Association between Structural Connectivity and Generalized Cognitive Spectrum in Alzheimer's Disease

Toward diffusion tensor imaging as a biomarker in neurodegenerative diseases: technical considerations to optimize recordings and data processing

Neuroimaging biomarkers have shown high potential to map the disease processes in the application to neurodegenerative diseases (NDD), e.g., diffusion tensor imaging (DTI). For DTI, the implementation of a standardized scanning and analysis cascade in clinical trials has potential to be further optimized. Over the last few years, various approaches to improve DTI applications to NDD have been developed. The core issue of this review was to address considerations and limitations of DTI in NDD: we discuss suggestions for improvements of DTI applications to NDD. Based on this technical approach, a set of recommendations was proposed for a standardized DTI scan protocol and an analysis cascade of DTI data pre-and postprocessing and statistical analysis. In summary, considering advantages and limitations of the DTI in NDD we suggest improvements for a standardized framework for a DTI-based protocol to be applied to future imaging studies in NDD, towards the goal to proceed to establish DTI as a biomarker in clinical trials in neurodegeneration.

Impact of white matter hyperintensities on structural connectivity and cognition in cognitively intact ADNI participants

We used indirect brain mapping with virtual lesion tractography to test the hypothesis that the extent of white matter tract disconnection due to white matter hyperintensities (WMH) is associated with corresponding tract-specific cognitive performance decrements. To estimate tract disconnection, WMH masks were extracted from FLAIR MRI data of 481 cognitively intact participants in the Alzheimer's Disease Neuroimaging Initiative (ADNI) and used as regions of avoidance for fiber tracking in diffusion MRI data from 50 healthy young participants from the Human Connectome Project. Estimated tract disconnection in the right inferior fronto-occipital fasciculus, right frontal aslant tract, and right superior longitudinal fasciculus mediated the effects of WMH volume on executive function. Estimated tract disconnection in the left uncinate fasciculus mediated the effects of WMH volume on memory and in the right frontal aslant tract on language. In a subset of ADNI control participants with amyloid data, positive status increased the probability of periventricular WMH and moderated the relationship between WMH burden and tract disconnection in executive function performance.

Markov model combined with MR diffusion tensor imaging for predicting the onset of Alzheimer's disease

Alzheimer's disease (AD) affects cognition, behavior, and memory of brain. It causes 60-80% of dementia cases. Cross-sectional imaging investigations of AD show that magnetic resonance (MR) with diffusion tensor image (DTI)-detected lesion locations in AD patients are heterogeneous and distributed across the imaging area. This study suggested that Markov model (MM) combined with MR-DTI (MM + MR-DTI) was offered as a method for predicting the onset of AD. In 120 subjects (normal controls [NCs], amnestic mild cognitive impairment [aMCI] patients, and AD patients) from a discovery dataset and 122 subjects (NCs, aMCI, and AD) from a replicated dataset, we used them to evaluate the white matter (WM) integrity and abnormalities. We did this by using automated fiber quantification, which allowed us to identify 20 central WM tracts. Point-wise alterations in WM tracts were shown using discovery and replication datasets. The statistical analysis revealed a substantial correlation between microstructural WM alterations and output in the patient groups and cognitive performance, suggesting that this may be a potential biomarker for AD. The MR-based classifier demonstrated the following performance levels for the basis classifiers, with DTI achieving the lowest performance. The following outcomes were seen in MM + MR-DTI using multimodal techniques when combining two modalities. Finally, a combination of every imaging method produced results with an accuracy of 98%, a specificity of 97%, and a sensitivity of 99%. In summary, DTI performs better when paired with structural MR, despite its relatively weak performance when used alone. These findings support the idea that WM modifications play a significant role in AD.

Diagnosis of Alzheimer's Disease using Structure Highlighting Key Slice Stacking and Transfer Learning

BACKGROUND

In recent years, two-dimensional convolutional neural network (2D CNN) have been widely used in the diagnosis of Alzheimer's disease (AD) based on structural magnetic resonance imaging (sMRI). However, due to the lack of targeted processing of the key slices of sMRI images, the classification performance of the CNN model needs to be improved.

