Ways toward an early diagnosis in Alzheimer's disease: the Alzheimer's Disease Neuroimaging Initiative (ADNI)

FetMRQC: A robust quality control system for multi-centric fetal brain MRI

Fetal brain MRI is becoming an increasingly relevant complement to neurosonography for perinatal diagnosis, allowing fundamental insights into fetal brain development throughout gestation. However, uncontrolled fetal motion and heterogeneity in acquisition protocols lead to data of variable quality, potentially biasing the outcome of subsequent studies. We present FetMRQC, an open-source machine-learning framework for automated image quality assessment and quality control that is robust to domain shifts induced by the heterogeneity of clinical data. FetMRQC extracts an ensemble of quality metrics from unprocessed anatomical MRI and combines them to predict experts' ratings using random forests. We validate our framework on a pioneeringly large and diverse dataset of more than 1600 manually rated fetal brain T2-weighted images from four clinical centers and 13 different scanners. Our study shows that FetMRQC's predictions generalize well to unseen data while being interpretable. FetMRQC is a step towards more robust fetal brain neuroimaging, which has the potential to shed new insights on the developing human brain.

Hypertension and cerebral blood flow in the development of Alzheimer's disease

INTRODUCTION

We investigated the interactive associations between amyloid and hypertension on the entorhinal cortex (EC) tau and atrophy and the role of cerebral blood flow (CBF) as a shared mechanism by which amyloid and hypertension contribute to EC tau and regional white matter hyperintensities (WMHs).

METHODS

We analyzed data from older adults without dementia participating in the Add-Tau study (NCT02958670, n = 138) or Alzheimer's Disease Neuroimaging Initiative (ADNI) (n = 523) who had available amyloid-positron emission tomography (PET), tau-PET, fluid-attenuated inversion recovery (FLAIR), and T1-weighted magnetic resonance imaging (MRI). A subsample in both cohorts had available arterial spin labeling (ASL) MRI (Add-Tau: n = 78; ADNI: n = 89).

RESULTS

The detrimental effects of hypertension on AD pathology and EC thickness were more pronounced in the Add-Tau cohort. Increased amyloid burden was associated with decreased occipital gray matter CBF in the ADNI cohort. In both cohorts, lower regional gray matter CBF was associated with higher EC tau and posterior WMH burden.

DISCUSSION

Reduced cerebral perfusion may be one common mechanism through which hypertension and amyloid are related to increased EC tau and WMH volume.

HIGHLIGHTS

Hypertension is associated with increased entorhinal cortex (EC) tau, particularly in the presence of amyloid. Decreased cortical cerebral blood flow (CBF) is associated with higher regional white matter hyperintensity volume. Increasing amyloid burden is associated with decreasing CBF in the occipital lobe. MTL CBF and amyloid are synergistically associated with EC tau.

Fully Automated Hippocampus Segmentation using T2-informed Deep Convolutional Neural Networks

Hippocampal atrophy (tissue loss) has become a fundamental outcome parameter in clinical trials on Alzheimer's disease. To accurately estimate hippocampus volume and track its volume loss, a robust and reliable segmentation is essential. Manual hippocampus segmentation is considered the gold standard but is extensive, time-consuming, and prone to rater bias. Therefore, it is often replaced by automated programs like FreeSurfer, one of the most commonly used tools in clinical research. Recently, deep learning-based methods have also been successfully applied to hippocampus segmentation. The basis of all approaches are clinically used T1-weighted whole-brain MR images with approximately 1 mm isotropic resolution. However, such T1 images show low contrast-to-noise ratios (CNRs), particularly for many hippocampal substructures, limiting delineation reliability. To overcome these limitations, high-resolution T2-weighted scans are suggested for better visualization and delineation, as they show higher CNRs and usually allow for higher resolutions. Unfortunately, such time-consuming T2-weighted sequences are not feasible in a clinical routine. We propose an automated hippocampus segmentation pipeline leveraging deep learning with T2-weighted MR images for enhanced hippocampus segmentation of clinical T1-weighted images based on a series of 3D convolutional neural networks and a specifically acquired multi-contrast dataset. This dataset consists of corresponding pairs of T1- and high-resolution T2-weighted images, with the T2 images only used to create more accurate manual ground truth annotations and to train the segmentation network. The T2-based ground truth labels were also used to evaluate all experiments by comparing the masks visually and by various quantitative measures. We compared our approach with four established state-of-the-art hippocampus segmentation algorithms (FreeSurfer, ASHS, HippoDeep, HippMapp3r) and demonstrated a superior segmentation performance. Moreover, we found that the automated segmentation of T1-weighted images benefits from the T2-based ground truth data. In conclusion, this work showed the beneficial use of high-resolution, T2-based ground truth data for training an automated, deep learning-based hippocampus segmentation and provides the basis for a reliable estimation of hippocampal atrophy in clinical studies.

