Morphological connectivity differences in Alzheimer's disease correlate with gene transcription and cell-type.

Alzheimer's disease (AD) is one of the most prevalent forms of dementia in older individuals. Convergent evidence suggests structural connectome abnormalities in specific brain regions are linked to AD progression. The biological basis underpinnings of these connectome changes, however, have remained elusive. We utilized an individual regional mean connectivity strength (RMCS) derived from a regional radiomics similarity network to capture altered morphological connectivity in 1654 participants (605 normal controls, 766 mild cognitive impairment [MCI], and 283 AD). Then, we also explored the biological basis behind these morphological changes through gene enrichment analysis and cell-specific analysis. We found that RMCS probes of the hippocampus and medial temporal lobe were significantly altered in AD and MCI, with these differences being spatially related to the expression of AD-risk genes. In addition, gene enrichment analysis revealed that the modulation of chemical synaptic transmission is the most relevant biological process associated with the altered RMCS in AD. Notably, neuronal cells were found to be the most pertinent cells in the altered RMCS. Our findings shed light on understanding the biological basis of structural connectome changes in AD, which may ultimately lead to more effective diagnostic and therapeutic strategies for this devastating disease.

Predicting brain age gap with radiomics and automl: A Promising approach for age-Related brain degeneration biomarkers.

The Brain Age Gap (BAG), which refers to the difference between chronological age and predicted neuroimaging age, is proposed as a potential biomarker for age-related brain degeneration. However, existing brain age prediction models usually rely on a single marker and can not discover meaningful hidden information in radiographic images. This study focuses on the application of radiomics, an advanced imaging analysis technique, combined with automated machine learning to predict BAG. Our methods achieve a promising result with a mean absolute error of 1.509 using the Alzheimer's Disease Neuroimaging Initiative dataset. Furthermore, we find that the hippocampus and parahippocampal gyrus play a significant role in predicting age with interpretable method called SHapley Additive exPlanations. Additionally, our investigation of age prediction discrepancies between patients with Alzheimer's disease (AD) and those with mild cognitive impairment (MCI) reveals a notable correlation with clinical cognitive assessment scale scores. This suggests that BAG has the potential to serve as a biomarker to support the diagnosis of AD and MCI. Overall, this study presents valuable insights into the application of neuroimaging models in the diagnosis of neurodegenerative diseases.

High-Resolution, Highly Transparent, and Efficient Quantum Dot Light-Emitting Diodes.

Aiming at next-generation displays, high-resolution quantum dot light-emitting diodes (QLEDs) with high efficiency and transparency are highly desired. However, there is limited study involving the improvements of QLED pixel resolution, efficiency, and transparency simultaneously, which undoubtedly restricts the practical applications of QLED for next-generation displays. Here, the strategy of electrostatic force-induced deposition (EF-ID) is proposed by introducing alternating polyethyleneimine (PEI) and fluorosilane patterns to synergistically improve the pixel accuracy and transmittance of QD patterns. More importantly, the leakage current induced by the void spaces between pixels that is usually reported for high-resolution QLEDs is greatly suppressed by substrate-assisted insulating fluorosilane patterns. Finally, high-performance QLEDs with high resolution ranging from 1104 to 3031 pixels per inch (PPI) and a high efficiency of 15.6% are achieved, among the best performances of high resolution QLEDs. Notably, the high resolution QD pixels greatly enhance the transmittance of the QD patterns, thus prompting an impressive transmittance of 90.7% for the transparent QLEDs (2116 PPI), which represents the highest transmittance of transparent QLED devices. Consequently, this work contributes an effective and general approach for high-resolution QLEDs with high efficiency and transparency.

Single-cell transcriptomics reveals variable trajectories of CSPCs in the progression of osteoarthritis.