PURPOSE

Therefore, in this paper, we propose a key slice processing technique called the structural highlighting key slice stacking (SHKSS) technique, and we apply it to a 2D transfer learning model for AD classification.

METHODS

Specifically, first, 3D MR images were preprocessed. Second, the 2D axial middle-layer image was extracted from the MR image as a key slice. Then, the image was normalized by intensity and mapped to the RGB space, and histogram specification was performed on the obtained RGB image to generate the final three-channel image. The final three-channel image was input into a pre-trained CNN model for AD classification. Finally, classification and generalization experiments were conducted to verify the validity of the proposed method.

RESULTS

The experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset show that our SHKSS method can effectively highlight the structural information in MRI slices. Compared with existing key slice processing techniques, our SHKSS method has an average accuracy improvement of at least 26% on the same test dataset, and it has better performance and generalization ability.

CONCLUSIONS

Our SHKSS method not only converts single-channel images into three-channel images to match the input requirements of the 2D transfer learning model but also highlights the structural information of MRI slices to improve the accuracy of AD diagnosis. This article is protected by copyright. All rights reserved.

A robust framework to investigate the reliability and stability of explainable artificial intelligence markers of Mild Cognitive Impairment and Alzheimer's Disease

In clinical practice, several standardized neuropsychological tests have been designed to assess and monitor the neurocognitive status of patients with neurodegenerative diseases such as Alzheimer's disease. Important research efforts have been devoted so far to the development of multivariate machine learning models that combine the different test indexes to predict the diagnosis and prognosis of cognitive decline with remarkable results. However, less attention has been devoted to the explainability of these models. In this work, we present a robust framework to (i) perform a threefold classification between healthy control subjects, individuals with cognitive impairment, and subjects with dementia using different cognitive indexes and (ii) analyze the variability of the explainability SHAP values associated with the decisions taken by the predictive models. We demonstrate that the SHAP values can accurately characterize how each index affects a patient's cognitive status. Furthermore, we show that a longitudinal analysis of SHAP values can provide effective information on Alzheimer's disease progression.

Accurate Evaluation of Feature Contributions for Sentinel Lymph Node Status Classification in Breast Cancer

The current guidelines recommend the sentinel lymph node biopsy to evaluate the lymph node involvement for breast cancer patients with clinically negative lymph nodes on clinical or radiological examination. Machine learning (ML) models have significantly improved the prediction of lymph nodes status based on clinical features, thus avoiding expensive, time-consuming and invasive procedures. However, the classification of sentinel lymph node status represents a typical example of an unbalanced classification problem. In this work, we developed a ML framework to explore the effects of unbalanced populations on the performance and stability of feature ranking for sentinel lymph node status classification in breast cancer. Our results indicate state-of-the-art AUC (Area under the Receiver Operating Characteristic curve) values on a hold-out set (67%) while providing particularly stable features related to tumor size, histological subtype and estrogen receptor expression, which should therefore be considered as potential biomarkers.

Plasma phosphorylated-tau181 levels reflect white matter microstructural changes across Alzheimer's disease progression

Alzheimer's Disease (AD) is characterized by cognitive impairments that hinder daily activities and lead to personal and behavioral problems. Plasma hyperphosphorylated tau protein at threonine 181 (p-tau181) has recently emerged as a new sensitive tool for the diagnosis of AD patients. We herein investigated the association of plasma P-tau181 and white matter (WM) microstructural changes in AD. We obtained data from a large prospective cohort of elderly individuals participating in the Alzheimer's Disease Neuroimaging Initiative (ADNI), which included baseline measurements of plasma P-tau181 and imaging findings. A subset of 41 patients with AD, 119 patients with mild cognitive impairments (MCI), and 43 healthy controls (HC) was included in the study, all of whom had baseline blood P-tau181 levels and had also undergone Diffusion Tensor Imaging. The analysis revealed that the plasma level of P-tau181 has a positive correlation with changes in Mean Diffusivity (MD), Radial Diffusivity (RD), and Axial Diffusivity (AxD), but a negative with Fractional Anisotropy (FA) parameters in WM regions of all participants. There is also a significant association between WM microstructural changes in different regions and P-tau181 plasma measurements within each MCI, HC, and AD group. In conclusion, our findings clarified that plasma P-tau181 levels are associated with changes in WM integrity in AD. P-tau181 could improve the accuracy of diagnostic procedures and support the application of blood-based biomarkers to diagnose WM neurodegeneration. Longitudinal clinical studies are also needed to demonstrate the efficacy of the P-tau181 biomarker and predict its role in structural changes.

