Background: Patients with Parkinson disease (PD) often experience visual hallucinations (VH) with retained insight (nonpsychotic) but the precise mechanism remains unclear. Objective: To clarify which neural substrates participate in nonpsychotic VH in PD, the authors evaluated regional cerebral blood flow (rCBF) changes in patients with PD and VH. Methods: The authors compared 24 patients with PD who had nonpsychotic VH (hallucinators) and 41 patients with PD who had never experienced VH (non-hallucinators) using SPECT images with N-isopropyl-p-[¹²³I]iodoamphetamine. There were no significant differences in age, sex, duration of disease, doses of PD medications, Hoehn and Yahr scale, or Mini-Mental State Examination (MMSE) scores between the two groups. The rCBF data were analyzed using statistical parametric mapping (SPM). Results: The rCBF in the right fusiform gyrus was lower in the hallucinators than in the non-hallucinators (corrected p < 0.05 at cluster levels). The hallucinators revealed higher rCBF in the right superior and middle temporal gyri than the non-hallucinators (uncorrected p < 0.001). These significant differences were demonstrated after MMSE scores and duration of disease, which are the relevant factors associated with VH, were covariated out. Conclusions: Nonpsychotic visual hallucinations in Parkinson disease (PD) may be associated with hypoperfusion in the right fusiform gyrus and hyperperfusion in the right superior and middle temporal gyri. These temporal regions are important for visual object recognition and these regional cerebral blood flow changes are associated with inappropriate visual processing and are responsible for nonpsychotic visual hallucinations in PD.

Background and Purpose—: For patients with large vessel occlusion, neuroimaging biomarkers that evaluate the changes in brain tissue are important for determining the indications for mechanical thrombectomy. In this study, we applied deep learning to derive imaging features from pretreatment diffusion-weighted image data and evaluated the ability of these features in predicting clinical outcomes for patients with large vessel occlusion. Methods—: This multicenter retrospective study included patients with anterior circulation large vessel occlusion treated with mechanical thrombectomy between 2013 and 2018. We designed a 2-output deep learning model based on convolutional neural networks (the convolutional neural network model). This model employed encoder-decoder architecture for the ischemic lesion segmentation, which automatically extracted high-level feature maps in its middle layers, and used its information to predict the clinical outcome. Its performance was internally validated with 5-fold cross-validation, externally validated, and the results compared with those from the standard neuroimaging biomarkers Alberta Stroke Program Early CT Score and ischemic core volume. The prediction target was a good clinical outcome, defined as a modified Rankin Scale score at 90-day follow-up of 0 to 2. Results—: The derivation cohort included 250 patients, and the validation cohort included 74 patients. The convolutional neural network model showed the highest area under the receiver operating characteristic curve: 0.81±0.06 compared with 0.63±0.05 and 0.64±0.05 for the Alberta Stroke Program Early CT Score and ischemic core volume models, respectively. In the external validation, the area under the curve for the convolutional neural network model was significantly superior to those for the other 2 models. Conclusions—: Compared with the standard neuroimaging biomarkers, our deep learning model derived a greater amount of prognostic information from pretreatment neuroimaging data. Although a confirmatory prospective evaluation is needed, the high-level imaging features derived by deep learning may offer an effective prognostic imaging biomarker.

The choice of biomarkers for early detection of Alzheimer's disease (AD) is important for improving the accuracy of imaging-based prediction of conversion from mild cognitive impairment (MCI) to AD. The primary goal of this study was to assess the effects of imaging modalities and brain atlases on prediction. We also investigated the influence of support vector machine recursive feature elimination (SVM-RFE) on predictive performance. Eighty individuals with amnestic MCI [40 developed AD within 3 years] underwent structural magnetic resonance imaging (MRI) and (18)F-fluorodeoxyglucose positron emission tomography (FDG-PET) scans at baseline. Using Automated Anatomical Labeling (AAL) and LONI Probabilistic Brain Atlas (LPBA40), we extracted features representing gray matter density and relative cerebral metabolic rate for glucose in each region of interest from the baseline MRI and FDG-PET data, respectively. We used linear SVM ensemble with bagging and computed the area under the receiver operating characteristic curve (AUC) as a measure of classification performance. We performed multiple SVM-RFE to compute feature ranking. We performed analysis of variance on the mean AUCs for eight feature sets. The interactions between atlas and modality choices were significant. The main effect of SVM-RFE was significant, but the interactions with the other factors were not significant. Multimodal features were found to be better than unimodal features to predict AD. FDG-PET was found to be better than MRI. Imaging modalities and brain atlases interact with each other and affect prediction. SVM-RFE can improve the predictive accuracy when using atlas-based features.

