Utilizing the publicly available neuroimaging database enabled by Alzheimer’s disease Neuroimaging Initiative (ADNI; http://adni.loni.usc.edu/), we have compared the performance of automated classification algorithms that differentiate AD vs. normal subjects using Positron Emission Tomography (PET) with fluorodeoxyglucose (FDG). General linear model, scaled subprofile modeling and support vector machines were examined. Among the tested classification methods, support vector machine with Iterative Single Data Algorithm produced the best performance, i.e., sensitivity (0.84) × specificity (0.95), by 10-fold cross-validation. We have applied the same classification algorithm to four different datasets from ADNI, Health Science Centre (Winnipeg, Canada), Dong-A University Hospital (Busan, S. Korea) and Asan Medical Centre (Seoul, S. Korea). Our data analyses confirmed that the support vector machine with Iterative Single Data Algorithm showed the best performance in prediction of future development of AD from the prodromal stage (mild cognitive impairment), and that it was also sensitive to other types of dementia such as Parkinson’s Disease Dementia and Dementia with Lewy Bodies, and that perfusion imaging using single photon emission computed tomography may achieve a similar accuracy to that of FDG-PET.

A two-dimensional (2D) self-consistent axisymmetric fluid simulation of an inductively coupled discharge of electronegative oxygen plasma with a one-turn antenna placed on the top of the dielectric roof is presented. The model equations include continuity equations, the Poisson equation, and an electron energy balance equation. For a planar inductive discharge, the electric field component E _θ (r, z) is calculated, assuming axisymmetric geometry. Considering a deep penetration of the induced rf field, the power deposition profile is formulated and used as the electron heating term in the electron energy balance equation. The 2D distributions of charged particle densities, electric potential, electron temperature, and ionization rate are calculated and compared with experiments. The effect of neutral gas pressure on plasma characteristics is investigated. As a result, for a relatively low pressure (5 mTorr) case, the ionization rate and charged particle densities are uniform in the radial direction, and for a medium pressure (20 mTorr) case, the ionization rate and the negative ion density are sharply maximized in the axial and radial directions. The results of the simulation agree reasonably well with the results of the spatially averaged global model and experimental results.

Although amyloid beta (Aβ) imaging is widely used for diagnosing and monitoring Alzheimer’s disease in clinical fields, paralleling comparison between ¹⁸F-flutemetamol and ¹⁸F-florbetaben was rarely attempted in AD mouse model. We performed a comparison of Aβ PET images between ¹⁸F-flutemetamol and ¹⁸F-florbetaben in a recently developed APPswe mouse model, C57BL/6-Tg (NSE-hAPPsw) Korl. After an injection (0.23 mCi) of ¹⁸F-flutemetamol and ¹⁸F-florbetaben at a time interval of 2–3 days, we compared group difference of SUVR and kinetic parameters between the AD (n = 7) and control (n = 7) mice, as well as between ¹⁸F-flutemetamol and ¹⁸F-florbetaben image. In addition, bio-distribution and histopathology were conducted. With visual image and VOI-based SUVR analysis, the AD group presented more prominent uptake than did the control group in both the ¹⁸F-florbetaben and ¹⁸F-flutemetamol images. With kinetic analysis, the ¹⁸F-florbetaben images showed differences in K1 and k4 between the AD and control groups, although ¹⁸F-flutemetamol images did not show significant difference. ¹⁸F-florbetaben images showed more prominent cortical uptake and matched well to the thioflavin S staining images than did the ¹⁸F-flutemetamol image. In contrast, ¹⁸F-flutemetamol images presented higher K1, k4, K1/k2 values than those of ¹⁸F-florbetaben images. Also, ¹⁸F-flutemetamol images presented prominent uptake in the bowel and bladder, consistent with higher bio-distribution in kidney, lung, blood and heart. Compared with ¹⁸F-flutemetamol images, ¹⁸F-florbetaben images showed prominent visual uptake intensity, SUVR, and higher correlations with the pathology. In contrast, ¹⁸F-flutemetamol was more actively metabolized than was ¹⁸F-florbetaben (Son et al. in J Nucl Med 58(Suppl 1):S278, 2017 ].

