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.
BackgroundRepetitive transcranial magnetic stimulation (rTMS) has shown promise in the alleviation of acute and chronic pain by altering the activity of cortical areas involved in pain sensation. However, current single-coil rTMS technology only allows for effects in surface cortical structures. The ability to affect activity in certain deep brain structures may however, allow for a better efficacy, safety, and tolerability. This study used PET imaging to determine whether a novel multi-coil rTMS would allow for preferential targeting of the dorsal anterior cingulate cortex (dACC), an area always activated with pain, and to provide preliminary evidence as to whether this targeted approach would allow for efficacious, safe, and tolerable analgesia both in a volunteer/acute pain model as well as in fibromyalgia chronic pain patients.MethodsPart 1: Different coil configurations were tested in a placebo-controlled crossover design in volunteers (N = 16). Tonic pain was induced using a capsaicin/thermal pain model and functional brain imaging was performed by means of H215O positron emission tomography – computed tomography (PET/CT) scans. Differences in NRS pain ratings between TMS and sham treatment (NRSTMS-NRSplacebo) which were recorded each minute during the 10 minute PET scans. Part 2: 16 fibromyalgia patients were subjected to 20 multi-coil rTMS treatments over 4 weeks and effects on standard pain scales (Brief Pain Inventory, item 5, i.e. average pain NRS over the last 24 hours) were recorded.ResultsA single 30 minute session using one of 3 tested rTMS coil configurations operated at 1 Hz consistently produced robust reduction (mean 70% on NRS scale) in evoked pain in volunteers. In fibromyalgia patients, the 20 rTMS sessions also produced a significant pain inhibition (43% reduction in NRS pain over last 24 hours), but only when operated at 10 Hz. This degree of pain control was maintained for at least 4 weeks after the final session.ConclusionMulti-coil rTMS may be a safe and effective treatment option for acute as well as for chronic pain, such as that accompanying fibromyalgia. Further studies are necessary to optimize configurations and settings as well as to elucidate the mechanisms that lead to the long-lasting pain control produced by these treatments.
18 F-DCFPyL (2-(3-{1-carboxy-5-[(6-18 F-fluoropyridine-3-carbonyl)amino]-pentyl}-ureido)-pentanedioic acid) is a promising PET radiopharmaceutical targeting prostate-specific membrane antigen (PSMA). We present our experience with this single-academic-center prospective study evaluating the positivity rate of 18 F-DCFPyL PET/CT in patients with biochemical recurrence (BCR) of prostate cancer (PC). Methods: We prospectively enrolled 72 men (52-91 y old; mean ± SD, 71.5 ± 7.2) with BCR after primary definitive treatment with prostatectomy (n 5 42) or radiotherapy (n 5 30). The presence of lesions compatible with PC was evaluated by 2 independent readers. Fifty-nine patients had scans concurrent with at least one other conventional scan: bone scanning (24), CT (21), MR (20), 18 F-fluciclovine PET/CT (18), or 18 F-NaF PET (14). Findings from 18 F-DCFPyL PET/CT were compared with those from other modalities. Impact on patient management based on 18 F-DCFPyL PET/CT was recorded from clinical chart review. Results: 18 F-DCFPyL PET/CT had an overall positivity rate of 85%, which increased with higher prostate-specific antigen (PSA) levels (ng/mL): 50% (PSA , 0.5), 69% (0.5 # PSA , 1), 100% (1 # PSA , 2), 91% (2 # PSA , 5), and 96% (PSA $ 5). 18 F-DCFPyL PET detected more lesions than conventional imaging. For anatomic imaging, 20 of 41 (49%) CT or MRI scans had findings congruent with 18 F-DCFPyL, whereas 18 F-DCFPyL PET was positive in 17 of 41 (41%) cases with negative CT or MRI findings. For bone imaging, 26 of 38 (68%) bone or 18 F-NaF PET scans were congruent with 18 F-DCFPyL PET, whereas 18 F-DCFPyL PET localized bone lesions in 8 of 38 (21%) patients with negative results on bone or 18 F-NaF PET scans. In 8 of 18 (44%) patients, 18 F-fluciclovine PET had located the same lesions as did 18 F-DCFPyL PET, whereas 5 of 18 (28%) patients with negative 18 F-fluciclovine findings had positive 18 F-DCFPyL PET findings and 1 of 18 (6%) patients with negative 18 F-DCFPyL findings had uptake in the prostate bed on 18 F-fluciclovine PET. In the remaining 4 of 18 (22%) patients, 18 F-DCFPyL and 18 F-fluciclovine scans showed different lesions. Lastly, 43 of 72 (60%) patients had treatment changes after 18 F-DCFPyL PET and, most noticeably, 17 of these patients (24% total) had lesion localization only on 18 F-DCFPyL PET, despite negative results on conventional imaging. Conclusion: 18 F-DCFPyL PET/CT is a promising diagnostic tool in the work-up of biochemically recurrent PC, given the high positivity rate as compared with Food and Drug Administration-approved currently available imaging modalities and its impact on clinical management in 60% of patients.
A B S T R A C T PurposeChildren with relapsed neuroblastoma have poor survival. It is crucial to have a reliable method for evaluating functional response to new therapies. In this study, we compared two functional imaging modalities for neuroblastoma: metaiodobenzylguanidine (MIBG) scan for uptake by the norepinephrine transporter and [18 F]fluorodeoxyglucose positron emission tomography (FDG-PET) uptake for glucose metabolic activity. Patients and MethodsPatients enrolled onto a phase I study of sequential infusion of iodine-131 ( 131 I) MIBG (NANT-2000-01) were eligible for inclusion if they had concomitant FDG-PET and MIBG scans.131 I-MIBG therapy was administered on days 0 and 14. For each patient, we compared all lesions identified on concomitant FDG-PET and MIBG scans and gave scans a semiquantitative score. ResultsThe overall concordance of positive lesions on concomitant MIBG and FDG-PET scans was 39.6% when examining the 139 unique anatomic lesions. MIBG imaging was significantly more sensitive than FDG-PET overall and for the detection of bone lesions (P Ͻ .001). There was a trend for increased sensitivity of FDG-PET for detection of soft tissue lesions. Both modalities showed similar improvement in number of lesions identified from day 0 to day 56 scan and in semiquantitative scores that correlated with overall response. FDG-PET scans became completely negative more often than MIBG scans after treatment. ConclusionMIBG scan is significantly more sensitive for individual lesion detection in relapsed neuroblastoma than FDG-PET, though FDG-PET can sometimes play a complementary role, particularly in soft tissue lesions. Complete response by FDG-PET metabolic evaluation did not always correlate with complete response by MIBG uptake.
A simultaneous PET/MRI using both (68)Ga-DOTA-TOC and gadoxetate disodium was successful in whole body staging of patients with neuroendocrine tumor. HBP imaging had an increased detection rate for hepatic metastases.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.