Diagnostic Efficacy of Voxel-Mirrored Homotopic Connectivity in Vascular Dementia as Compared to Alzheimer's Related Neurodegenerative Diseases-A Resting State fMRI Study

Integrating Demographics and Imaging Features for Various Stages of Dementia Classification: Feed Forward Neural Network Multi-Class Approach

BACKGROUND

MRI magnetization-prepared rapid acquisition (MPRAGE) is an easily available imaging modality for dementia diagnosis. Previous studies suggested that volumetric analysis plays a crucial role in various stages of dementia classification. In this study, volumetry, radiomics and demographics were integrated as inputs to develop an artificial intelligence model for various stages, including Alzheimer's disease (AD), mild cognitive decline (MCI) and cognitive normal (CN) dementia classifications.

METHOD

The Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset was separated into training and testing groups, and the Open Access Series of Imaging Studies (OASIS) dataset was used as the second testing group. The MRI MPRAGE image was reoriented via statistical parametric mapping (SPM12). Freesurfer was employed for brain segmentation, and 45 regional brain volumes were retrieved. The 3D Slicer software was employed for 107 radiomics feature extractions from within the whole brain. Data on patient demographics were collected from the datasets. The feed-forward neural network (FFNN) and the other most common artificial intelligence algorithms, including support vector machine (SVM), ensemble classifier (EC) and decision tree (DT), were used to build the models using various features.

RESULTS

The integration of brain regional volumes, radiomics and patient demographics attained the highest overall accuracy at 76.57% and 73.14% in ADNI and OASIS testing, respectively. The subclass accuracies in MCI, AD and CN were 78.29%, 89.71% and 85.14%, respectively, in ADNI testing, as well as 74.86%, 88% and 83.43% in OASIS testing. Balanced sensitivity and specificity were obtained for all subclass classifications in MCI, AD and CN.

CONCLUSION

The FFNN yielded good overall accuracy for MCI, AD and CN categorization, with balanced subclass accuracy, sensitivity and specificity. The proposed FFNN model is simple, and it may support the triage of patients for further confirmation of the diagnosis.

Self-supervised multimodal learning for group inferences from MRI data: Discovering disorder-relevant brain regions and multimodal links

In recent years, deep learning approaches have gained significant attention in predicting brain disorders using neuroimaging data. However, conventional methods often rely on single-modality data and supervised models, which provide only a limited perspective of the intricacies of the highly complex brain. Moreover, the scarcity of accurate diagnostic labels in clinical settings hinders the applicability of the supervised models. To address these limitations, we propose a novel self-supervised framework for extracting multiple representations from multimodal neuroimaging data to enhance group inferences and enable analysis without resorting to labeled data during pre-training. Our approach leverages Deep InfoMax (DIM), a self-supervised methodology renowned for its efficacy in learning representations by estimating mutual information without the need for explicit labels. While DIM has shown promise in predicting brain disorders from single-modality MRI data, its potential for multimodal data remains untapped. This work extends DIM to multimodal neuroimaging data, allowing us to identify disorder-relevant brain regions and explore multimodal links. We present compelling evidence of the efficacy of our multimodal DIM analysis in uncovering disorder-relevant brain regions, including the hippocampus, caudate, insula, - and multimodal links with the thalamus, precuneus, and subthalamus hypothalamus. Our self-supervised representations demonstrate promising capabilities in predicting the presence of brain disorders across a spectrum of Alzheimer's phenotypes. Comparative evaluations against state-of-the-art unsupervised methods based on autoencoders, canonical correlation analysis, and supervised models highlight the superiority of our proposed method in achieving improved classification performance, capturing joint information, and interpretability capabilities. The computational efficiency of the decoder-free strategy enhances its practical utility, as it saves compute resources without compromising performance. This work offers a significant step forward in addressing the challenge of understanding multimodal links in complex brain disorders, with potential applications in neuroimaging research and clinical diagnosis.

