Increased extra-neurite conductivity of brain in patients with Alzheimer's disease: A pilot study.

The objectives of this study were to investigate how the extra-neurite conductivity (EC) and intra-neurite conductivity (IC) were reflected in Alzheimer's disease (AD) patients compared with old cognitively normal (CN) people and patients with amnestic mild cognitive impairment (MCI) and to evaluate the association between those conductivity values and cognitive decline. To do this, high-frequency conductivity (HFC) at the Larmor frequency was obtained using MRI-based electrical property tomography (MREPT) and was decomposed into EC and IC using information of multi-shell multi-gradient direction diffusion tensor images. This prospective single-center study included 20 patients with mild or moderate AD, 25 patients with amnestic MCI, and 21 old CN participants. After decomposing EC and IC from HFC for all participants, we performed voxel-based and regions-of-interest analyses to compare conductivity between the three participant groups and to evaluate the association with either age or the Mini-Mental State Examination (MMSE) scores. We found increased EC in AD compared to CN and MCI. EC was significantly negatively associated with MMSE scores in the insula, and middle temporal gyrus. EC might be used as an imaging biomarker for helping to monitor cognitive function.

Predicting the apolipoprotein E ε4 allele carrier status based on gray matter volumes and cognitive function.

BACKGROUND: Apolipoprotein E (ApoE) ε4 carriers have a higher risk of developing Alzheimer's disease (AD) and show brain atrophy and cognitive decline even before diagnosis. OBJECTIVE: To predict ApoE ε4 status using gray matter volume (GMV) obtained from magnetic resonance imaging images and demographic data with machine learning (ML) methods. METHODS: We recruited 74 participants (25 probable AD, 24 amnestic mild cognitive impairment, and 25 cognitively normal older people) with known ApoE genotype (22 ApoE ε4 carriers and 52 noncarriers) and scanned them with three-dimensional (3D) T1-weighted (T1W) and 3D double inversion recovery (DIR) sequences. We extracted GMV from regions of interest related to AD pathology and used them as features along with age and mini-mental state examination (MMSE) scores to train different ML models. We performed both receiver operating characteristic curve analysis and the prediction analysis of the ApoE ε4 carrier with different ML models. RESULTS: The best model of ML analyses was a cubic support vector machine (SVM3) that used age, the MMSE score, and DIR GMVs at the amygdala, hippocampus, and precuneus as features (AUC = .88). This model outperformed models using T1W GMV or demographic data alone. CONCLUSION: Our results suggest that brain atrophy with DIR GMV and cognitive decline with aging can be useful biomarkers for predicting ApoE ε4 status and identifying individuals at risk of AD progression.

Altered functional connectivity of the ascending reticular activating system in obstructive sleep apnea.

Repeated arousals during sleep in obstructive sleep apnea (OSA) may lead to altered functional connectivity (FC) of the ascending reticular activating system (ARAS). We evaluated resting-state FC between eight ARAS nuclei and 105 cortical/subcortical regions in OSA patients and healthy controls. Fifty patients with moderate to severe OSA and 20 controls underwent overnight polysomnography and resting-state functional magnetic resonance imaging. Seed-to-voxel analysis of ARAS-cortex FC was compared between OSA patients and controls. The ARAS nuclei included the locus coeruleus (LC), laterodorsal tegmental nucleus (LDTg), and ventral tegmental area (VTA). FC values of three ARAS nuclei (the LC, LDTg, and VTA) significantly differed between the groups. FC of the LC with the precuneus, posterior cingulate gyrus, and right lateral occipital cortex (LOC) was stronger in OSA patients than controls. FC between the LDTg and right LOC was stronger in OSA patients than controls, but FC between the VTA and right LOC was weaker. Average LC-cortex FC values positively correlated with the arousal, apnea, and apnea-hypopnea index in OSA patients. Alterations in ARAS-cortex FC were observed in OSA patients. The strength of LC-cortex noradrenergic FC was related to arousal or OSA severity in patients.

Malignant Transformation of Warthin Tumor in the Cervical Lymph Node.

