Altered Patterns of Phase Position Connectivity in Default Mode Subnetwork of Subjective Cognitive Decline and Amnestic Mild Cognitive Impairment

Research related to the diagnosis of prostate cancer based on machine learning medical images: A review

BACKGROUND

Prostate cancer is currently the second most prevalent cancer among men. Accurate diagnosis of prostate cancer can provide effective treatment for patients and greatly reduce mortality. The current medical imaging tools for screening prostate cancer are mainly MRI, CT and ultrasound. In the past 20 years, these medical imaging methods have made great progress with machine learning, especially the rise of deep learning has led to a wider application of artificial intelligence in the use of image-assisted diagnosis of prostate cancer.

METHOD

This review collected medical image processing methods, prostate and prostate cancer on MR images, CT images, and ultrasound images through search engines such as web of science, PubMed, and Google Scholar, including image pre-processing methods, segmentation of prostate gland on medical images, registration between prostate gland on different modal images, detection of prostate cancer lesions on the prostate.

CONCLUSION

Through these collated papers, it is found that the current research on the diagnosis and staging of prostate cancer using machine learning and deep learning is in its infancy, and most of the existing studies are on the diagnosis of prostate cancer and classification of lesions, and the accuracy is low, with the best results having an accuracy of less than 0.95. There are fewer studies on staging. The research is mainly focused on MR images and much less on CT images, ultrasound images.

DISCUSSION

Machine learning and deep learning combined with medical imaging have a broad application prospect for the diagnosis and staging of prostate cancer, but the research in this area still has more room for development.

Altered functional hubs and connectivity in type 2 diabetes mellitus with and without mild cognitive impairment

Cognitive impairment in type 2 diabetes mellitus (T2DM) is associated with functional and structural abnormalities of brain networks, especially the damage to hub nodes in networks. This study explored the abnormal hub nodes of brain functional networks in patients with T2DM under different cognitive states. Sixty-five patients with T2DM and 34 healthy controls (HCs) underwent neuropsychological assessment. Then, degree centrality (DC) analysis and seed-based functional connectivity (FC) analysis were performed to identify the abnormal hub nodes and the FC patterns of these hubs in T2DM patients with mild cognitive impairment (MCI) (DMCI group, N = 31) and without MCI (DMCN group, N = 34). Correlation analyzes examined the relationship between abnormal DC and FC and clinical/cognitive variables. Compared with HCs, both T2DM groups showed decreased DC values in the visual cortex, and the T2DM patients with MCI (DMCI) showed more extensive alterations in the right parahippocampal gyrus (PHG), bilateral posterior cingulate cortex (PCC), and left superior frontal gyrus (SFG) regions than T2DM patients with normal cognitive function. Seed-based FC analysis of PHG and PCC nodes showed that functional disconnection mainly occurred in visual and memory connectivity in patients with DMCI. Multiple abnormal DC values correlated with neuropsychological tests in patients with T2DM. In conclusion, this study found that the DMCI group displayed more extensive alterations in hub nodes and FC in vision and memory-related brain regions, suggesting that visual-related regions dysfunctions and disconnection may be involved in the neuropathology of visuospatial function impairment in patients with DMCI.

Associations between disrupted functional brain network topology and cognitive impairment in patients with rectal cancer during chemotherapy

Introduction

Cognitive impairment has been identified in patients with non-central nervous system cancer received chemotherapy. Chemotherapy-induced changes in the brain are considered as the possible causes of the cognitive deficits of patients. This study aimed to explore chemotherapy-related functional brain changes and cognitive impairment in rectal cancer (RC) patients who had just finished chemotherapy treatment.

Methods

In this study, RC patients after chemotherapy (on the day patients received the last dose of chemotherapy) (n=30) and matched healthy controls (HCs) (n=30) underwent cognitive assessments, structural magnetic resonance imaging (MRI) and resting-state functional MRI. The functional brain networks were constructed by thresholding the partial correlation matrices of 90 brain regions in the Anatomical Automatic Labeling template and the topologic properties were evaluated by graph theory analysis. Moreover, correlations between altered topological measures and scores of cognitive scales were explored in the patient group.

Results

Compared with HCs, RC patients had lower scores of cognitive scales. The functional brain network had preserved small-world topological features but with a tendency towards higher path length in the whole network. In addition, patients had decreased nodal global efficiency (E_glo(i)) in the left superior frontal gyrus (dorsolateral), superior frontal gyrus (orbital part), inferior frontal gyrus (opercular part), inferior frontal gyrus (triangular part) and right inferior frontal gyrus (triangular part). Moreover, values of E_glo(i) in the superior and inferior frontal gyrus were positively associated with cognitive function in the patient group.

Conclusion

These results suggested that cognitive impairment was associated with disruptions of the topological organization in functional brain networks of RC patients who had just finished chemotherapy, which provided new insights into the pathophysiology underlying acute effects of chemotherapy on cognitive function.