Contributions of the ADNI Biostatistics Core

The goal of the Biostatistics Core of the Alzheimer's Disease Neuroimaging Initiative (ADNI) has been to ensure that sound study designs and statistical methods are used to meet the overall goals of ADNI. We have supported the creation of a well-validated and well-curated longitudinal database of clinical and biomarker information on ADNI participants and helped to make this accessible and usable for researchers. We have developed a statistical methodology for characterizing the trajectories of clinical and biomarker change for ADNI participants across the spectrum from cognitively normal to dementia, including multivariate patterns and evidence for heterogeneity in cognitive aging. We have applied these methods and adapted them to improve clinical trial design. ADNI-4 will offer us a chance to help extend these efforts to a more diverse cohort with an even richer panel of biomarker data to support better knowledge of and treatment for Alzheimer's disease and related dementias. HIGHLIGHTS: The Alzheimer's Disease Neuroimaging Initiative (ADNI) Biostatistics Core provides study design and analytic support to ADNI investigators. Core members develop and apply novel statistical methodology to work with ADNI data and support clinical trial design. The Core contributes to the standardization, validation, and harmonization of biomarker data. The Core serves as a resource to the wider research community to address questions related to the data and study as a whole.

Cognitive subtypes in youth at clinical high risk for psychosis

Introduction

Schizophrenia is a mental health condition that severely impacts well-being. Cognitive impairment is among its core features, often presenting well before the onset of overt psychosis, underscoring a critical need to study it in the psychosis proneness (clinical high risk; CHR) stage, to maximize the benefits of interventions and to improve clinical outcomes. However, given the heterogeneity of cognitive impairment in this population, a one-size-fits-all approach to therapeutic interventions would likely be insufficient. Thus, identifying cognitive subtypes in this population is crucial for tailored and successful therapeutic interventions. Here we identify, validate, and characterize cognitive subtypes in large CHR samples and delineate their baseline and longitudinal cognitive and functional trajectories.

Methods

Using machine learning, we performed cluster analysis on cognitive measures in a large sample of CHR youth (n = 764), and demographically comparable controls (HC; n = 280) from the North American Prodrome Longitudinal Study (NAPLS) 2, and independently validated our findings with an equally large sample (NAPLS 3; n = 628 CHR, 84 HC). By utilizing several statistical approaches, we compared the clusters on cognition and functioning at baseline, and over 24 months of followup. We further delineate the conversion status within those clusters.

Results

Two main cognitive clusters were identified, "impaired" and "intact" across all cognitive domains in CHR compared to HC. Baseline differences between the cognitively intact cluster and HC were found in the verbal abilities and attention and working memory domains. Longitudinally, those in the cognitively impaired cluster group demonstrated an overall floor effect and did not deteriorate further over time. However, a "catch up" trajectory was observed in the attention and working memory domain. This group had higher instances of conversion overall, with these converters having significantly more non-affective psychotic disorder diagnosis versus bipolar disorder, than those with intact cognition. In the cognitively intact group, we observed differences in trajectory based on conversion status, where those who start with intact cognition and later convert demonstrate a sharp decline in attention and functioning. Functioning was significantly better in the cognitively intact than in the impaired group at baseline. Most of the cognitive trajectories demonstrate a positive relationship with functional ones.

Conclusion

Our findings provide evidence for intact and impaired cognitive subtypes in youth at CHR, independent of conversion status. They further indicate that attention and working memory are important to distinguish between the CHR with intact cognition and controls. The cognitively intact CHR group becomes less attentive after conversion, while the cognitively impaired one demonstrates a catch up trajectory on both attention and working memory. Overall, early evaluation, covering several cognitive domains, is crucial for identifying trajectories of improvement and deterioration for the purpose of tailoring intervention for improving outcomes in individuals at CHR for psychosis.

Advances in blood biomarkers for Alzheimer disease (AD): A review

Alzheimer disease (AD) and Alzheimer Disease and Related Dementias (AD/ADRD) are growing public health challenges globally affecting millions of older adults, necessitating concerted efforts to advance our understanding and management of these conditions. AD is a progressive neurodegenerative disorder characterized pathologically by amyloid plaques and tau neurofibrillary tangles that are the primary cause of dementia in older individuals. Early and accurate diagnosis of AD dementia is crucial for effective intervention and treatment but has proven challenging to accomplish. Although testing for AD brain pathology with cerebrospinal fluid (CSF) or positron emission tomography (PET) has been available for over 2 decades, most patients never underwent this testing because of inaccessibility, high out-of-pocket costs, perceived risks, and the lack of AD-specific treatments. However, in recent years, rapid progress has been made in developing blood biomarkers for AD/ADRD. Consequently, blood biomarkers have emerged as promising tools for non-invasive and cost-effective diagnosis, prognosis, and monitoring of AD progression. This review presents the evolving landscape of blood biomarkers in AD/ADRD and explores their potential applications in clinical practice for early detection, prognosis, and therapeutic interventions. It covers recent advances in blood biomarkers, including amyloid beta (Aβ) peptides, tau protein, neurofilament light chain (NfL), and glial fibrillary acidic protein (GFAP). It also discusses their diagnostic and prognostic utility while addressing associated challenges and limitations. Future research directions in this rapidly evolving field are also proposed.