ABSTRACT: Warthin tumor is the second most common benign tumor of salivary glands. Here we present an interesting case of squamous cell carcinoma arising from the Warthin tumor in the cervical lymph node. The patient had another Warthin tumor in the parotid gland as well. Both the malignant transformation of Warthin tumor and the heterotopic occurrence of Warthin tumor in the cervical lymph node are rare. This exceptionally rare case demonstrates that the 2 rare clinical entities can occur simultaneously and affect clinical decisions.

Concurrent FDG-Avid and Non-FDG-Avid Pleomorphic Adenomas in the Submandibular Gland and Parapharyngeal Space.

ABSTRACT: Pleomorphic adenoma is the most common benign tumor of salivary glands. Here we present an interesting case of concurrent pleomorphic adenomas in the parapharyngeal space and submandibular gland. The tumors showed stark differences in the imaging findings on FDG PET/CT and MRI. Pathology confirmed the diagnosis of pleomorphic adenomas with the different composition of the cellular component and chondromyxoid stroma. This case suggests that the difference in cellularity of pleomorphic adenomas can affect FDG uptake and diffusion-weighted MRI-derived apparent diffusion coefficient values.

Microvascular morphology alteration using relaxation rate change with gadolinium-based magnetic resonance imaging contrast agent in patients with Alzheimer's disease.

Background: Conventional magnetic resonance imaging (MRI) techniques cannot demonstrate microvascular alterations in mild Alzheimer's disease (AD). Thus, the diagnosis of microvascular pathology commonly relies on postmortem. The purpose of this study was to evaluate alterations of microvascular structures in patients with AD using a 3T clinical MRI system with a commercially available contrast agent. Methods: Eleven patients with AD and 11 cognitively normal (CN) controls were included in this cross-sectional prospective study. R2 and R2* relaxation rate changes (∆R2 and ∆R2*) before and after a Gadolinium (Gd)-based contrast agent injection were calculated from images obtained with a multi-echo turbo spin-echo sequence and multi-echo gradient-echo sequence to obtain microvascular index maps of blood volume fraction (BVf), mean vessel diameter (mVD), vessel size index (VSI), mean vessel density (Q), and microvessel-weighted imaging (MvWI). Two-sample t-test was used to compare those values between the two groups. Correlation analysis was performed to evaluate the relationship between those values and age. Results: BVfs at the corpus callosum and at the thalamus were significantly increased in the AD group (P=0.024 and P=0.005, respectively). BVf at the gray matter (P=0.020) and white matter area (P=0.012) were also significantly increased in the AD group compared with the CN group. MvWIs at the hippocampus and parahippocampal gyrus were significantly increased in the AD group compared with the CN group (P=0.020 and P=0.006, respectively). Voxel-based analysis showed both mVD and VSI were significantly decreased at the prefrontal lobe in the AD group. Q were not significant difference between CN and AD groups. MvWI were significantly positively correlated with age. Conclusions: Microvascular index was a useful non-invasive method to evaluate microvascular morphology alteration. The microvascular morphology of AD was manifested as increasing BVf and microvessel-weighted.

Altered intrinsic brain functional network dynamics in moderate-to-severe obstructive sleep apnea.

OBJECTIVES: Obstructive sleep apnea (OSA) can affect temporal fluctuations in brain activity during rest. Dynamic functional connectivity (dFC) captures the fluctuations in FC during the resting state. This study aimed to investigate differences in dFC between moderate-to-severe OSA patients and healthy controls using resting-state functional magnetic resonance imaging (fMRI) and sliding-window analysis. METHODS: Thirty-seven consecutive patients with moderate-to-severe OSA and 16 age- and sex-matched controls underwent resting-state fMRI in the morning following overnight polysomnography. The dynamics of aberrant FC between the groups and the correlation between the dynamics and clinical variables were evaluated. RESULTS: dFC analysis revealed two distinct connectivity states: hypoconnected (State I) and hyperconnected (State II). In OSA patients, State I occurred 34% more often than in the controls and the occurrence of State II was proportionally reduced. The time in State I positively correlated with the Pittsburg Sleep Quality Index score in the OSA patients. CONCLUSIONS: This study showed dFC alterations in moderate-to-severe OSA patients, which may serve as a novel physiological biomarker for OSA.

Gray-white matter boundary Z-score and volume as imaging biomarkers of Alzheimer's disease.