Gliomas are the most common intra-axial primary brain tumour; therefore, predicting glioma grade would influence therapeutic strategies. Although several methods based on single or multiple parameters from diagnostic images exist, a definitive method for pre-operatively determining glioma grade remains unknown. We aimed to develop an unsupervised method using multiple parameters from pre-operative diffusion tensor images for obtaining a clustered image that could enable visual grading of gliomas. Fourteen patients with low-grade gliomas and 19 with high-grade gliomas underwent diffusion tensor imaging and three-dimensional T1-weighted magnetic resonance imaging before tumour resection. Seven features including diffusion-weighted imaging, fractional anisotropy, first eigenvalue, second eigenvalue, third eigenvalue, mean diffusivity and raw T2 signal with no diffusion weighting, were extracted as multiple parameters from diffusion tensor imaging. We developed a two-level clustering approach for a self-organizing map followed by the K-means algorithm to enable unsupervised clustering of a large number of input vectors with the seven features for the whole brain. The vectors were grouped by the self-organizing map as protoclusters, which were classified into the smaller number of clusters by K-means to make a voxel-based diffusion tensor-based clustered image. Furthermore, we also determined if the diffusion tensor-based clustered image was really helpful for predicting pre-operative glioma grade in a supervised manner. The ratio of each class in the diffusion tensor-based clustered images was calculated from the regions of interest manually traced on the diffusion tensor imaging space, and the common logarithmic ratio scales were calculated. We then applied support vector machine as a classifier for distinguishing between low- and high-grade gliomas. Consequently, the sensitivity, specificity, accuracy and area under the curve of receiver operating characteristic curves from the 16-class diffusion tensor-based clustered images that showed the best performance for differentiating high- and low-grade gliomas were 0.848, 0.745, 0.804 and 0.912, respectively. Furthermore, the log-ratio value of each class of the 16-class diffusion tensor-based clustered images was compared between low- and high-grade gliomas, and the log-ratio values of classes 14, 15 and 16 in the high-grade gliomas were significantly higher than those in the low-grade gliomas (p < 0.005, p < 0.001 and p < 0.001, respectively). These classes comprised different patterns of the seven diffusion tensor imaging-based parameters. The results suggest that the multiple diffusion tensor imaging-based parameters from the voxel-based diffusion tensor-based clustered images can help differentiate between low- and high-grade gliomas.

We hypothesized that the integrity of white matter might be related to the severity of freezing of gait in age-related white matter changes. Twenty subjects exhibiting excessive hyperintensities in the periventricular and deep white matter were recruited. The subjects underwent the Freezing of Gait Questionnaire, computerized gait analyses, and diffusion tensor magnetic resonance imaging. Images of axial, radial and mean diffusivity, and fractional anisotropy were calculated as indices of white matter integrity and analyzed with tract-based spatial statistics. The fractional anisotropy, mean, axial and radial diffusivity averaged across the whole white matter structure were all significantly correlated with Freezing of Gait Questionnaire scores. Regionally, a negative correlation between Freezing of Gait Questionnaire scores and fractional anisotropy was found in the left superior longitudinal fasciculus beneath the left premotor cortex, right corpus callosum, and left cerebral peduncle. The scores of the Freezing of Gait Questionnaire were positively correlated with mean diffusivity in the left corona radiata and right corpus callosum, and with both axial and radial diffusivity in the left corona radiata. The white matter integrity in these tracts (except the corpus callosum) showed no correlation with cognitive or other gait measures, supporting the specificity of those abnormalities to freezing of gait. Divergent pathological lesions involved neural circuits composed of the cerebral cortex, basal ganglia and brainstem, suggesting that freezing of gait has a multifactorial nature.