Osteoarthritis (OA) is characterised by cartilage destruction; however, there are no specific drugs available for its treatment. Cartilage-derived stem/progenitor cells (CSPCs) are multipotent cells that play an essential role in cartilage renewal and may provide critical insights into the medical needs for OA treatment. However, alterations in cell function and fate of CSPCs during OA progression have seldom been analysed, especially at the single-cell level. Additionally, it has been reported that CSPCs can migrate to the cartilage injury area, although the mechanism of migration remains elusive. Thus, understanding the changing patterns of CSPCs in the pathological process of OA is important in the effort to develop stem cell therapy for OA. Here, we downloaded single-cell transcriptomic data of patients with OA from the Gene Expression Omnibus (GEO) database and performed unbiased clustering of the cells based on gene expression patterns using the Seurat package. Using common stem cell markers and chondrogenic transcription factors, we traced CSPCs throughout all stages of OA. We further explored the dynamics of CSPCs in OA progression and validated the single-cell RNA sequencing data in vitro using qPCR, immunofluorescence, and western blotting. Specifically, we primarily explored the heterogeneity of CSPCs at the single-cell level and found that it was closely associated with OA progression. Our results indicate significantly reduced chondrogenic differentiation capacity in CSPCs during the late stage of OA, while their proliferation capacity tended to increase. We also found that genes implicated in fibrosis, cell motility, and extracellular matrix remodelling were upregulated in CSPCs during the progression of OA. Our study revealed the dynamics of stem cells in OA progression and may inform the development of stem cell therapy for OA.

Accurate segmentation of green fruit based on optimized mask RCNN application in complex orchard.

Fruit and vegetable picking robots are affected by the complex orchard environment, resulting in poor recognition and segmentation of target fruits by the vision system. The orchard environment is complex and changeable. For example, the change of light intensity will lead to the unclear surface characteristics of the target fruit; the target fruits are easy to overlap with each other and blocked by branches and leaves, which makes the shape of the fruits incomplete and difficult to accurately identify and segment one by one. Aiming at various difficulties in complex orchard environment, a two-stage instance segmentation method based on the optimized mask region convolutional neural network (mask RCNN) was proposed. The new model proposed to apply the lightweight backbone network MobileNetv3, which not only speeds up the model but also greatly improves the accuracy of the model and meets the storage resource requirements of the mobile robot. To further improve the segmentation quality of the model, the boundary patch refinement (BPR) post-processing module is added to the new model to optimize the rough mask boundaries of the model output to reduce the error pixels. The new model has a high-precision recognition rate and an efficient segmentation strategy, which improves the robustness and stability of the model. This study validates the effect of the new model using the persimmon dataset. The optimized mask RCNN achieved mean average precision (mAP) and mean average recall (mAR) of 76.3 and 81.1%, respectively, which are 3.1 and 3.7% improvement over the baseline mask RCNN, respectively. The new model is experimentally proven to bring higher accuracy and segmentation quality and can be widely deployed in smart agriculture.

A semi-supervised learning framework for micropapillary adenocarcinoma detection.

PURPOSE: Micropapillary adenocarcinoma is a distinctive histological subtype of lung adenocarcinoma with poor prognosis. Computer-aided diagnosis method has the potential to provide help for its early diagnosis. But the implementation of the existing methods largely relies on massive manually labeled data and consumes a lot of time and energy. To tackle these problems, we propose a framework that applies semi-supervised learning method to detect micropapillary adenocarcinoma, which aims to utilize labeled and unlabeled data better. METHODS: The framework consists of a teacher model and a student model. The teacher model is first obtained by using the labeled data. Then, it makes predictions on unlabeled data as pseudo-labels for students. Finally, high-quality pseudo-labels are selected and associated with the labeled data to train the student model. During the learning process of the student model, augmentation is added so that the student model generalizes better than the teacher model. RESULTS: Experiments are conducted on our own whole slide micropapillary lung adenocarcinoma histopathology image dataset and we selected 3527 patches for the experiment. In the supervised learning, our detector achieves a precision of 0.762 and recall of 0.884. In the semi-supervised learning, our method achieves a precision of 0.775 and recall of 0.896; it is superior to other methods. CONCLUSION: We proposed a semi-supervised learning framework for micropapillary adenocarcinoma detection, which has better performance in utilizing both labeled and unlabeled data. In addition, the detector we designed improves the detection accuracy and speed and achieves promising results in detecting micropapillary adenocarcinoma.