Introduction: Alzheimer's disease (AD) presents typically gray matter atrophy and white matter abnormalities in neuroimaging, suggesting that the gray-white matter boundary could be altered in individuals with AD. The purpose of this study was to explore differences of gray-white matter boundary Z-score (gwBZ) and its tissue volume (gwBTV) between patients with AD, amnestic mild cognitive impairment (MCI), and cognitively normal (CN) elderly participants. Methods: Three-dimensional T1-weight images of a total of 227 participants were prospectively obtained from our institute from 2006 to 2022 to map gwBZ and gwBTV on images. Statistical analyses of gwBZ and gwBTV were performed to compare the three groups (AD, MCI, CN), to assess their correlations with age and Korean version of the Mini-Mental State Examination (K-MMSE), and to evaluate their effects on AD classification in the hippocampus. Results: This study included 62 CN participants (71.8 ± 4.8 years, 20 males, 42 females), 72 MCI participants (72.6 ± 5.1 years, 23 males, 49 females), and 93 AD participants (73.6 ± 7.7 years, 22 males, 71 females). The AD group had lower gwBZ and gwBTV than CN and MCI groups. K-MMSE showed positive correlations with gwBZ and gwBTV whereas age showed negative correlations with gwBZ and gwBTV. The combination of gwBZ or gwBTV with K-MMSE had a high accuracy in classifying AD from CN in the hippocampus with an area under curve (AUC) value of 0.972 for both. Conclusion: gwBZ and gwBTV were reduced in AD. They were correlated with cognitive function and age. Moreover, gwBZ or gwBTV combined with K-MMSE had a high accuracy in differentiating AD from CN in the hippocampus. These findings suggest that evaluating gwBZ and gwBTV in AD brain could be a useful tool for monitoring AD progression and diagnosis.

Psammomatoid ossifying fibroma in the extraconal space: a case report.

A 24-year-old patient with left eye proptosis and intermittent pain for 5 months was admitted to our hospital. Physical examination revealed neither extra ocular muscle limitations nor visual field defects. Magnetic resonance imaging (MRI) revealed a multicystic mass in the left extraconal space compressing the superior oblique muscle and adjacent frontal lobe. Layered hemorrhage was observed within the lesion in the 1-month follow-up MRI. Dynamic contrast enhanced imaging showed mild increased perfusion of the surrounding peripheral portion. Magnetic resonance spectroscopy showed an increased lactate/lipid peak of 1.3 ppm. Combined open and endonasal surgery was performed, and the final diagnosis was psammomatoid ossifying fibroma. The tumor was positive for vimentin, and negative for smooth muscle actin, S100 and epithelial membrane antigen. Despite its rarity, psammomatoid ossifying fibroma should be considered when multicystic lesions with peripheral enhancement near the orbit exhibit progressive inner hemorrhage.

Association between carotid atherosclerosis and presence of intracranial atherosclerosis using three-dimensional high-resolution vessel wall magnetic resonance imaging in asymptomatic patients with type 2 diabetes.

AIMS: Carotid atherosclerosis (CAS) is associated with a high risk of cardiovascular diseases. We aimed to investigate whether CAS is associated with the presence of intracranial atherosclerosis (ICAS). METHODS: A total of 69 asymptomatic patients with type 2 diabetes (36 with CAS and 33 without CAS) who were free of cerebrovascular disease were enrolled in this case-control study. CAS was defined as a mean carotid intima-media thickness ≥ 1.0 mm or carotid plaque. The presence of ICAS was identified using three-dimensional high-resolution vessel wall magnetic resonance imaging. RESULTS: There was no difference between the case and control groups in baseline characteristics, such as age, the proportion of men, duration of diabetes, and other cardiometabolic risk factors. The prevalence of ICAS was significantly higher in patients with CAS than those without CAS (72.2 % vs 48.5 %, P = 0.044). CAS was significantly associated with the presence of ICAS, even after adjusting other covariates (odds ratio [OR], 3.19; 95 % confidence interval [CI] 1.09-9.33, P = 0.034). In addition, CAS was significantly associated with the presence of multiple ICAS lesions (OR, 5.57; 95 % CI 1.75-17.78, P = 0.004). CONCLUSIONS: CAS is significantly and independently associated with the presence and extent of ICAS in asymptomatic patients with type 2 diabetes.

Application of High-Frequency Conductivity Map Using MRI to Evaluate It in the Brain of Alzheimer's Disease Patients.

