No abstract

To develop and validate a deep learning algorithm that predicts the final diagnosis of Alzheimer disease (AD), mild cognitive impairment, or neither at fluorine 18 (18 F) fluorodeoxyglucose (FDG) PET of the brain and compare its performance to that of radiologic readers. Materials and Methods: Prospective 18 F-FDG PET brain images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) (2109 imaging studies from 2005 to 2017, 1002 patients) and retrospective independent test set (40 imaging studies from 2006 to 2016, 40 patients) were collected. Final clinical diagnosis at follow-up was recorded. Convolutional neural network of InceptionV3 architecture was trained on 90% of ADNI data set and tested on the remaining 10%, as well as the independent test set, with performance compared to radiologic readers. Model was analyzed with sensitivity, specificity, receiver operating characteristic (ROC), saliency map, and t-distributed stochastic neighbor embedding. Results: The algorithm achieved area under the ROC curve of 0.98 (95% confidence interval: 0.94, 1.00) when evaluated on predicting the final clinical diagnosis of AD in the independent test set (82% specificity at 100% sensitivity), an average of 75.8 months prior to the final diagnosis, which in ROC space outperformed reader performance (57% [four of seven] sensitivity, 91% [30 of 33] specificity; P , .05). Saliency map demonstrated attention to known areas of interest but with focus on the entire brain. Conclusion: By using fluorine 18 fluorodeoxyglucose PET of the brain, a deep learning algorithm developed for early prediction of Alzheimer disease achieved 82% specificity at 100% sensitivity, an average of 75.8 months prior to the final diagnosis.

Patients with metastatic or unresectable (advanced) pheochromocytoma and paraganglioma (PPGL) have poor prognoses and few treatment options. This multicenter, phase 2 trial evaluated the efficacy and safety of high-specific-activity 131 I-meta-iodobenzylguanidine (HSA 131 I-MIBG) in patients with advanced PPGL. Methods: In this open-label, single-arm study, 81 PPGL patients were screened for enrollment, and 74 received a treatment-planning dose of HSA 131 I-MIBG. Of these patients, 68 received at least 1 therapeutic dose (∼18.5 GBq) of HSA 131 I-MIBG intravenously. The primary endpoint was the proportion of patients with at least a 50% reduction in baseline antihypertensive medication use lasting at least 6 mo. Secondary endpoints included objective tumor response as assessed by Response Evaluation Criteria in Solid Tumors version 1.0, biochemical tumor marker response, overall survival, and safety. Results: Of the 68 patients who received at least 1 therapeutic dose of HSA 131 I-MIBG, 17 (25%; 95% confidence interval, 16%–37%) had a durable reduction in baseline antihypertensive medication use. Among 64 patients with evaluable disease, 59 (92%) had a partial response or stable disease as the best objective response within 12 mo. Decreases in elevated (≥1.5 times the upper limit of normal at baseline) serum chromogranin levels were observed, with confirmed complete and partial responses 12 mo after treatment in 19 of 28 patients (68%). The median overall survival was 36.7 mo (95% confidence interval, 29.9–49.1 mo). The most common treatment-emergent adverse events were nausea, myelosuppression, and fatigue. No patients had drug-related acute hypertensive events during or after the administration of HSA 131 I-MIBG. Conclusion: HSA 131 I-MIBG offers multiple benefits, including sustained blood pressure control and tumor response in PPGL patients.

Aromatic L-amino acid decarboxylase (AADC) deficiency is a rare genetic disorder characterized by deficient synthesis of dopamine and serotonin. It presents in early infancy, and causes severe developmental disability and lifelong motor, behavioral, and autonomic symptoms including oculogyric crises (OGC), sleep disorder, and mood disturbance. We investigated the safety and efficacy of delivery of a viral vector expressing AADC (AAV2-hAADC) to the midbrain in children with AADC deficiency (ClinicalTrials.gov Identifier NCT02852213). Seven (7) children, aged 4–9 years underwent convection-enhanced delivery (CED) of AAV2-hAADC to the bilateral substantia nigra (SN) and ventral tegmental area (VTA) (total infusion volume: 80 µL per hemisphere) in 2 dose cohorts: 1.3 × 1011 vg (n = 3), and 4.2 × 1011 vg (n = 4). Primary aims were to demonstrate the safety of the procedure and document biomarker evidence of restoration of brain AADC activity. Secondary aims were to assess clinical improvement in symptoms and motor function. Direct bilateral infusion of AAV2-hAADC was safe, well-tolerated and achieved target coverage of 98% and 70% of the SN and VTA, respectively. Dopamine metabolism was increased in all subjects and FDOPA uptake was enhanced within the midbrain and the striatum. OGC resolved completely in 6 of 7 subjects by Month 3 post-surgery. Twelve (12) months after surgery, 6/7 subjects gained normal head control and 4/7 could sit independently. At 18 months, 2 subjects could walk with 2-hand support. Both the primary and secondary endpoints of the study were met. Midbrain gene delivery in children with AADC deficiency is feasible and safe, and leads to clinical improvements in symptoms and motor function.