An Attention Based Bidirectional LSTM Method to Predict the Binding of TCR and Epitope.

The T-cell epitope prediction has always been a long-term challenge in immunoinformatics and bioinformatics. Studying the specific recognition between T-cell receptor (TCR) and peptide-major histocompatibility complex (p-MHC) complexes can help us better understand the immune mechanism, it's also make a signification contribution in developing vaccines and targeted drugs. Meanwhile, more advanced methods are needed for distinguishing TCRs binding from different epitopes. In this paper, we introduce a hybrid model composed of bidirectional long short-term memory networks (BiLSTM), attention and convolutional neural networks (CNN) that can identified the binding of TCRs to epitopes. The BiLSTM can more completely extract amino acid forward and backward information in the sequence, and attention mechanism can focus on amino acids at certain positions from complex sequences to capture the most important feature, then CNN was used to further extract salient features to predict the binding of TCR-epitope. In McPAS dataset, the AUC value (the area under ROC curve) of naive TCR-epitope binding is 0.974 and specific TCR-epitope binding is 0.887. The model has achieved better prediction results than other existing models (TCRGP, ERGO, NetTCR), and some experiments are used to analyze the advantages of our model. The algorithm is available at https://github.com/bijingshu/BiAttCNN.git.

A semi-supervised learning approach with consistency regularization for tumor histopathological images analysis.

Introduction: Manual inspection of histopathological images is important in clinical cancer diagnosis. Pathologists implement pathological diagnosis and prognostic evaluation through the microscopic examination of histopathological slices. This entire process is time-consuming, laborious, and challenging for pathologists. The modern use of whole-slide imaging, which scans histopathology slides to digital slices, and analysis using computer-aided diagnosis is an essential problem. Methods: To solve the problem of difficult labeling of histopathological data, and improve the flexibility of histopathological analysis in clinical applications, we herein propose a semi-supervised learning algorithm coupled with consistency regularization strategy, called"Semi- supervised Histopathology Analysis Network"(Semi-His-Net), for automated normal-versus-tumor and subtype classifications. Specifically, when inputted disturbing versions of the same image, the model should predict similar outputs. Based on this, the model itself can assign artificial labels to unlabeled data for subsequent model training, thereby effectively reducing the labeled data required for training. Results: Our Semi-His-Net is able to classify patches from breast cancer histopathological images into normal tissue and three other different tumor subtypes, achieving an accuracy was 90%. The average AUC of cross-classification between tumors reached 0.893. Discussion: To overcome the limitations of visual inspection by pathologists for histopathology images, such as long time and low repeatability, we have developed a deep learning-based framework (Semi-His-Net) for automatic classification subdivision of the subtypes contained in the whole pathological images. This learning-based framework has great potential to improve the efficiency and repeatability of histopathological image diagnosis.

A systematic analysis of diagnostic performance for Alzheimer's disease using structural MRI.

Background: Alzheimer's disease (AD) is one of the most common neurodegenerative disorders in the elderly. Although numerous structural magnetic resonance imaging (sMRI) studies have reported diagnostic models that could distinguish AD from normal controls (NCs) with 80-95% accuracy, limited efforts have been made regarding the clinically practical computer-aided diagnosis (CAD) system for AD. Objective: To explore the potential factors that hinder the clinical translation of the AD-related diagnostic models based on sMRI. Methods: To systematically review the diagnostic models for AD based on sMRI, we identified relevant studies published in the past 15 years on PubMed, Web of Science, Scopus, and Ovid. To evaluate the heterogeneity and publication bias among those studies, we performed subgroup analysis, meta-regression, Begg's test, and Egger's test. Results: According to our screening criterion, 101 studies were included. Our results demonstrated that high diagnostic accuracy for distinguishing AD from NC was obtained in recently published studies, accompanied by significant heterogeneity. Meta-analysis showed that many factors contributed to the heterogeneity of high diagnostic accuracy of AD using sMRI, which included but was not limited to the following aspects: (i) different datasets; (ii) different machine learning models, e.g. traditional machine learning or deep learning model; (iii) different cross-validation methods, e.g. k-fold cross-validation leads to higher accuracies than leave-one-out cross-validation, but both overestimate the accuracy when compared to validation in independent samples; (iv) different sample sizes; and (v) the publication times. We speculate that these complicated variables might be the adverse factor for developing a clinically applicable system for the early diagnosis of AD. Conclusions: Our findings proved that previous studies reported promising results for classifying AD from NC with different models using sMRI. However, considering the many factors hindering clinical radiology practice, there would still be a long way to go to improve.