The Use of Diffusion Kurtosis Imaging for the Differential Diagnosis of Alzheimer's Disease Spectrum

Structural and diffusion kurtosis imaging (DKI) can be used to assess hippocampal macrostructural and microstructural alterations respectively, in Alzheimer's disease (AD) spectrum, spanning from subjective cognitive decline (SCD) to mild cognitive impairment (MCI) and AD. In this study, we explored the diagnostic performance of structural imaging and DKI of the hippocampus in the AD spectrum. Eleven SCD, thirty-seven MCI, sixteen AD, and nineteen age- and sex-matched normal controls (NCs) were included. Bilateral hippocampal volume, mean diffusivity (MD), and mean kurtosis (MK) were obtained. We detected that in AD vs. NCs, the right hippocampal volume showed the most prominent AUC value (AUC = 0.977); in MCI vs. NCs, the right hippocampal MD was the most sensitive discriminator (AUC = 0.819); in SCD vs. NCs, the left hippocampal MK was the most sensitive biomarker (AUC = 0.775). These findings suggest that, in the predementia stage (SCD and MCI), hippocampal microstructural changes are predominant, and the best discriminators are microstructural measurements (left hippocampal MK for SCD and right hippocampal MD for MCI); while in the dementia stage (AD), hippocampal macrostructural alterations are superior, and the best indicator is the macrostructural index (right hippocampal volume).

Progressive Voxel-Wise Homotopic Connectivity from childhood to adulthood: Age-related functional asymmetry in resting-state functional magnetic resonance imaging

Homotopic connectivity during resting state has been proposed as a risk marker for neurologic and psychiatric conditions, but a precise characterization of its trajectory through development is currently lacking. Voxel-Mirrored Homotopic Connectivity (VMHC) was evaluated in a sample of 85 neurotypical individuals aged 7-18 years. VMHC associations with age, handedness, sex, and motion were explored at the voxel-wise level. VMHC correlates were also explored within 14 functional networks. Primary and secondary outcomes were repeated in a sample of 107 adults aged 21-50 years. In adults, VMHC was negatively correlated with age only in the posterior insula (false discovery rate p < .05, >30-voxel clusters), while a distributed effect among the medial axis was observed in minors. Four out of 14 considered networks showed significant negative correlations between VMHC and age in minors (basal ganglia r = -.280, p = .010; anterior salience r = -.245, p = .024; language r = -.222, p = .041; primary visual r = -.257, p = .017), but not adults. In minors, a positive effect of motion on VMHC was observed only in the putamen. Sex did not significantly influence age effects on VMHC. The current study showed a specific decrease in VMHC for minors as a function of age, but not adults, supporting the notion that interhemispheric interactions can shape late neurodevelopment.

Centrality and interhemispheric coordination are related to different clinical/behavioral factors in attention deficit/hyperactivity disorder: a resting-state fMRI study

Eigenvector-Centrality (EC) has shown promising results in the field of Psychiatry, with early results also pertaining to ADHD. Parallel efforts have focused on the description of aberrant interhemispheric coordination in ADHD, as measured by Voxel-Mirrored-Homotopic-Connectivity (VMHC), with early evidence of altered Resting-State fMRI. A sample was collected from the ADHD200-NYU initiative: 86 neurotypicals and 89 participants with ADHD between 7 and 18 years old were included after quality control for motion. After preprocessing, voxel-wise EC and VMHC values between diagnostic groups were compared, and network-level values from 15 functional networks extracted. Age, ADHD severity (Connor's Parent Rating-Scale), IQ (Wechsler-Abbreviated-Scale), and right-hand dominance were correlated with EC/VMHC values in the whole sample and within groups, both at the voxel-wise and network-level. Motion was controlled by censoring time-points with Framewise-Displacement > 0.5 mm, as well as controlling for group differences in mean Framewise-Displacement values. EC was significantly higher in ADHD compared to neurotypicals in the left inferior Frontal lobe, Lingual gyri, Peri-Calcarine cortex, superior and middle Occipital lobes, right inferior Occipital lobe, right middle Temporal gyrus, Fusiform gyri, bilateral Cuneus, right Precuneus, and Cerebellum (FDR-corrected-p = 0.05). No differences were observed between groups in voxel-wise VMHC. EC was positively correlated with ADHD severity scores at the network level (at p-value < 0.01, Inattentive: Cerebellum rho = 0.273; Hyper/Impulsive: High-Visual Network rho = 0.242, Cerebellum rho = 0.273; Global Index Severity: High-Visual Network rho = 0.241, Cerebellum rho = 0.293). No differences were observed between groups for motion (p = 0.443). While EC was more related to ADHD psychopathology, VMHC was consistently and negatively correlated with age across all networks.