DeepComBat: A statistically motivated, hyperparameter-robust, deep learning approach to harmonization of neuroimaging data

Neuroimaging data acquired using multiple scanners or protocols are increasingly available. However, such data exhibit technical artifacts across batches which introduce confounding and decrease reproducibility. This is especially true when multi-batch data are analyzed using complex downstream models which are more likely to pick up on and implicitly incorporate batch-related information. Previously proposed image harmonization methods have sought to remove these batch effects; however, batch effects remain detectable in the data after applying these methods. We present DeepComBat, a deep learning harmonization method based on a conditional variational autoencoder and the ComBat method. DeepComBat combines the strengths of statistical and deep learning methods in order to account for the multivariate relationships between features while simultaneously relaxing strong assumptions made by previous deep learning harmonization methods. As a result, DeepComBat can perform multivariate harmonization while preserving data structure and avoiding the introduction of synthetic artifacts. We apply this method to cortical thickness measurements from a cognitive-aging cohort and show DeepComBat qualitatively and quantitatively outperforms existing methods in removing batch effects while preserving biological heterogeneity. Additionally, DeepComBat provides a new perspective for statistically motivated deep learning harmonization methods.

Edge Density Imaging Identifies White Matter Biomarkers of Late-Life Obesity and Cognition

Alzheimer disease (AD) and obesity are related to disruptions in the white matter (WM) connectome. We examined the link between the WM connectome and obesity and AD through edge-density imaging/index (EDI), a tractography-based method that characterizes the anatomical embedding of tractography connections. A total of 60 participants, 30 known to convert from normal cognition or mild-cognitive impairment to AD within a minimum of 24 months of follow up, were selected from the Alzheimer disease Neuroimaging Initiative (ADNI). Diffusion-weighted MR images from the baseline scans were used to extract fractional anisotropy (FA) and EDI maps that were subsequently averaged using deterministic WM tractography based on the Desikan-Killiany atlas. Multiple linear and logistic regression analysis were used to identify the weighted sum of tract-specific FA or EDI indices that maximized correlation to body-mass-index (BMI) or conversion to AD. Participants from the Open Access Series of Imaging Studies (OASIS) were used as an independent validation for the BMI findings. The edge-density rich, periventricular, commissural and projection fibers were among the most important WM tracts linking BMI to FA as well as to EDI. WM fibers that contributed significantly to the regression model related to BMI overlapped with those that predicted conversion; specifically in the frontopontine, corticostriatal, and optic radiation pathways. These results were replicated by testing the tract-specific coefficients found using ADNI in the OASIS-4 dataset. WM mapping with EDI enables identification of an abnormal connectome implicated in both obesity and conversion to AD.

Harmonizing three-dimensional MRI using pseudo-warping field guided GAN

In pursuit of cultivating automated models for magnetic resonance imaging (MRI) to aid in diagnostics, an escalating demand for extensive, multisite, and heterogeneous brain imaging datasets has emerged. This potentially introduces biased outcomes when directly applied for subsequent analysis. Researchers have endeavored to address this issue by pursuing the harmonization of MRIs. However, most existing image-based harmonization methods for MRI are tailored for 2D slices, which may introduce inter-slice variations when they are combined into a 3D volume. In this study, we aim to resolve inconsistencies between slices by introducing a pseudo-warping field. This field is created randomly and utilized to transform a slice into an artificially warped subsequent slice. The objective of this pseudo-warping field is to ensure that generators can consistently harmonize adjacent slices to another domain, without being affected by the varying content present in different slices. Furthermore, we construct unsupervised spatial and recycle loss to enhance the spatial accuracy and slice-wise consistency across the 3D images. The results demonstrate that our model effectively mitigates inter-slice variations and successfully preserves the anatomical details of the images during the harmonization process. Compared to generative harmonization models that employ 3D operators, our model exhibits greater computational efficiency and flexibility.

Examining the Stability and Predictive Utility of Across- and Within-Domain Intra-Individual Variability in Mild Cognitive Impairment

OBJECTIVE

Dispersion is a form of intra-individual variability across neuropsychological tests that has been shown to predict cognitive decline. However, few studies have investigated the stability and predictive utility of both across- and within-domain dispersion. The current study aims to fill these gaps in the literature by examining multiple indices of dispersion in a longitudinal clinical sample of individuals diagnosed with mild cognitive impairment (MCI) at baseline.

METHOD

Two hundred thirty-eight MCI patients from a cognitive disorders clinic underwent testing at baseline and after approximately 1.5 years. Linear regression was used to examine whether baseline across- and within-domain dispersion predicted cognitive decline in individuals whose diagnostic classification progressed to dementia (i.e., MCI-Decline) and those who retained an MCI diagnosis at follow-up (i.e., MCI-Stable). Cognitive decline was operationalized dichotomously using group status and continuously using standardized regression-based (SRB) z-scores.

RESULTS

Dispersion variables at baseline and follow-up were positively correlated in both groups, with the exception of within-domain executive functioning and language dispersion in the MCI-Decline group. None of the dispersion variables predicted diagnostic conversion to MCI. Using SRB z-scores, greater across-domain dispersion predicted greater overall cognitive decline at follow-up, but this was not the case for within-domain variables with the exception of visuospatial skills.

CONCLUSIONS

Results suggest that across- and within-domain dispersion are relatively stable across time, and that across-domain dispersion is predictive of subtle cognitive decline in patients with MCI. However, these results also highlight that findings may differ based on the tests included in dispersion calculations.