In Vitro Activity of Auranofin in Combination With Aztreonam-Avibactam Against Metallo-ß-lactamase (MBL)-Producing Enterobacterales.

Objectives: To assess the efficacy of aztreonam-avibactam-auranofin (ATM-AVI-AUR) against a collection of 88 carbapenemase-producing Enterobacterales (CPE) clinical isolates and 6 in vitro selected ATM-AVI-resistant CPE with CMY-16 Tyr150Ser and Asn346His mutants or transformants. Methods: MICs of imipenem, ceftazidime-avibact8am (CAZ-AVI), ATM-AVI, CAZ-AVI-AUR and ATM-AVI-AUR were determined via the broth microdilution method. Genetic background and carbapenemase genes were determined by PCR and Sanger sequencing. Results: AUR alone showed little antibacterial activity with AUR MICs were greater than 64 µg/mL for all the 88 clinical CPE isolates. The addition of AUR (16 µg/mL) resulted in an 3-folding dilutions MIC reduction of ATM-AVI MIC50 (0.5 to 0.0625 µg/mL) and a 2-folding dilutions MIC reduction of MIC90 (1 to 0.25 µg/mL) against all 88 clinical CPE isolates, respectively. Notably, the reduced ATM-AVI MIC values were mainly found in MBL-producers, and the MIC50 and MIC90 reduced by 2-folding dilutions (0.25 to 0.0625 µg/mL) and 3-folding dilutions (2 to 0.25 µg/mL) respectively by AUR among the 51 MBL-producers. By contrast, the addition of AUR did not showed significant effects on ATM-AVI MIC50 (0.0625 µg/mL) and MIC90 (0.125 µg/mL) among single KPC-producers. Interestingly, the addition of AUR restored the ATM-AVI susceptibility against the 6 in vitro selected ATM-AVI-resistant CMY-16 Tyr150Ser and Asn346His mutants or transfromants, with the MICs reduced from ≥32 µg/mL (32->256 µg/mL) to ≤8 µg/mL (0.0625-8 µg/mL). Conclusions: Our results demonstrated that AUR potentiated the activities of CAZ-AVI and ATM-AVI against MBL-producing isolates in vitro. Importantly, AUR restored the ATM-AVI activity against ATM-AVI resistant mutant strains. As a clinically approved drug, AUR might be repurposed in combination with ATM-AVI to treat infections caused by highly resistant MBL-producing Enterobacterales.

Regional radiomics similarity networks (R2SNs) in the human brain: Reproducibility, small-world properties and a biological basis.

A structural covariance network (SCN) has been used successfully in structural magnetic resonance imaging (sMRI) studies. However, most SCNs have been constructed by a unitary marker that is insensitive for discriminating different disease phases. The aim of this study was to devise a novel regional radiomics similarity network (R2SN) that could provide more comprehensive information in morphological network analysis. R2SNs were constructed by computing the Pearson correlations between the radiomics features extracted from any pair of regions for each subject (AAL atlas). We further assessed the small-world property of R2SNs, and we evaluated the reproducibility in different datasets and through test-retest analysis. The relationships between the R2SNs and general intelligence/interregional coexpression of genes were also explored. R2SNs could be replicated in different datasets, regardless of the use of different feature subsets. R2SNs showed high reproducibility in the test-retest analysis (intraclass correlation coefficient > 0.7). In addition, the small-word property (σ > 2) and the high correlation between gene expression (R = 0.29, p < 0.001) and general intelligence were determined for R2SNs. Furthermore, the results have also been repeated in the Brainnetome atlas. R2SNs provide a novel, reliable, and biologically plausible method to understand human morphological covariance based on sMRI.

Saturated impulsive control for synchronization of coupled delayed neural networks.

