attenuation-corrected (NAC) images. Results: Among plaques, average TBR was highest in LP (2.21±0.88), while it was significantly lower in MP (1.59±0.53, p<0.001) and further decreased in HP (1.14±0.37, p<0.0001 with respect to both LP and MP). CR TBR was not significantly different to the one of HP and MP (P = ns), while it was significantly lower than LP and MP (p<0.01). HS had the highest absolute TBR (3.89±1.87, p<0.0001 vs LP). Considering TBR values originated from NAC didn’t provide significant difference from AC. Conclusion: The present study is in keeping with the concept that ¹⁸F-NaF is a feasible option in imaging molecular calcium deposition in the early stages of plaque formation, when active uptake mechanism are the main determinants of calcium presence while its retention progressively decreases with increasing calcium deposition in the arterial wall. From a technical point of view, our data suggest that NAC reconstruction doesn’t significantly affect output when evaluating plaques of any thickness.

The present translational study aimed to verify whether serial ¹⁸F-FDG PET/CT predicts doxorubicin cardiotoxicity. Methods: Fifteen athymic mice were treated intravenously with saline (n = 5) or with 5 or 7.5 mg of doxorubicin per kilogram (n = 5 each) and underwent dynamic small-animal PET beforehand and afterward to estimate left ventricular (LV) metabolic rate of glucose (MRGlu). Thereafter, we retrospectively identified 69 patients who had been successfully treated with a regimen of doxorubicin, bleomycin, vinblastine, and dacarbazine for Hodgkin disease (HD) and had undergone 4 consecutive ¹⁸F-FDG PET/CT scans. Volumes of interest were drawn on LV myocardium to quantify mean SUV. All patients were subsequently interviewed by telephone (median follow-up, 30 mo); 36 of them agreed to undergo electrocardiography and transthoracic echocardiography. Results: In mice, LV MRGlu was 17.9 ± 4.4 nmol × min⁻¹ × g⁻¹ at baseline. Doxorubicin selectively and dose-dependently increased this value in the standard-dose (27.9 ± 9 nmol × min⁻¹ × g⁻¹, P < 0.05 vs. controls) and high-dose subgroups (37.2 ± 7.8 nmol × min⁻¹ × g⁻¹, P < 0.01 vs. controls, P < 0.05 vs. standard-dose). In HD patients, LV SUV showed a progressive increase during doxorubicin treatment that persisted at follow-up. New-onset cardiac abnormalities appeared in 11 of 36 patients (31%). In these subjects, pretherapy LV SUV was markedly lower with respect to the remaining patients (1.53 ± 0.9 vs. 3.34 ± 2.54, respectively, P < 0.01). Multivariate analysis confirmed the predictive value of baseline LV SUV for subsequent cardiac abnormalities. Conclusion: Doxorubicin dose-dependently increases LV MRGlu, particularly in the presence of low baseline ¹⁸F-FDG uptake. These results imply that low myocardial ¹⁸F-FDG uptake before the initiation of doxorubicin chemotherapy in HD patients may predict the development of chemotherapy-induced cardiotoxicity, suggesting that prospective clinical trials are warranted to test this hypothesis.