AI-based differential diagnosis of dementia etiologies on multimodal data

Differential diagnosis of dementia remains a challenge in neurology due to symptom overlap across etiologies, yet it is crucial for formulating early, personalized management strategies. Here, we present an artificial intelligence (AI) model that harnesses a broad array of data, including demographics, individual and family medical history, medication use, neuropsychological assessments, functional evaluations and multimodal neuroimaging, to identify the etiologies contributing to dementia in individuals. The study, drawing on 51,269 participants across 9 independent, geographically diverse datasets, facilitated the identification of 10 distinct dementia etiologies. It aligns diagnoses with similar management strategies, ensuring robust predictions even with incomplete data. Our model achieved a microaveraged area under the receiver operating characteristic curve (AUROC) of 0.94 in classifying individuals with normal cognition, mild cognitive impairment and dementia. Also, the microaveraged AUROC was 0.96 in differentiating the dementia etiologies. Our model demonstrated proficiency in addressing mixed dementia cases, with a mean AUROC of 0.78 for two co-occurring pathologies. In a randomly selected subset of 100 cases, the AUROC of neurologist assessments augmented by our AI model exceeded neurologist-only evaluations by 26.25%. Furthermore, our model predictions aligned with biomarker evidence and its associations with different proteinopathies were substantiated through postmortem findings. Our framework has the potential to be integrated as a screening tool for dementia in clinical settings and drug trials. Further prospective studies are needed to confirm its ability to improve patient care.

Growth-Associated Protein 43 and Tensor-Based Morphometry Indices in Mild Cognitive Impairment

Growth-associated protein 43 (GAP-43) is found in the axonal terminal of neurons in the limbic system, which is affected in people with Alzheimer's disease (AD). We assumed GAP-43 may contribute to AD progression and serve as a biomarker. So, in a two-year follow-up study, we assessed GAP-43 changes and whether they are correlated with tensor-based morphometry (TBM) findings in patients with mild cognitive impairment (MCI). We included MCI and cognitively normal (CN) people with available baseline and follow-up cerebrospinal fluid (CSF) GAP-43 and TBM findings from the ADNI database. We assessed the difference between the two groups and correlations in each group at each time point. CSF GAP-43 and TBM measures were similar in the two study groups in all time points, except for the accelerated anatomical region of interest (ROI) of CN subjects that were significantly greater than those of MCI. The only significant correlations with GAP-43 observed were those inverse correlations with accelerated and non-accelerated anatomical ROI in MCI subjects at baseline. Plus, all TBM metrics decreased significantly in all study groups during the follow-up in contrast to CSF GAP-43 levels. Our study revealed significant associations between CSF GAP-43 levels and TBM indices among people of the AD spectrum.

Analyzing heterogeneity in Alzheimer Disease using multimodal normative modeling on imaging-based ATN biomarkers

INTRODUCTION

Previous studies have applied normative modeling on a single neuroimaging modality to investigate Alzheimer Disease (AD) heterogeneity. We employed a deep learning-based multimodal normative framework to analyze individual-level variation across ATN (amyloid-tau-neurodegeneration) imaging biomarkers.

METHODS

We selected cross-sectional discovery (n = 665) and replication cohorts (n = 430) with available T1-weighted MRI, amyloid and tau PET. Normative modeling estimated individual-level abnormal deviations in amyloid-positive individuals compared to amyloid-negative controls. Regional abnormality patterns were mapped at different clinical group levels to assess intra-group heterogeneity. An individual-level disease severity index (DSI) was calculated using both the spatial extent and magnitude of abnormal deviations across ATN.

RESULTS

Greater intra-group heterogeneity in ATN abnormality patterns was observed in more severe clinical stages of AD. Higher DSI was associated with worse cognitive function and increased risk of disease progression.

DISCUSSION

Subject-specific abnormality maps across ATN reveal the heterogeneous impact of AD on the brain.

Associations of liver function with plasma biomarkers for Alzheimer's Disease

BACKGROUND

Blood-based biomarkers for Alzheimer's disease (AD) are promising to be used in clinical settings. The liver is an important degradation organ of the body. Whether liver function affects the levels of AD biomarkers needs to be studied.

OBJECTIVE

To investigate the associations between liver function and the plasma levels of AD biomarkers.

METHODS

We conducted an ADNI cohort-based cross-sectional study. Thirteen liver function markers commonly used in clinical settings were analyzed: total protein (TP), albumin (AL), globulin (GL), AL/GL ratio (A/G), total bilirubin (TB), direct bilirubin (DB), indirect bilirubin (IB), alanine aminotransferase (ALT), aspartate aminotransferase (AST), AST/ALT ratio, alkaline phosphatase (ALP), lactate dehydrogenase (LDH), and γ-glutamyltransferase (GGT). Liquid chromatography-tandem mass spectrometry was used to detect the plasma Aβ42 and Aβ40 concentrations. Single Molecule array technique was used to measure the plasma p-tau181 and NfL concentrations. We used linear regression models to analyze the associations between liver function markers and the levels of AD plasma biomarkers.

RESULTS

ALP was positively associated with the levels of plasma Aβ42 (β = 0.16, P = 0.018) and Aβ40 (β = 0.21, P = 0.004). LDH was positively associated with the levels of plasma p-tau181 (β = 0.09, P = 0.022). While NfL was correlated with multiple liver function markers, including AL, A/G, ALT, AST/ALT, and LDH.

