Phosphorus-31 NMR spectroscopy using slice selection (DRESS) was used to investigate the absolute concentrations of metabolites in the human liver. Absolute concentrations provide more specific biochemical information compared to spectrum integral ratios. Nine patients with histopathologically proven diffuse liver disease and 12 healthy individuals were examined in a 1.5-T MR scanner (GE Signa LX Echospeed plus). The metabolite concentration quantification procedures included: (1) determination of optimal depth for the in vivo measurements, (2) mapping the detection coil characteristics, (3) calculation of selected slice and liver volume ratios using simple segmentation procedures and (4) spectral analysis in the time domain. The patients had significantly lower concentrations of phosphodiesters (PDE), 6.3+/-3.9 mM, and ATP-beta, 3.6+/-1.1 mM, (P<0.05) compared with the control group (10.0+/-4.2 mM and 4.2+/-0.3 mM, respectively). The concentrations of phosphomonoesters (PME) were higher in the patient group, although this was not significant. Constructing an anabolic charge (AC) based on absolute concentrations, [PME]/([PME] + [PDE]), the patients had a significantly larger AC than the control subjects, 0.29 vs. 0.16 (P<0.005). Absolute concentration measurements of phosphorus metabolites in the liver are feasible using a slice selective sequence, and the technique demonstrates significant differences between patients and healthy 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.
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.