Background: The previous studies reported increased concentrations of metallic ions, imbalanced Na+ and K+ ions, and the increased mobility of protons by microstructural disruptions in Alzheimer's disease (AD). Purpose: (1) to apply a high-frequency conductivity (HFC) mapping technique using a clinical 3T MRI system, (2) compare HFC values in the brains of participants with AD, amnestic mild cognitive impairment (MCI), and cognitively normal (CN) elderly people, (3) evaluate the relationship between HFC values and cognitive decline, and (4) explore usefulness of HFC values as an imaging biomarker to evaluate the differentiation of AD from CN. Materials and Methods: This prospective study included 74 participants (23 AD patients, 27 amnestic MCI patients, and 24 CN elderly people) to explore the clinical application of HFC mapping in the brain from March 2019 to August 2021. We performed statistical analyses to compare HFC maps between the three participant groups, evaluate the association of HFC maps with Mini-Mental State Examination (MMSE) scores, and to evaluate the differentiation between the participant groups for HFC values for some brain areas. Results: We obtained a good HFC map non-invasively. The HFC value was higher in the AD group than in the CN and MCI groups. MMSE scores were negatively associated with HFC values. Age was positively associated with HFC values. The HFC value in the insula has a high area under the receiver operating characteristic (ROC) curve (AUC) value to differentiate AD patients from the CN participants (Sensitivity [SE] = 82, Specificity [SP] =97, AUC = 0.902, p < 0.0001), better than gray matter volume (GMV) in hippocampus (SE = 79, SP = 83, AUC = 0.880, p < 0.0001). The classification for differentiating AD from CN was highest by adding the hippocampal GMV to the insular HFC value (SE = 87, SP = 87, AUC = 0.928, p < 0.0001). Conclusion: High-frequency conductivity values were significantly increased in the AD group compared to the CN group and increased with age and disease severity. HFC values of the insula along with the GMV of the hippocampus can be used as an imaging biomarker to improve the differentiation of AD from CN.

Myelin-Weighted Imaging Presents Reduced Apparent Myelin Water in Patients with Alzheimer's Disease.

The purpose of this study was to investigate myelin loss in both AD and mild cognitive impairment (MCI) patients with a new myelin water mapping technique within reasonable scan time and evaluate the clinical relevance of the apparent myelin water fraction (MWF) values by assessing the relationship between decreases in myelin water and the degree of memory decline or aging. Twenty-nine individuals were assigned to the cognitively normal (CN) elderly group, 32 participants were assigned to the MCI group, and 31 patients were assigned to the AD group. A 3D visualization of the short transverse relaxation time component (ViSTa)-gradient and spin-echo (GraSE) sequence was developed to map apparent MWF. Then, the MWF values were compared between the three participant groups and was evaluated the relationship with the degree of memory loss. The AD group showed a reduced apparent MWF compared to the CN and MCI groups. The largest AUC (area under the curve) value was in the corpus callosum and used to classify the CN and AD groups using the apparent MWF. The ViSTa-GraSE sequence can be a useful tool to map the MWF in a reasonable scan time. Combining the MWF in the corpus callosum with the detection of atrophy in the hippocampus can be valuable for group classification.

Effective End-to-End Deep Learning Process in Medical Imaging Using Independent Task Learning: Application for Diagnosis of Maxillary Sinusitis.

PURPOSE: This study aimed to propose an effective end-to-end process in medical imaging using an independent task learning (ITL) algorithm and to evaluate its performance in maxillary sinusitis applications. MATERIALS AND METHODS: For the internal dataset, 2122 Waters' view X-ray images, which included 1376 normal and 746 sinusitis images, were divided into training (n=1824) and test (n=298) datasets. For external validation, 700 images, including 379 normal and 321 sinusitis images, from three different institutions were evaluated. To develop the automatic diagnosis system algorithm, four processing steps were performed: 1) preprocessing for ITL, 2) facial patch detection, 3) maxillary sinusitis detection, and 4) a localization report with the sinusitis detector. RESULTS: The accuracy of facial patch detection, which was the first step in the end-to-end algorithm, was 100%, 100%, 99.5%, and 97.5% for the internal set and external validation sets #1, #2, and #3, respectively. The accuracy and area under the receiver operating characteristic curve (AUC) of maxillary sinusitis detection were 88.93% (0.89), 91.67% (0.90), 90.45% (0.86), and 85.13% (0.85) for the internal set and external validation sets #1, #2, and #3, respectively. The accuracy and AUC of the fully automatic sinusitis diagnosis system, including site localization, were 79.87% (0.80), 84.67% (0.82), 83.92% (0.82), and 73.85% (0.74) for the internal set and external validation sets #1, #2, and #3, respectively. CONCLUSION: ITL application for maxillary sinusitis showed reasonable performance in internal and external validation tests, compared with applications used in previous studies.