CONCLUSION

Liver function was associated with the plasma levels of AD biomarkers. It needs to consider the potential influence of liver function on the reference ranges and the interpretation of results for AD biomarkers before clinical use.

p75 neurotrophin receptor modulation in mild to moderate Alzheimer disease: a randomized, placebo-controlled phase 2a trial

p75 neurotrophin receptor (p75NTR) signaling pathways substantially overlap with degenerative networks active in Alzheimer disease (AD). Modulation of p75NTR with the first-in-class small molecule LM11A-31 mitigates amyloid-induced and pathological tau-induced synaptic loss in preclinical models. Here we conducted a 26-week randomized, placebo-controlled, double-blinded phase 2a safety and exploratory endpoint trial of LM11A-31 in 242 participants with mild to moderate AD with three arms: placebo, 200 mg LM11A-31 and 400 mg LM11A-31, administered twice daily by oral capsules. This trial met its primary endpoint of safety and tolerability. Within the prespecified secondary and exploratory outcome domains (structural magnetic resonance imaging, fluorodeoxyglucose positron-emission tomography and cerebrospinal fluid biomarkers), significant drug-placebo differences were found, consistent with the hypothesis that LM11A-31 slows progression of pathophysiological features of AD; no significant effect of active treatment was observed on cognitive tests. Together, these results suggest that targeting p75NTR with LM11A-31 warrants further investigation in larger-scale clinical trials of longer duration. EU Clinical Trials registration: 2015-005263-16 ; ClinicalTrials.gov registration: NCT03069014 .

Comparison of consistency in centiloid scale among different analytical methods in amyloid PET: the CapAIBL, VIZCalc, and Amyquant methods

OBJECTIVE

The Centiloid (CL) scale is a standardized measure for quantifying amyloid deposition in amyloid positron emission tomography (PET) imaging. We aimed to assess the agreement among 3 CL calculation methods: CapAIBL, VIZCalc, and Amyquant.

METHODS

This study included 192 participants (mean age: 71.5 years, range: 50-87 years), comprising 55 with Alzheimer's disease, 65 with mild cognitive impairment, 13 with non-Alzheimer's dementia, and 59 cognitively normal participants. All the participants were assessed using the three CL calculation methods. Spearman's rank correlation, linear regression, Friedman tests, Wilcoxon signed-rank tests, and Bland-Altman analysis were employed to assess data correlations, linear associations, method differences, and systematic bias, respectively.

RESULTS

Strong correlations (rho = 0.99, p < .001) were observed among the CL values calculated using the three methods. Scatter plots and regression lines visually confirmed these strong correlations and met the validation criteria. Despite the robust correlations, a significant difference in CL value between CapAIBL and Amyquant was observed (36.1 ± 39.7 vs. 34.9 ± 39.4; p < .001). In contrast, no significant differences were found between CapAIBL and VIZCalc or between VIZCalc and Amyquant. The Bland-Altman analysis showed no observable systematic bias between the methods.

CONCLUSIONS

The study demonstrated strong agreement among the three methods for calculating CL values. Despite minor variations in the absolute values of the Centiloid scores obtained using these methods, the overall agreement suggests that they are interchangeable.

Exploring Brain Effective Connectivity Networks Through Spatiotemporal Graph Convolutional Models

Learning brain effective connectivity networks (ECN) from functional magnetic resonance imaging (fMRI) data has gained much attention in recent years. With the successful applications of deep learning in numerous fields, several brain ECN learning methods based on deep learning have been reported in the literature. However, current methods ignore the deep temporal features of fMRI data and fail to fully employ the spatial topological relationship between brain regions. In this article, we propose a novel method for learning brain ECN based on spatiotemporal graph convolutional models (STGCM), named STGCMEC, in which we first adopt the temporal convolutional network to extract the deep temporal features of fMRI data and utilize the graph convolutional network to update the spatial features of each brain region by aggregating information from neighborhoods, which makes the features of brain regions more discriminative. Then, based on such features of brain regions, we design a joint loss function to guide STGCMEC to learn the brain ECN, which includes a task prediction loss and a graph regularization loss. The experimental results on a simulated dataset and a real Alzheimer's disease neuroimaging initiative (ADNI) dataset show that the proposed STGCMEC is able to better learn brain ECN compared with some state-of-the-art methods.

ClinicalGAN: powering patient monitoring in clinical trials with patient digital twins

Conducting clinical trials is becoming increasingly challenging lately due to spiraling costs, increased time to market, and high failure rates. Patient recruitment and retention is one of the key challenges that impact 90% of the trials directly. While a lot of attention has been given to optimizing patient recruitment, limited progress has been made towards developing comprehensive clinical trial monitoring systems to determine patients at risk and potentially improve patient retention through the right intervention at the right time. Earlier research in patient retention primarily focused on using deterministic frameworks to model the inherently stochastic patient journey process. Existing generative approaches to model temporal data such as TimeGAN or CRBM , face challenges and fail to address key requirements such as personalized generation, variable patient journey, and multi-variate time-series needed to model patient digital twin. In response to these challenges, current research proposes ClinicalGAN to enable patient level generation, effectively creating a patient's digital twin. ClinicalGAN provides capabilities for: (a) patient-level personalized generation by utilizing patient meta-data for conditional generation; (b) dynamic termination prediction to enable pro-active patient monitoring for improved patient retention; (c) multi-variate time-series training to incorporate relationship and dependencies among different tests measures captured during patient journey. The proposed solution is validated on two Alzheimer's clinical trial datasets and the results are benchmarked across multiple dimensions of generation quality. Empirical results demonstrate that the proposed ClinicalGAN outperforms the SOTA approach by 3-4 × on average across all the generation quality metrics. Furthermore, the proposed architecture is shown to outperform predictive methods at the task of drop-off prediction significantly (5-10% MAPE scores).