The Road to Personalized Medicine in Alzheimer’s Disease: The Use of Artificial Intelligence

Dementia remains an extremely prevalent syndrome among older people and represents a major cause of disability and dependency. Alzheimer’s disease (AD) accounts for the majority of dementia cases and stands as the most common neurodegenerative disease. Since age is the major risk factor for AD, the increase in lifespan not only represents a rise in the prevalence but also adds complexity to the diagnosis. Moreover, the lack of disease-modifying therapies highlights another constraint. A shift from a curative to a preventive approach is imminent and we are moving towards the application of personalized medicine where we can shape the best clinical intervention for an individual patient at a given point. This new step in medicine requires the most recent tools and analysis of enormous amounts of data where the application of artificial intelligence (AI) plays a critical role on the depiction of disease–patient dynamics, crucial in reaching early/optimal diagnosis, monitoring and intervention. Predictive models and algorithms are the key elements in this innovative field. In this review, we present an overview of relevant topics regarding the application of AI in AD, detailing the algorithms and their applications in the fields of drug discovery, and biomarkers.

Tau deposition and structural connectivity demonstrate differential association patterns with neurocognitive tests

Tau neurofibrillary tangles have a central role in the pathogenesis of Alzheimer’s Disease (AD). Mounting evidence indicates that the propagation of tau is assisted by brain connectivity with weakened white-matter integrity along the propagation pathways. Recent advances in tau positron emission tomography tracers and diffusion magnetic resonance imaging allow the visualization of tau pathology and white-matter connectivity of the brain in vivo. The current study aims to investigate how tau deposition and structural connectivity are associated with memory function in prodromal AD. In this study, tau accumulation and structural connectivity data from 83 individuals (57 cognitively normal participants and 26 participants with mild cognitive impairment) were associated with neurocognitive test scores. Statistical analyses were performed in 70 cortical/subcortical brain regions to determine: 1. the level of association between tau and network metrics extracted from structural connectivity and 2. the association patterns of brain memory function with tau accumulation and network metrics. The results showed that tau accumulation and network metrics were correlated in early tau deposition regions. Furthermore, tau accumulation was associated with worse performance in almost all neurocognitive tests performance evaluated in the study. In comparison, decreased network connectivity was associated with declines in the delayed memory recall in Craft Stories and Benson Figure Copy. Interaction analysis indicates that tau deposition and dysconnectivity have a synergistic effect on the delayed Benson Figure Recall. Overall, our findings indicate that both tau deposition and structural dysconnectivity are associated with neurocognitive dysfunction. They also suggest that tau-PET may have better sensitivity to neurocognitive performance than diffusion MRI-derived measures of white-matter connectivity.

Explainable Deep Learning for Personalized Age Prediction With Brain Morphology

Predicting brain age has become one of the most attractive challenges in computational neuroscience due to the role of the predicted age as an effective biomarker for different brain diseases and conditions. A great variety of machine learning (ML) approaches and deep learning (DL) techniques have been proposed to predict age from brain magnetic resonance imaging scans. If on one hand, DL models could improve performance and reduce model bias compared to other less complex ML methods, on the other hand, they are typically black boxes as do not provide an in-depth understanding of the underlying mechanisms. Explainable Artificial Intelligence (XAI) methods have been recently introduced to provide interpretable decisions of ML and DL algorithms both at local and global level. In this work, we present an explainable DL framework to predict the age of a healthy cohort of subjects from ABIDE I database by using the morphological features extracted from their MRI scans. We embed the two local XAI methods SHAP and LIME to explain the outcomes of the DL models, determine the contribution of each brain morphological descriptor to the final predicted age of each subject and investigate the reliability of the two methods. Our findings indicate that the SHAP method can provide more reliable explanations for the morphological aging mechanisms and be exploited to identify personalized age-related imaging biomarker.