Treatment evaluation of Kami Guibi-tang on participants with amnestic mild cognitive impairment using magnetic resonance imaging on brain metabolites, gamma-aminobutyric acid, and cerebral blood flow.

PURPOSE: To evaluate the effectiveness of Kami Guibi-tang (KGT) in the treatment of mild cognitive impairment (MCI) using magnetic resonance imaging (MRI) on brain metabolites, neurotransmitter, and cerebral blood flow (CBF). METHODS: We randomly allocated a total of 30 MCI patients to a KGT (N = 16) or a placebo (N = 14) group and performed MRI scans before and after 24 weeks of treatment. The participants underwent brain magnetic resonance spectroscopy and MRI scans to obtain brain metabolites using Point-RESolved Spectroscopy (PRESS) single-voxel spectroscopy, gamma-aminobutyric acid (GABA) neurotransmitter using Mescher-Garwood PRESS, and CBF using pseudocontinuous arterial spin labeling sequences using a 3.0 Tesla MRI system. We analyzed metabolite and neurotransmitter levels and CBF using repeated-measure analysis of variance to evaluate between-subject group effect, within-subject treatment condition effect, and interaction of group by condition (group x condition). RESULTS: The GABA+/creatine (Cr) ratio values were not significantly different between the before and after treatment conditions. The glutamate complex/Cr ratio difference before and after treatment was lower in the KGT group than in the placebo group, but was not statistically significant (p = 0.077). The result of region of interest-based CBF measurement showed that CBF values were significantly lower after treatment at Cluster 2 for the KGT group (p = 0.003) and the placebo group (p = 0.011), at hippocampus for the KGT group (p = 0.004) and the placebo group (p = 0.008), and at the fusiform gyrus for the KGT group (p = 0.002). Furthermore, the absolute CBF difference before and after treatment in the fusiform gyrus was significantly lower in the KGT group than in the placebo group (p = 0.024). CONCLUSIONS: Although a KGT treatment of 24 weeks showed some significant impact on the level of CBF, the Korean version of the mini-mental state examination score was not significantly different between before and after treatment conditions, indicating that there was no memory function improvement after treatment in amnestic MCI patients. Therefore, further studies should be performed with a relatively larger population and extending the duration of the KGT treatment.

Longitudinal Functional Magnetic Resonance Spectroscopy Study in Subjects with Mild Cognitive Impairment and Alzheimer's Disease.

BACKGROUND: Longitudinal changes of brain metabolites during a functional stimulation are unknown in amnestic mild cognitive impairment (aMCI) and Alzheimer's disease (AD) subjects. OBJECTIVE: This study was to evaluate the longitudinal changes of brain metabolites using proton magnetic resonance spectroscopy (1H MRS) in response to treatment during a memory task in the subjects of cognitive normal (CN), aMCI, and AD. METHODS: We acquired functional magnetic resonance spectroscopy (fMRS) data from 28 CN elderly, 16 aMCI and 12 AD subjects during a face-name association task. We measured fMRS metabolite ratios over 24 months in the 8-month apart, determined the temporal changes of the metabolites, and evaluated the differences among the three groups under the three different conditions (base, novel, repeat). RESULTS: The results of comparisons for the three subject groups and the three-time points showed that tNAA/tCho and tCr/tCho were statistically significant among the three subject groups in any of the three conditions. The dynamic temporal change measurements for the metabolites for each condition showed that Glx/tCho and Glu/tCho levels at the third visit increased significantly compared with in the first visit in the novel condition in the AD group. CONCLUSION: We found declines in tNAA/tCho and tCr/tCho in the aMCI and AD subjects with increasing disease severity, being highest in CN and lowest in AD. The Glx/tCho level increased temporally in the AD subjects after they took an acetylcholine esterase inhibitor. Therefore, Glx may be suitable to demonstrate functional recovery after treatment.