Positive Effect of Super-Resolved Structural Magnetic Resonance Imaging for Mild Cognitive Impairment Detection

This paper presents a novel approach to improving the detection of mild cognitive impairment (MCI) through the use of super-resolved structural magnetic resonance imaging (MRI) and optimized deep learning models. The study introduces enhancements to the perceptual quality of super-resolved 2D structural MRI images using advanced loss functions, modifications to the upscaler part of the generator, and experiments with various discriminators within a generative adversarial training setting. It empirically demonstrates the effectiveness of super-resolution in the MCI detection task, showcasing performance improvements across different state-of-the-art classification models. The paper also addresses the challenge of accurately capturing perceptual image quality, particularly when images contain checkerboard artifacts, and proposes a methodology that incorporates hyperparameter optimization through a Pareto optimal Markov blanket (POMB). This approach systematically explores the hyperparameter space, focusing on reducing overfitting and enhancing model generalizability. The research findings contribute to the field by demonstrating that super-resolution can significantly improve the quality of MRI images for MCI detection, highlighting the importance of choosing an adequate discriminator and the potential of super-resolution as a preprocessing step to boost classification model performance.

Generalizability of Tau and Amyloid Plasma Biomarkers in Alzheimer's Disease Cohorts of Diverse Genetic Ancestries

Introduction

Plasma phosphorylated threonine-181 of Tau and amyloid beta are biomarkers for differential diagnosis and preclinical detection of Alzheimer disease (AD). Given differences in AD risk across diverse populations, generalizability of existing biomarker data is not assured.

Methods

In 2,086 individuals of diverse genetic ancestries (African American, Caribbean Hispanic, and Peruvians) we measured plasma pTau-181 and Aβ42/Aβ40. Differences in biomarkers between cohorts and clinical diagnosis groups and the potential discriminative performance of the two biomarkers were assessed.

Results

pTau-181 and Aβ42/Aβ40 were consistent across cohorts. Higher levels of pTau181 were associated with AD while Aβ42/Aβ40 had minimal differences. Correspondingly, pTau-181 had greater predictive value than Aβ42/Aβ40, however, the area under the curve differed between cohorts.

Discussion

pTau-181 as a plasma biomarker for clinical AD is generalizable across genetic ancestries, but predictive value may differ. Combining genomic and biomarker data from diverse individuals will increase understanding of genetic risk and refine clinical diagnoses.

Three-dimensional histology reveals dissociable human hippocampal long-axis gradients of Alzheimer's pathology

INTRODUCTION

Three-dimensional (3D) histology analyses are essential to overcome sampling variability and understand pathological differences beyond the dissection axis. We present Path2MR, the first pipeline allowing 3D reconstruction of sparse human histology without a magnetic resonance imaging (MRI) reference. We implemented Path2MR with post-mortem hippocampal sections to explore pathology gradients in Alzheimer's disease.

METHODS

Blockface photographs of brain hemisphere slices are used for 3D reconstruction, from which an MRI-like image is generated using machine learning. Histology sections are aligned to the reconstructed hemisphere and subsequently to an atlas in standard space.

RESULTS

Path2MR successfully registered histological sections to their anatomic position along the hippocampal longitudinal axis. Combined with histopathology quantification, we found an expected peak of tau pathology at the anterior end of the hippocampus, whereas amyloid-beta (Aβ) displayed a quadratic anterior-posterior distribution.

CONCLUSION

Path2MR, which enables 3D histology using any brain bank data set, revealed significant differences along the hippocampus between tau and Aβ.

HIGHLIGHTS

Path2MR enables three-dimensional (3D) brain reconstruction from blockface dissection photographs. This pipeline does not require dense specimen sampling or a subject-specific magnetic resonance (MR) image. Anatomically consistent mapping of hippocampal sections was obtained with Path2MR. Our analyses revealed an anterior-posterior gradient of hippocampal tau pathology. In contrast, the peak of amyloid-beta (Aβ) deposition was closer to the hippocampal body.

