Correction to: Staging and quantification of florbetaben PET images using machine learning: impact of predicted regional cortical tracer uptake and amyloid stage on clinical outcomes.

Incorrect acknowledgments.

Staging and quantification of florbetaben PET images using machine learning: impact of predicted regional cortical tracer uptake and amyloid stage on clinical outcomes.

PURPOSE: We developed a machine learning-based classifier for in vivo amyloid positron emission tomography (PET) staging, quantified cortical uptake of the PET tracer by using a machine learning method, and investigated the impact of these amyloid PET parameters on clinical and structural outcomes. METHODS: A total of 337 18F-florbetaben PET scans obtained at Samsung Medical Center were assessed. We defined a feature vector representing the change in PET tracer uptake from grey to white matter. Using support vector machine (SVM) regression and SVM classification, we quantified the cortical uptake as predicted regional cortical tracer uptake (pRCTU) and categorised the scans as positive and negative. Positive scans were further classified into two stages according to the striatal uptake. We compared outcome parameters among stages and further assessed the association between the pRCTU and outcome variables. Finally, we performed path analysis to determine mediation effects between PET variables. RESULTS: The classification accuracy was 97.3% for cortical amyloid positivity and 91.1% for striatal positivity. The left frontal and precuneus/posterior cingulate regions, as well as the anterior portion of the striatum, were important in determination of stages. The clinical scores and magnetic resonance imaging parameters showed negative associations with PET stage. However, except for the hippocampal volume, most outcomes were associated with the stage through the complete mediation effect of pRCTU. CONCLUSION: Using a machine learning algorithm, we achieved high accuracy for in vivo amyloid PET staging. The in vivo amyloid stage was associated with cognitive function and cerebral atrophy mostly through the mediation effect of cortical amyloid.

Correction to: Staging and quantification of florbetaben PET images using machine learning: impact of predicted regional cortical tracer uptake and amyloid stage on clinical outcomes.

The Table 2 in the original version of this article contained a mistake in the alignment. Correct Table 2 presentation is presented here.

Neural correlates of anxiety under interrogation in guilt or innocence contexts.

Interrogation elicits anxiety in individuals under scrutiny regardless of their innocence, and thus, anxious responses to interrogation should be differentiated from deceptive behavior in practical lie detection settings. Despite its importance, not many empirical studies have yet been done to separate the effects of interrogation from the acts of lying or guilt state. The present fMRI study attempted to identify neural substrates of anxious responses under interrogation in either innocent or guilt contexts by developing a modified "Doubt" game. Participants in the guilt condition showed higher brain activations in the right central-executive network and bilateral basal ganglia. Regardless of the person's innocence, we observed higher activation of the salience, theory of mind and sensory-motor networks-areas associated with anxiety-related responses in the interrogative condition, compared to the waived conditions. We further explored two different types of anxious responses under interrogation-true detection anxiety in the guilty (true positive) and false detection anxiety in the innocent (false positive). Differential neural responses across these two conditions were captured at the caudate, thalamus, ventral anterior cingulate and ventromedial prefrontal cortex. We conclude that anxiety is a common neural response to interrogation, regardless of an individual's innocence, and that there are detectable differences in neural responses for true positive and false positive anxious responses under interrogation. The results of our study highlight a need to isolate complex cognitive processes involved in the deceptive acts from the emotional and regulatory responses to interrogation in lie detection schemes.

Differences in neuroimaging features of early- versus late-onset nonfluent/agrammatic primary progressive aphasia.

This study investigated distinct neuroimaging features measured by cortical thickness and subcortical structural shape abnormality in early-onset (EO, onset age <65 years) and late-onset (LO, onset age ≥65 years) nonfluent/agrammatic variant of primary progressive aphasia (nfvPPA) patients. Cortical thickness and subcortical structural shape analyses were performed using a surface-based method from 38 patients with nfvPPA and 76 cognitively normal individuals. To minimize the effects of physiological aging, we used W-scores in comparisons between the groups. The EO-nfvPPA group exhibited more extensive cortical thickness reductions predominantly in the left perisylvian, lateral and medial prefrontal, temporal, posterior cingulate, and precuneus regions than the LO-nfvPPA group. The EO-nfvPPA group also exhibited significantly greater subcortical structural shape abnormality than the LO-nfvPPA group, mainly in the left striatum, hippocampus, and amygdala. Our findings suggested that there were differences in neuroimaging features between these groups by the age of symptom onset, which might be explained by underlying heterogeneous neuropathological differences or the age-related brain reserve hypothesis.

Machine learning based hierarchical classification of frontotemporal dementia and Alzheimer's disease.

BACKGROUND: In a clinical setting, an individual subject classification model rather than a group analysis would be more informative. Specifically, the subtlety of cortical atrophy in some frontotemporal dementia (FTD) patients and overlapping patterns of atrophy among three FTD clinical syndromes including behavioral variant FTD (bvFTD), non-fluent/agrammatic variant primary progressive aphasia (nfvPPA), and semantic variant PPA (svPPA) give rise to the need for classification models at the individual level. In this study, we aimed to classify each individual subject into one of the diagnostic categories in a hierarchical manner by employing a machine learning-based classification method. METHODS: We recruited 143 patients with FTD, 50 patients with Alzheimer's disease (AD) dementia, and 146 cognitively normal subjects. All subjects underwent a three-dimensional volumetric brain magnetic resonance imaging (MRI) scan, and cortical thickness was measured using FreeSurfer. We applied the Laplace Beltrami operator to reduce noise in the cortical thickness data and to reduce the dimension of the feature vector. Classifiers were constructed by applying both principal component analysis and linear discriminant analysis to the cortical thickness data. For the hierarchical classification, we trained four classifiers using different pairs of groups: Step 1 - CN vs. FTD + AD, Step 2 - FTD vs. AD, Step 3 - bvFTD vs. PPA, Step 4 - svPPA vs. nfvPPA. To evaluate the classification performance for each step, we used a10-fold cross-validation approach, performed 1000 times for reliability. RESULTS: The classification accuracy of the entire hierarchical classification tree was 75.8%, which was higher than that of the non-hierarchical classifier (73.0%). The classification accuracies of steps 1-4 were 86.1%, 90.8%, 86.9%, and 92.1%, respectively. Changes in the right frontotemporal area were critical for discriminating behavioral variant FTD from PPA. The left frontal lobe discriminated nfvPPA from svPPA, while the bilateral anterior temporal regions were critical for identifying svPPA. CONCLUSIONS: In the present study, our automated classifier successfully classified FTD clinical subtypes with good to excellent accuracy. Our classifier may help clinicians diagnose FTD subtypes with subtle cortical atrophy and facilitate appropriate specific interventions.