Functional Neural Alterations in Pathological Internet Use: A Meta-Analysis of Neuroimaging Studies

Previous resting-state functional MRI (fMRI) studies found spontaneous neural activity in the brains of Pathological Internet Use (PIU) subjects. However, the findings were inconsistent in studies using different neuroimaging analyses. This meta-analytic study aimed to identify a common pattern of altered brain activity from different studies. Resting-state fMRI studies, based on whole-brain analysis methods published before July 1, 2021, were searched in multiple databases (PubMed, EMBASE, MEDLINE, and Web of Science). A voxel-based signed differential mapping (SDM) method was used to clarify brain regions, which showed anomalous activity in PIU subjects compared with healthy controls (HCs). Ten eligible publications consisting of 306 PIU subjects and 314 HCs were included in the SDM meta-analysis. Compared with HCs, subjects with PIU showed increased spontaneous neural functional activity in the left temporal pole of the superior temporal cortex, left amygdala, bilateral median cingulate cortex, and right insula. Meanwhile, a decreased spontaneous neural activity was identified in the left dorsolateral superior frontal gyrus and right middle frontal gyrus in the subjects with PIU. These abnormal brain regions are associated with cognitive executive control and emotional regulation. The consistent changes under different functional brain imaging indicators found in our study may provide important targets for the future diagnosis and intervention of PIU.

Systematic Review Registration:www.crd.york.ac.uk/PROSPERO, identifier: CRD42021258119.

Brain network hierarchy reorganization in Alzheimer's disease: A resting‐state functional magnetic resonance imaging study

Hierarchy is a fundamental organizational principle of the human brain network. Whether and how the network hierarchy changes in Alzheimer's disease (AD) remains unclear. To explore brain network hierarchy alterations in AD and their clinical relevance. Forty‐nine healthy controls (HCs), 49 patients with mild cognitive impairment (MCI), and 49 patients with AD were included. The brain network hierarchy of each group was depicted by connectome gradient analyses. We assessed the network hierarchy changes by comparing the gradient values in each network across the AD, MCI, and HC groups. Whole‐brain voxel‐level gradient values were compared across the AD, MCI, and HC groups to identify abnormal brain regions. Finally, we examined the relationships between altered gradient values and clinical features. In the secondary gradient, the posterior default mode network (DMN) gradient values decreased significantly in patients with AD compared with HCs. Regionally, compared with HCs, both MCI and AD groups showed that most of the brain regions with increased gradient values were located in anterior DMN, while most of the brain regions with decreased gradient values were located in posterior DMN. The decrease of gradients in the left middle occipital gyrus was associated with better logical memory performance. The increase of gradients in the right middle frontal gyrus was associated with lower rates of dementia. The network hierarchy changed characteristically in patients with AD and was closely related to memory function and disease severity. These results provide a novel view for further understanding the underlying neuro‐mechanisms of AD.

Influence and interaction of resting state functional magnetic resonance and tryptophan hydroxylase-2 methylation on short-term antidepressant drug response

BACKGROUND

Most antidepressants have been developed on the basis of the monoamine deficiency hypothesis of depression, in which neuronal serotonin (5-HT) plays a key role. 5-HT biosynthesis is regulated by the rate-limiting enzyme tryptophan hydroxylase-2 (TPH2). TPH2 methylation is correlated with antidepressant effects. Resting-state functional MRI (rs-fMRI) is applied for detecting abnormal brain functional activity in patients with different antidepressant effects. We will investigate the effect of the interaction between rs-fMRI and TPH2 DNA methylation on the early antidepressant effects.

METHODS

A total of 300 patients with major depressive disorder (MDD) and 100 healthy controls (HCs) were enrolled, of which 60 patients with MDD were subjected to rs-fMRI. Antidepressant responses was assessed by a 50% reduction in 17-item Hamilton Rating Scale for Depression (HAMD-17) scores at baseline and after two weeks of medication. The RESTPlus software in MATLAB was used to analyze the rs-fMRI data. The amplitude of low-frequency fluctuation (ALFF), regional homogeneity (ReHo), fractional ALFF (fALFF), and functional connectivity (FC) were used, and the above results were used as regions of interest (ROIs) to extract the average value of brain ROIs regions in the RESTPlus software. Generalized linear model analysis was performed to analyze the association between abnormal activity found in rs-fMRI and the effect of TPH2 DNA methylation on antidepressant responses.

RESULTS

Two hundred ninety-one patients with MDD and 100 HCs were included in the methylation statistical analysis, of which 57 patients were included in the further rs-fMRI analysis (3 patients were excluded due to excessive head movement). 57 patients were divided into the responder group (n = 36) and the non-responder group (n = 21). Rs-fMRI results showed that the ALFF of the left inferior frontal gyrus (IFG) was significantly different between the two groups. The results showed that TPH2-1-43 methylation interacted with ALFF of left IFG to affect the antidepressant responses (p = 0.041, false discovery rate (FDR) corrected p = 0.149).