Amyloid-β prediction machine learning model using source-based morphometry across neurocognitive disorders

Previous studies have developed and explored magnetic resonance imaging (MRI)-based machine learning models for predicting Alzheimer's disease (AD). However, limited research has focused on models incorporating diverse patient populations. This study aimed to build a clinically useful prediction model for amyloid-beta (Aβ) deposition using source-based morphometry, using a data-driven algorithm based on independent component analyses. Additionally, we assessed how the predictive accuracies varied with the feature combinations. Data from 118 participants clinically diagnosed with various conditions such as AD, mild cognitive impairment, frontotemporal lobar degeneration, corticobasal syndrome, progressive supranuclear palsy, and psychiatric disorders, as well as healthy controls were used for the development of the model. We used structural MR images, cognitive test results, and apolipoprotein E status for feature selection. Three-dimensional T1-weighted images were preprocessed into voxel-based gray matter images and then subjected to source-based morphometry. We used a support vector machine as a classifier. We applied SHapley Additive exPlanations, a game-theoretical approach, to ensure model accountability. The final model that was based on MR-images, cognitive test results, and apolipoprotein E status yielded 89.8% accuracy and a receiver operating characteristic curve of 0.888. The model based on MR-images alone showed 84.7% accuracy. Aβ-positivity was correctly detected in non-AD patients. One of the seven independent components derived from source-based morphometry was considered to represent an AD-related gray matter volume pattern and showed the strongest impact on the model output. Aβ-positivity across neurological and psychiatric disorders was predicted with moderate-to-high accuracy and was associated with a probable AD-related gray matter volume pattern. An MRI-based data-driven machine learning approach can be beneficial as a diagnostic aid.

AI-based differential diagnosis of dementia etiologies on multimodal data

Differential diagnosis of dementia remains a challenge in neurology due to symptom overlap across etiologies, yet it is crucial for formulating early, personalized management strategies. Here, we present an AI model that harnesses a broad array of data, including demographics, individual and family medical history, medication use, neuropsychological assessments, functional evaluations, and multimodal neuroimaging, to identify the etiologies contributing to dementia in individuals. The study, drawing on 51,269 participants across 9 independent, geographically diverse datasets, facilitated the identification of 10 distinct dementia etiologies. It aligns diagnoses with similar management strategies, ensuring robust predictions even with incomplete data. Our model achieved a micro-averaged area under the receiver operating characteristic curve (AUROC) of 0.94 in classifying individuals with normal cognition, mild cognitive impairment and dementia. Also, the micro-averaged AUROC was 0.96 in differentiating the dementia etiologies. Our model demonstrated proficiency in addressing mixed dementia cases, with a mean AUROC of 0.78 for two co-occurring pathologies. In a randomly selected subset of 100 cases, the AUROC of neurologist assessments augmented by our AI model exceeded neurologist-only evaluations by 26.25%. Furthermore, our model predictions aligned with biomarker evidence and its associations with different proteinopathies were substantiated through postmortem findings. Our framework has the potential to be integrated as a screening tool for dementia in various clinical settings and drug trials, with promising implications for person-level management.

Impaired sleep is associated with tau deposition on 18F-flortaucipir PET and accelerated cognitive decline, accounting for medications that affect sleep

BACKGROUND

Impaired sleep is commonly associated with Alzheimer's disease (AD), although the underlying mechanisms remain unclear. Furthermore, the moderating effects of sleep-affecting medications, which have been linked to AD pathology, are incompletely characterized. Using data from the Alzheimer's Disease Neuroimaging Initiative, we investigated whether a medical history of impaired sleep, informant-reported nighttime behaviors, and sleep-affecting medications are associated with beta-amyloid and tau deposition on PET and cognitive change, cross-sectionally and longitudinally.

METHODS

We included 964 subjects with 18F-florbetapir PET scans. Measures of sleep impairment and medication use were obtained from medical histories and the Neuropsychiatric Inventory Questionnaire. Multivariate models, adjusted for covariates, were used to assess associations among sleep-related features, beta-amyloid and tau, and cognition. Cortical tau deposition, categorized by Braak stage, was assessed using the standardized uptake value peak alignment (SUVP) method on 18F-flortaucipir PET.

RESULTS

Medical history of sleep impairment was associated with greater baseline tau in the meta-temporal, Braak 1, and Braak 4 regions (p = 0.04, p < 0.001, p = 0.025, respectively). Abnormal nighttime behaviors were also associated with greater baseline tau in the meta-temporal region (p = 0.024), and greater cognitive impairment, cross-sectionally (p = 0.007) and longitudinally (p < 0.001). Impaired sleep was not associated with baseline beta-amyloid (p > 0.05). Short-term use of selective serotonin reuptake inhibitors and benzodiazepines slightly weakened the sleep-tau relationship.

CONCLUSIONS

Sleep impairment was associated with tauopathy and cognitive decline, which could be linked to increased tau secretion from neuronal hyperactivity. Clinically, our results help identify high-risk individuals who could benefit from sleep-related interventions aimed to delay cognitive decline and AD.

The impact of Bayesian optimization on feature selection

Feature selection is an indispensable step for the analysis of high-dimensional molecular data. Despite its importance, consensus is lacking on how to choose the most appropriate feature selection methods, especially when the performance of the feature selection methods itself depends on hyper-parameters. Bayesian optimization has demonstrated its advantages in automatically configuring the settings of hyper-parameters for various models. However, it remains unclear whether Bayesian optimization can benefit feature selection methods. In this research, we conducted extensive simulation studies to compare the performance of various feature selection methods, with a particular focus on the impact of Bayesian optimization on those where hyper-parameters tuning is needed. We further utilized the gene expression data obtained from the Alzheimer's Disease Neuroimaging Initiative to predict various brain imaging-related phenotypes, where various feature selection methods were employed to mine the data. We found through simulation studies that feature selection methods with hyper-parameters tuned using Bayesian optimization often yield better recall rates, and the analysis of transcriptomic data further revealed that Bayesian optimization-guided feature selection can improve the accuracy of disease risk prediction models. In conclusion, Bayesian optimization can facilitate feature selection methods when hyper-parameter tuning is needed and has the potential to substantially benefit downstream tasks.