Development and evaluation of a T1 standard brain template for Alzheimer disease.

BACKGROUND: Patients with Alzheimer disease (AD) and mild cognitive impairment (MCI) have high variability in brain tissue loss, making it difficult to use a disease-specific standard brain template. The objective of this study was to develop an AD-specific three-dimensional (3D) T1 brain tissue template and to evaluate the characteristics of the populations used to form the template. METHODS: We obtained 3D T1-weighted images from 294 individuals, including 101 AD, 96 amnestic MCI, and 97 cognitively normal (CN) elderly individuals, and segmented them into different brain tissues to generate AD-specific brain tissue templates. Demographic data and clinical outcome scores were compared between the three groups. Voxel-based analyses and regions-of-interest-based analyses were performed to compare gray matter volume (GMV) and white matter volume (WMV) between the three participant groups and to evaluate the relationship of GMV and WMV loss with age, years of education, and Mini-Mental State Examination (MMSE) scores. RESULTS: We created high-resolution AD-specific tissue probability maps (TPMs). In the AD and MCI groups, losses of both GMV and WMV were found with respect to the CN group in the hippocampus (F >44.60, P<0.001). GMV was lower with increasing age in all individuals in the left (r=-0.621, P<0.001) and right (r=-0.632, P<0.001) hippocampi. In the left hippocampus, GMV was positively correlated with years of education in the CN groups (r=0.345, P<0.001) but not in the MCI (r=0.223, P=0.0293) or AD (r=-0.021, P=0.835) groups. WMV of the corpus callosum was not significantly correlated with years of education in any of the three subject groups (r=0.035 and P=0.549 for left, r=0.013 and P=0.821 for right). In all individuals, GMV of the hippocampus was significantly correlated with MMSE scores (left, r=0.710 and P<0.001; right, r=0.680 and P<0.001), while WMV of the corpus callosum showed a weak correlation (left, r=0.142 and P=0.015; right, r=0.123 and P=0.035). CONCLUSIONS: A 3D, T1 brain tissue template was created using imaging data from CN, MCI, and AD participants considering the participants' age, sex, and years of education. Our disease-specific template can help evaluate brains to promote early diagnosis of MCI individuals and aid treatment of MCI and AD individuals.

Relationship between Brain Tissue Changes and Blood Biomarkers of Cyclophilin A, Heme Oxygenase-1, and Inositol-Requiring Enzyme 1 in Patients with Alzheimer's Disease.

Cyclophilin A (CypA), heme oxygenase-1 (HO-1), and inositol-requiring enzyme 1 (IRE1) are believed to be associated with Alzheimer's disease (AD). In this study, we investigated the association between gray matter volume (GMV) changes and blood levels of CypA, HO-1, and IRE1 in cognitively normal (CN) subjects and those with amnestic mild cognitive impairment (aMCI) and AD. Forty-five elderly CN, 34 aMCI, and 39 AD subjects were enrolled in this study. The results of voxel-based multiple regression analysis showed that blood levels of CypA, HO-1, and IRE1 were correlated with GMV on brain magnetic resonance imaging (MRI) in the entire population (p = 0.0005). The three serum protein levels were correlated with GMV of signature AD regions in the population as a whole. CypA values increased with increasing GMV in the occipital gyrus (r = 0.387, p < 0.0001) and posterior cingulate (r = 0.196, p = 0.034). HO-1 values increased with increasing GMV at the uncus (r = 0.307, p = 0.0008), lateral globus pallidus and putamen (r = 0.287, p = 0.002), and hippocampus (r = 0.197, p = 0.034). IRE1 values decreased with increasing GMV at the uncus (r = -0.239, p = 0.010) and lateral globus pallidus and putamen (r = -0.335, p = 0.0002). Associations between the three serum protein levels and regional GMV indicate that the blood levels of these biomarkers may reflect the pathological mechanism of AD in the brain.

Added Value of Chemical Exchange-Dependent Saturation Transfer MRI for the Diagnosis of Dementia.