Reduced homotopic interhemispheric connectivity in psychiatric disorders: evidence for both transdiagnostic and disorder specific features

There is considerable interest in the significance of structural and functional connections between the two brain hemispheres in terms of both normal function and in relation to psychiatric disorders. In recent years, many studies have used voxel mirrored homotopic connectivity analysis of resting state data to investigate the importance of connectivity between homotopic regions in the brain hemispheres in a range of neuropsychiatric disorders. The current review summarizes findings from these voxel mirrored homotopic connectivity studies in individuals with autism spectrum disorder, addiction, attention deficit hyperactivity disorder, anxiety and depression disorders, and schizophrenia, as well as disorders such as Alzheimer's disease, mild cognitive impairment, epilepsy, and insomnia. Overall, other than attention deficit hyperactivity disorder, studies across psychiatric disorders report decreased homotopic resting state functional connectivity in the default mode, attention, salience, sensorimotor, social cognition, visual recognition, primary visual processing, and reward networks, which are often associated with symptom severity and/or illness onset/duration. Decreased homotopic resting state functional connectivity may therefore represent a transdiagnostic marker for general psychopathology. In terms of disorder specificity, the extensive decreases in homotopic resting state functional connectivity in autism differ markedly from attention deficit hyperactivity disorder, despite both occurring during early childhood and showing extensive co-morbidity. A pattern of more posterior than anterior regions showing reductions in schizophrenia is also distinctive. Going forward, more studies are needed to elucidate the functions of these homotopic functional connections in both health and disorder and focusing on associations with general psychopathology, and not only on disorder specific symptoms.

Alterations in a cross-hemispheric circuit associates with novelty discrimination deficits in mouse models of neurodegeneration

A major pathological hallmark of neurodegenerative diseases, including Alzheimer's, is a significant reduction in the white matter connecting the two cerebral hemispheres, as well as in the correlated activity between anatomically corresponding bilateral brain areas. However, the underlying circuit mechanisms and the cognitive relevance of cross-hemispheric (CH) communication remain poorly understood. Here, we show that novelty discrimination behavior activates CH neurons and enhances homotopic synchronized neural oscillations in the visual cortex. CH neurons provide excitatory drive required for synchronous neural oscillations between hemispheres, and unilateral inhibition of the CH circuit is sufficient to impair synchronous oscillations and novelty discrimination behavior. In the 5XFAD and Tau P301S mouse models, CH communication is altered, and novelty discrimination is impaired. These data reveal a hitherto uncharacterized CH circuit in the visual cortex, establishing a causal link between this circuit and novelty discrimination behavior and highlighting its impairment in mouse models of neurodegeneration.

A Perspective: Challenges in Dementia Research

Although dementia is a common and devastating disease that has been studied intensely for more than 100 years, no effective disease modifying treatment has been found. At this impasse, new approaches are important. The purpose of this paper is to provide, in the context of current research, one clinician's perspective regarding important challenges in the field in the form of specific challenges. These challenges not only illustrate the scope of the problems inherent in finding treatments for dementia, but can also be specific targets to foster discussion, criticism and new research. One common theme is the need to transform research activities from small projects in individual laboratories/clinics to larger multinational projects, in which each clinician and researcher works as an integral part. This transformation will require collaboration between researchers, large corporations, regulatory/governmental authorities and the general population, as well as significant financial investments. However, the costs of transforming the approach are small in comparison with the cost of dementia.

Level of Amyloid-β (Aβ) Binding Leading to Differential Effects on Resting State Functional Connectivity in Major Brain Networks

Introduction: Amyloid-β protein (Aβ) is one of the biomarkers for Alzheimer’s disease (AD). The recent application of interhemispheric functional connectivity (IFC) in resting-state fMRI has been used as a non-invasive diagnostic tool for early dementia. In this study, we focused on the level of Aβ accumulated and its effects on the major functional networks, including default mode network (DMN), central executive network (CEN), salience network (SN), self-referential network (SRN) and sensory motor network (SMN). Methods: 58 participants (27 Hi Aβ (HiAmy) and 31 low Aβ (LowAmy)) and 25 healthy controls (HC) were recruited. [¹⁸F]flutemetamol PET/CT was performed for diseased groups, and MRI scanning was done for all participants. Voxel-by-voxel correlation analysis was done for both groups in all networks. Results: In HiAmy, IFC was reduced in all networks except SN. A negative correlation in DMN, CEN, SRN and SMN suggests high Aβ related to IFC reduction; However, a positive correlation in SN suggests high Aβ related to an increase in IFC. In LowAmy, IFC increased in CEN, SMN, SN and SRN. Positive correlation in all major brain networks. Conclusion: The level of Aβ accumulated demonstrated differential effects on IFC in various brain networks. As the treatment to reduce Aβ plaque deposition is available in the market, it may be an option for the HiAmy group to improve their IFC in major brain networks.