CONCLUSIONS

Our study demonstrated that the differences in the ALFF of left IFG between the two groups and its association with TPH2 methylation affect short-term antidepressant drug responses.

Detecting Biomarkers of Alzheimer's Disease Based on Multi-constrained Uncertainty-Aware Adaptive Sparse Multi-view Canonical Correlation Analysis

Image genetics mainly explores the pathogenesis of Alzheimer's disease (AD) by studying the relationship between genetic data (such as SNP, gene expression data, and DNA methylation) and imaging data (such as structural MRI (sMRI), fMRI, and PET). Most of the existing research on brain imaging genomics uses two-way or three-way bi-multivariate methods to explore the correlation analysis between genes and brain imaging. However, many of these methods are still affected by the gradient domination or cannot take into account the effect of feature redundancy on the results, so that the typical correlation coefficient and program running speed are not significantly improved. In order to solve the above problems, this paper proposes a multi-constrained uncertainty-aware adaptive sparse multi-view canonical correlation analysis method (MC-unAdaSMCCA) to explore associations among SNPs, gene expression data, and sMRI; that is, based on traditional unAdaSMCCA, orthogonal constraints are imposed on the weights of the three data features through linear programming, which can reduce the redundancy of feature weights to improve the correlation between the data and reduce the complexity of the algorithm to significantly speed up the running speed of the program. Three adaptive sparse multi-view canonical correlation analysis methods are used as benchmarks to evaluate the difference between real neuroimaging data and synthetic data. Compared with the other three methods, our proposed method has obtained better or comparable typical correlation coefficients and typical weights. Moreover, the following experimental results show that the MC-unAdaSMCCA method cannot only identify biomarkers related to AD and mild cognitive impairment (MCI), but also has a strong ability to resist noise and process high-dimensional data. Therefore, our proposed method provides a reliable approach to multi-modal imaging genetic researches.

Functional MRI-Specific Alterations in Salience Network in Mild Cognitive Impairment: An ALE Meta-Analysis

Background Mild cognitive impairment (MCI) is an intermediate stage between normal aging and dementia. Amnestic MCI (aMCI) and non-amnestic MCI are the two subtypes of MCI with the former having a higher risk for progressing to Alzheimer's disease (AD). Compared with healthy elderly adults, individuals with MCI have specific functional alterations in the salience network (SN). However, no consistent results are documenting these changes. This meta-analysis aimed to investigate the specific functional alterations in the SN in MCI and aMCI. Methods: We systematically searched PubMed, Embase, and Web of Science for scientific neuroimaging literature based on three research methods, namely, functional connectivity (FC), regional homogeneity (ReHo), and the amplitude of low-frequency fluctuation or fractional amplitude of low-frequency fluctuation (ALFF/fALFF). Then, we conducted the coordinate-based meta-analysis by using the activation likelihood estimation algorithm. Results: In total, 30 functional neuroimaging studies were included. After extracting the data and analyzing it, we obtained specific changes in some brain regions in the SN including decreased ALFF/fALFF in the left superior temporal gyrus, the insula, the precentral gyrus, and the precuneus in MCI and aMCI; increased FC in the thalamus, the caudate, the superior temporal gyrus, the insula, and the cingulate gyrus in MCI; and decreased ReHo in the anterior cingulate gyrus in aMCI. In addition, as to FC, interactions of the SN with other networks including the default mode network and the executive control network were also observed mainly in the middle frontal gyrus and superior frontal gyrus in MCI and inferior frontal gyrus in aMCI. Conclusions: Specific functional alternations in the SN and interactions of the SN with other networks in MCI could be useful as potential imaging biomarkers for MCI or aMCI. Meanwhile, it provided a new insight in predicting the progression of health to MCI or aMCI and novel targets for proper intervention to delay the progression. Systematic Review Registration: [PROSPERO], identifier [No. CRD42020216259].

FFA-DMRI: A Network Based on Feature Fusion and Attention Mechanism for Brain MRI Denoising

Magnetic Resonance Imaging (MRI) is an indispensable tool in the diagnosis of brain diseases due to painlessness and safety. Nevertheless, Rician noise is inevitably injected during the image acquisition process, which leads to poor observation and interferes with the treatment. Owing to the complexity of Rician noise, using the elimination method of Gaussian to remove it does not perform well. Therefore, the feature fusion and attention network (FFA-DMRI) is proposed to separate noise from observed MRI. Inspired by the attention-guided CNN network (ADNet) and Convolutional block attention module (CBAM), a spatial attention mechanism has been specially designed to obtain the area of interest in MRI. Furthermore, the feature fusion block concatenates local with global information, which makes full use of the multilevel structure and boosts the expressive ability of network. The comprehensive experiments on Alzheimer's disease neuroimaging initiative dataset (ADNI) have demonstrated high effectiveness of FFA-DMRI with maintaining the crucial brain details. Moreover, in terms of visual inspections, the denoising results are also consistent with human perception.