The paper focuses on the synchronization problem for a class of coupled neural networks with impulsive control, where the saturation structure of impulse action is fully considered. The coupled neural networks under consideration are subject to mixed delays including transmission delay and coupled delay. The sector condition in virtue of a new constraint of set inclusion is given for a addressed network, based on which a sufficient condition for exponential synchronization problem is obtained by replacing saturation nonlinearity with a dead-zone function. In the framework of saturated impulses, our results relying on the domain of attraction can still achieve the synchronization of coupled delayed neural networks. In addition, the estimating domain of attraction is proposed as large as possible by solving an optimization problem. Finally, a numerical simulation example is presented to demonstrate the effectiveness of the proposed results.

Quantitative Radiomic Features as New Biomarkers for Alzheimer's Disease: An Amyloid PET Study.

Growing evidence indicates that amyloid-beta (Aß) accumulation is one of the most common neurobiological biomarkers in Alzheimer's disease (AD). The primary aim of this study was to explore whether the radiomic features of Aß positron emission tomography (PET) images are used as predictors and provide a neurobiological foundation for AD. The radiomics features of Aß PET imaging of each brain region of the Brainnetome Atlas were computed for classification and prediction using a support vector machine model. The results showed that the area under the receiver operating characteristic curve (AUC) was 0.93 for distinguishing AD (N = 291) from normal control (NC; N = 334). Additionally, the AUC was 0.83 for the prediction of mild cognitive impairment (MCI) converting (N = 88) (vs. no conversion, N = 100) to AD. In the MCI and AD groups, the systemic analysis demonstrated that the classification outputs were significantly associated with clinical measures (apolipoprotein E genotype, polygenic risk scores, polygenic hazard scores, cerebrospinal fluid Aß, and Tau, cognitive ability score, the conversion time for progressive MCI subjects and cognitive changes). These findings provide evidence that the radiomic features of Aß PET images can serve as new biomarkers for clinical applications in AD/MCI, further providing evidence for predicting whether MCI subjects will convert to AD.

Resistance Trends of Klebsiella pneumoniae Causing Urinary Tract Infections in Chongqing, 2011-2019.

PURPOSE: To analyze the characteristics and trends of drug resistance for Klebsiella pneumoniae (K. pneumoniae), isolated from urinary tract infections (UTIs), to common antibiotics used in clinics. METHODS: This retrospective study was conducted in a teaching hospital in Chongqing from 2011 to 2019. Laboratory data of isolated bacteria were collected and analyzed. RESULTS: Among the 17,966 non-repetitive strains isolated from the urine sample, a total of 1543 K. pneumoniae isolates were identified, with an isolation frequency secondary only to Escherichia coli (E. coli) and there was a peak in the K. pneumoniae isolates in the year 2013. During the period, the rate of extended-spectrum ß-lactamase (ESBL)-producing K. pneumoniae fell from 48.4% in 2011 to 32.9% in 2019, and a marked jump of resistance was seen in carbapenems from 2.2% to 18.0%. The peak of carbapenem resistance rate (22.6%) to K. pneumoniae was observed in 2017 along with a low ESBL-producing rate (30.9%). Piperacillin/tazobactam and cefepime resistance levels went up from 4.4% to 25.7% and from 18.2% to 30.5%, respectively. Moreover, the K. pneumoniae isolates resistance rate to carbapenems and amikacin gradually grew up, showing their peaks in 2017, and then dropped year by year. However, ceftazidime and aztreonam resistance levels were relatively stable, fluctuating between 21.8% and 35.6%, 32.2% and 39.4%, respectively. CONCLUSION: There is a significant upward tendency in carbapenem resistance rate and a downward tendency in ESBL-production rate in K. pneumoniae isolates from UTIs, and continuous surveillance is necessary in the future.

Deep multispectral image registration network.