Background: The quantification of heterogeneity for the striatum and whole brain with F-18 FP-CIT PET images will be useful for diagnosis. The index obtained from texture analysis on PET images is related to pathological change that the neuronal loss of the nigrostriatal tract is heterogeneous according to the disease state. The aim of this study is to evaluate various heterogeneity indices of F-18 FP-CIT PET images in the diagnosis of Parkinson's disease (PD) patients and to access the diagnostic accuracy of the indices using machine learning (ML). Methods: This retrospective study included F-18 FP-CIT PET images of 31 PD and 31 age-matched health controls (HC). The volume of interest was delineated according to iso-contour lines around standardized uptake value (SUV) 3.0 g/ml for each region of the striatum by PMod 3.603. One hundred eight heterogeneity indices were calculated using CGITA to find indices from which the PD and HC were classified using statistical significance. PD group was classified by constructing a 2-dimensional or 3-dimensional phase space quantifier using these heterogeneity indices. We used 71 heterogeneity indices to classify PD from HC using ML for dimensional reduction. Results: The heterogeneity indices for classifying PD from HC were size-zone variability, contrast, inverse difference-moment, and homogeneity in the order of low P value. Three-dimensional quantifiers composed of normalized-contrast, code-similarity, and contrast were more clearly classified than 2-dimensional ones. After 71-dimensional reduction using PCA, classification was possible by logistic regression with 91.3% accuracy. The 2 groups were classified with an accuracy of 85.5% using the support vector machine and 88.4% using the random forest. The classification accuracy using the eXtreme Gradient Boosting was 95.7%, and feature importance was highest in order of SUV bias-corrected kurtosis, size-zone-variability, intensity-variability, and high-intensity-zone-variability. Conclusion: It was confirmed that PD patients is more clearly classified than the conventional 2-dimensional quantifier by introducing a 3-dimensional phase space quantifier. We observed that ML can be used to classify the 2 groups in an easy and explanatory manner. For the discrimination of the disease, 24 heterogeneity indices were found to be statistically useful, and the major cut-off values of 3 heterogeneity indices were size-zone variability (1906.44), intensity variability (129.21), and high intensity zone emphasis (800.29).

Purpose The regions of significant correlation between cerebral hypoperfusion and neuropsychological assessment scores were evaluated using ^99mTc-HMPAO SPECT in patients with mild cognitive impairment (MCI) on the basis of its three subtypes, namely, single-domain amnestic MCI (aMCI-s), multiple-domain amnestic MCI (aMCI-m), and nonamnestic MCI (naMCI), following which comparisons were made among the three subtypes of MCI. Methods Regions of hypoperfusion were determined by comparing the three groups with the normal group. Neuropsychological assessment included tests to evaluate attention, language and related functions, visuospatial function, memory, frontal-executive function, and mini-mental state examination and depression scores. Regions of cerebral hypoperfusion were identified by comparing the three groups of MCI patients with the normal group (P<0.05, uncorrected). One-way analysis of variance was used to examine differences across groups, and post-hoc a-priori pairwise comparisons were used for between-group analyses. The regions of significant correlation, related to the neuropsychological assessment scores, were identified by simple regression of SPM8 within the masking image of the area of cerebral hypoperfusion (P<0.05, uncorrected). Results The regions of cerebral hypoperfusion were identified by comparing members of the normal group with patients with aMCI-s, aMCI-m, and naMCI. The patients with aMCI-m showed significant correlation with all neuropsychological assessment scores, but the patients with aMCI-s correlated with four neuropsychological assessment scores of attention. The patients with naMCI revealed no significantly correlated regions (P<0.05, uncorrected). The regions that correlated with neuropsychological assessment scores in patients with aMCI-s were very small compared with those in patients with aMCI-m. The correlated regions in patients with aMCI-m were restricted to the left cerebrum and cerebellum. Brain areas showed significant correlation between neuropsychological assessment scores and hypoperfusion, which was evaluated by simple regression with the threshold being P less than 0.05, uncorrected. Rey complex figure test 20 min delayed, Korean-color word stroop test word reading, and Korean mini-mental state examination scores correlated more strongly with cerebral hypoperfusion compared with other assessment scores. Conclusion The specific pattern of significant correlation of cerebral hypoperfusion with neuropsychological assessment scores was classified into three subtypes (aMCI-s, aMCI-m, and naMCI) according to the patients’ deficits in their cognitive domains.