OBJECTIVE: Chemical exchange-dependent saturation transfer (CEST) MRI is sensitive for detecting solid-like proteins and may detect changes in the levels of mobile proteins and peptides in tissues. The objective of this study was to evaluate the characteristics of chemical exchange proton pools using the CEST MRI technique in patients with dementia. MATERIALS AND METHODS: Our institutional review board approved this cross-sectional prospective study and informed consent was obtained from all participants. This study included 41 subjects (19 with dementia and 22 without dementia). Complete CEST data of the brain were obtained using a three-dimensional gradient and spin-echo sequence to map CEST indices, such as amide, amine, hydroxyl, and magnetization transfer ratio asymmetry (MTRasym) values, using six-pool Lorentzian fitting. Statistical analyses of CEST indices were performed to evaluate group comparisons, their correlations with gray matter volume (GMV) and Mini-Mental State Examination (MMSE) scores, and receiver operating characteristic (ROC) curves. RESULTS: Amine signals (0.029 for non-dementia, 0.046 for dementia, p = 0.011 at hippocampus) and MTRasym values at 3 ppm (0.748 for non-dementia, 1.138 for dementia, p = 0.022 at hippocampus), and 3.5 ppm (0.463 for non-dementia, 0.875 for dementia, p = 0.029 at hippocampus) were significantly higher in the dementia group than in the non-dementia group. Most CEST indices were not significantly correlated with GMV; however, except amide, most indices were significantly correlated with the MMSE scores. The classification power of most CEST indices was lower than that of GMV but adding one of the CEST indices in GMV improved the classification between the subject groups. The largest improvement was seen in the MTRasym values at 2 ppm in the anterior cingulate (area under the ROC curve = 0.981), with a sensitivity of 100 and a specificity of 90.91. CONCLUSION: CEST MRI potentially allows noninvasive image alterations in the Alzheimer's disease brain without injecting isotopes for monitoring different disease states and may provide a new imaging biomarker in the future.

Evaluation and Prediction of Early Alzheimer's Disease Using a Machine Learning-based Optimized Combination-Feature Set on Gray Matter Volume and Quantitative Susceptibility Mapping.

BACKGROUND: Because Alzheimer's Disease (AD) has very complicated pattern changes, it is difficult to evaluate it with a specific factor. Recently, novel machine learning methods have been applied to solve limitations. OBJECTIVE: The objective of this study was to investigate the approach of classification and prediction methods using the Machine Learning (ML)-based Optimized Combination-Feature (OCF) set on Gray Matter Volume (GMV) and Quantitative Susceptibility Mapping (QSM) in the subjects of Cognitive Normal (CN) elderly, Amnestic Mild Cognitive Impairment (aMCI), and mild and moderate AD. MATERIALS AND METHODS: 57 subjects were included: 19 CN, 19 aMCI, and 19 AD with GMV and QSM. Regions-of-Interest (ROIs) were defined at the well-known regions for rich iron contents and amyloid accumulation areas in the AD brain. To differentiate the three subject groups, the Support Vector Machine (SVM) with the three different kernels and with the OCF set was conducted with GMV and QSM values. To predict the aMCI stage, regression-based ML models were performed with the OCF set. The result of prediction was compared with the accuracy of clinical data. RESULTS: In the group classification between CN and aMCI, the highest accuracy was shown using the combination of GMVs (hippocampus and entorhinal cortex) and QSMs (hippocampus and pulvinar) data using the 2nd SVM classifier (AUC = 0.94). In the group classification between aMCI and AD, the highest accuracy was shown using the combination of GMVs (amygdala, entorhinal cortex, and posterior cingulate cortex) and QSMs (hippocampus and pulvinar) data using the 2nd SVM classifier (AUC = 0.93). In the group classification between CN and AD, the highest accuracy was shown using the combination of GMVs (amygdala, entorhinal cortex, and posterior cingulate cortex) and QSMs (hippocampus and pulvinar) data using the 2nd SVM classifier (AUC = 0.99). To predict aMCI from CN, the exponential Gaussian process regression model with the OCF set using GMV and QSM data was shown the most similar result (RMSE = 0.371) to clinical data (RMSE = 0.319). CONCLUSION: The proposed OCF based ML approach with GMV and QSM was shown the effective performance of the subject group classification and prediction for aMCI stage. Therefore, it can be used as personalized analysis or diagnostic aid program for diagnosis.