Multispectral imaging (MSI) of the ocular fundus provides a sequence of narrow-band images to show the different depths in the retina and choroid. One challenge in analyzing MSI images comes from the image-to-image spatial misalignment, which occurs because the acquisition time of eye MSI images is commonly longer than the natural time scale of the eye's saccadic movement. It is necessary to align images because ophthalmologists usually overlay two of the images to analyze specific features when analyzing MSI images. In this paper, we propose a weakly supervised MSI image registration network, called MSI-R-NET, for multispectral fundus image registration. Compared to other deep-learning-based registration methods, MSI-R-NET utilizes the blood vessel segmentation label to provide spatial correspondence. In addition, we employ a feature equilibrium module to connect the aggregating layers better, and propose a multiresolution auto-context structure to adapt the registration task. In the testing stage, given a new pair of MSI images, the trained model can predict the pixelwise spatial correspondence without labeled blood vessel information. The experimental results demonstrate that the proposed segmentation-driven registration method is highly accurate.

A Genome-Wide RNAi Screen for Enhancers of a Germline Tumor Phenotype Caused by Elevated GLP-1/Notch Signaling in Caenorhabditis elegans.

Stem cells are tightly controlled in vivo Both the balance between self-renewal and differentiation and the rate of proliferation are often regulated by multiple factors. The Caenorhabditis elegans hermaphrodite germ line provides a simple and accessible system for studying stem cells in vivo In this system, GLP-1/Notch activity prevents the differentiation of distal germ cells in response to ligand production from the nearby distal tip cell, thereby supporting a stem cell pool. However, a delay in germline development relative to somatic gonad development can cause a pool of undifferentiated germ cells to persist in response to alternate Notch ligands expressed in the proximal somatic gonad. This pool of undifferentiated germ cells forms a proximal tumor that, in adulthood, blocks the oviduct. This type of "latent niche"-driven proximal tumor is highly penetrant in worms bearing the temperature-sensitive weak gain-of-function mutation glp-1(ar202) at the restrictive temperature. At the permissive temperature, few worms develop tumors. Nevertheless, several interventions elevate the penetrance of proximal tumor formation at the permissive temperature, including reduced insulin signaling or the ablation of distal-most sheath cells. To systematically identify genetic perturbations that enhance proximal tumor formation, we sought genes that, upon RNAi depletion, elevate the percentage of worms bearing proximal germline tumors in glp-1(ar202) at the permissive temperature. We identified 43 genes representing a variety of functional classes, the most enriched of which is "translation". Some of these genes also influence the distal germ line, and some are conserved genes for which genetic interactions with Notch were not previously known in this system.

Myosin light chain kinase inhibitor ML7 improves vascular endothelial dysfunction and permeability via the mitogen-activated protein kinase pathway in a rabbit model of atherosclerosis.

Endothelial dysfunction (ED) and hyperpermeability are considered as the initiating steps in early atherosclerosis. Phosphorylation of myosin light chain (MLC) is key to cause vascular hyperpermeability via endothelial cell contraction. However, it is unclear whether MLC phosphorylation can also regulate the balance between contraction and relaxation of endothelial cells, thereby affecting endothelium-dependent diastolic function and leading to ED. The present study investigated relationships between ED and MLC phosphorylation and underlying mechanisms. Twenty-four male New Zealand white rabbits were randomly divided into three groups: control, AS, and ML7 (MLCK inhibitor) groups, and fed with normal diet, high-fat diet (HFD), and HFD plus oral ML7 (1 mg/kg daily) respectively. HFD-fed rabbits showed typical atheromatous lesions and endothelial hyperpermeability, and these lesions could be partly reversed following ML7 therapy. Western blotting revealed significant increased expression of myosin light chain kinase (MLCK) and phosphorylation of MLC, JNK, and ERK in the arterial wall of rabbits in the AS group compared with those of the control group (p < 0.05), whereas the ML7 group showed markedly decreased levels of these proteins compared with the AS group (p < 0.05). The endothelium-dependent relaxation rate was significantly reduced both in vitro and in vivo in AS group, and was improved using ML7 therapy. Taken together, these results indicate that MLCK expression and subsequent MLC phosphorylation increase vascular endothelial permeability and endothelium-dependent diastolic dysfunction by promoting endothelial cell contraction, which may be initiated by the activation of the MAP/ERK (MEK) and MAP/JNK (MEK) pathways.

Independent and reproducible hippocampal radiomic biomarkers for multisite Alzheimer's disease: diagnosis, longitudinal progress and biological basis.

Hippocampal morphological change is one of the main hallmarks of Alzheimer's disease (AD). However, whether hippocampal radiomic features are robust as predictors of progression from mild cognitive impairment (MCI) to AD dementia and whether these features provide any neurobiological foundation remains unclear. The primary aim of this study was to verify whether hippocampal radiomic features can serve as robust magnetic resonance imaging (MRI) markers for AD. Multivariate classifier-based support vector machine (SVM) analysis provided individual-level predictions for distinguishing AD patients (n = 261) from normal controls (NCs; n = 231) with an accuracy of 88.21% and intersite cross-validation. Further analyses of a large, independent the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset (n = 1228) reinforced these findings. In MCI groups, a systemic analysis demonstrated that the identified features were significantly associated with clinical features (e.g., apolipoprotein E (APOE) genotype, polygenic risk scores, cerebrospinal fluid (CSF) Aß, CSF Tau), and longitudinal changes in cognition ability; more importantly, the radiomic features had a consistently altered pattern with changes in the MMSE scores over 5 years of follow-up. These comprehensive results suggest that hippocampal radiomic features can serve as robust biomarkers for clinical application in AD/MCI, and further provide evidence for predicting whether an MCI subject would convert to AD based on the radiomics of the hippocampus. The results of this study are expected to have a substantial impact on the early diagnosis of AD/MCI.

Radiomic Features of Hippocampal Subregions in Alzheimer's Disease and Amnestic Mild Cognitive Impairment.

Alzheimer's disease (AD) is characterized by progressive dementia, especially in episodic memory, and amnestic mild cognitive impairment (aMCI) is associated with a high risk of developing AD. Hippocampal atrophy/shape changes are believed to be the most robust magnetic resonance imaging (MRI) markers for AD and aMCI. Radiomics, a method of texture analysis, can quantitatively examine a large set of features and has previously been successfully applied to evaluate imaging biomarkers for AD. To test whether radiomic features in the hippocampus can be employed for early classification of AD and aMCI, 1692 features from the caudal and head parts of the bilateral hippocampus were extracted from 38 AD patients, 33 aMCI patients and 45 normal controls (NCs). One way analysis of variance (ANOVA) showed that 111 features exhibited statistically significant group differences (P < 0.01, Bonferroni corrected). Among these features, 98 were significantly correlated with Mini-Mental State Examination (MMSE) scores in AD and aMCI subjects (P < 0.01). The support vector machine (SVM) model demonstrated that radiomic features allowed us to distinguish AD from NC with an accuracy of 86.75% (specificity = 88.89% and sensitivity = 84.21%) and an area under curve (AUC) of 0.93. In conclusion, these findings provide evidence showing that radiomic features are beneficial in detecting early cognitive decline, and SVM classification analysis provides encouraging evidence for using hippocampal radiomic features as a potential biomarker for clinical applications in AD.

Study of altered functional connectivity in individuals at risk for Alzheimer's Disease.

BACKGROUND: Mild Cognitive Impairment (MCI) has been considered to have a high risk in converting into Alzheimer's Disease (AD). Previous studies showed that AD was associated with changes in resting-state networks (RSNs). However, few studies have evaluated the altered functional connectivity in early mild cognitive impairment (EMCI) and late mild cognitive impairment (LMCI). OBJECTIVE: The aim of this work was to evaluate the impaired network functional connectivity with the disease progression. METHODS: In this paper, we evaluated the impaired function connectivity with the progression of disease based on a priori defined 246 regions of interest based on Brainnetome Atlas. Connectivity analysis based on three levels (node integrity, intra-network, and inter-network) was conducted. RESULTS: Altered function connectivity was detected in several RSNs. These results provided insights into the dysfunction of more RSNs accompany the progression of AD. We also found that one brain region may belong to multiple RSNs and contribute to achieving different network function. CONCLUSIONS: The aberrant intra- and inter-network dysfunctions might be potential biomarkers or predictors of MCI and AD progression and provide new insight into the pathophysiology of these diseases.