Predictive power of gait and gait-related cognitive measures in amnestic mild cognitive impairment: a machine learning analysis

Introduction

Gait disorders and gait-related cognitive tests were recently linked to future Alzheimer's Disease (AD) dementia diagnosis in amnestic Mild Cognitive Impairment (aMCI). This study aimed to evaluate the predictive power of gait disorders and gait-related neuropsychological performances for future AD diagnosis in aMCI through machine learning (ML).

Methods

A sample of 253 aMCI (stable, converter) individuals were included. We explored the predictive accuracy of four predictors (gait profile plus MMSE, DSST, and TMT-B) previously identified as critical for the conversion from aMCI to AD within a 36-month follow-up. Supervised ML algorithms (Support Vector Machine [SVM], Logistic Regression, and k-Nearest Neighbors) were trained on 70% of the dataset, and feature importance was evaluated for the best algorithm.

Results

The SVM algorithm achieved the best performance. The optimized training set performance achieved an accuracy of 0.67 (sensitivity = 0.72; specificity = 0.60), improving to 0.70 on the test set (sensitivity = 0.79; specificity = 0.52). Feature importance revealed MMSE as the most important predictor in both training and testing, while gait type was important in the testing phase.

Discussion

We created a predictive ML model that is capable of identifying aMCI at high risk of AD dementia within 36 months. Our ML model could be used to quickly identify individuals at higher risk of AD, facilitating secondary prevention (e.g., cognitive and/or physical training), and serving as screening for more expansive and invasive tests. Lastly, our results point toward theoretically and practically sound evidence of mind and body interaction in AD.

A chromogenic diarylethene-based probe for the detection of Cu2+ in aqueous medium in Drosophila for early diagnosis of Alzheimer

A diarylethene-based probe (Z)-N'-((2-amino-5-chlorophenyl)(phenyl)methylene)-2-hydroxy benzohydrazide (KBH) has been proficiently developed and its structure has been confirmed by single crystal X-ray diffraction technique. It displays a selective and sensitive colorimetric sensing of Cu2+ ions in aqueous medium with a naked eye colour change from colourless to yellow. It exhibits a significantly low limit of detection as 1.5 nM. A plausible binding mechanism has been proposed using Job's plot, FT-IR, 1H NMR titration, HRMS and DFT studies. The chemosensor is effectively reversible and reusable with EDTA. Test strip kit and real water sample analysis have been shown to establish its practical applicability. Further, the potential of KBH for the early diagnosis of Cu2+ ion-induced amyloid toxicity has been investigated in eye imaginal disc of Alzheimer's disease model of Drosophila 3rd instar larvae. The in-vivo interaction of KBH with Cu2+ in gut tissues of Drosophila larvae establishes its sensing capability in biological system. Interestingly, the in-vivo detection of Cu2+ has been done using bright field imaging which eliminates the necessity of a fluorescent label, hence making the method highly economical.

Traumatic Brain Injury and Post-Traumatic Stress Disorder and Their Influence on Development and Pattern of Alzheimer's Disease Pathology in Later Life

Background

Traumatic brain injury (TBI) and posttraumatic stress disorder (PTSD) are potential risk factors for the development of dementia including Alzheimer's disease (AD) in later life. The findings of studies investigating this question are inconsistent though.

Objective

To investigate if these inconsistencies are caused by the existence of subgroups with different vulnerability for AD pathology and if these subgroups are characterized by atypical tau load/atrophy pattern.

Methods

The MRI and PET data of 89 subjects with or without previous TBI and/or PTSD from the DoD ADNI database were used to calculate an age-corrected gray matter tau mismatch metric (ageN-T mismatch-score and matrix) for each subject. This metric provides a measure to what degree regional tau accumulation drives regional gray matter atrophy (matrix) and can be used to calculate a summary score (score) reflecting the severity of AD pathology in an individual.

Results

The ageN-T mismatch summary score was positively correlated with whole brain beta-amyloid load and general cognitive function but not with PTSD or TBI severity. Hierarchical cluster analysis identified five different spatial patterns of tau-gray matter interactions. These clusters reflected the different stages of the typical AD tau progression pattern. None was exclusively associated with PTSD and/or TBI.

Conclusions

These findings suggest that a) although subsets of patients with PTSD and/or TBI develop AD-pathology, a history of TBI or PTSD alone or both is not associated with a significantly higher risk to develop AD pathology in later life. b) remote TBI or PTSD do not modify the typical AD pathology distribution pattern.

A Novel Peptidome Technology for the Diagnosis of Mild Cognitive Impairment and Alzheimer's Disease by Selected Reaction Monitoring

Background

With the aging of populations worldwide, Alzheimer's disease (AD) has become a concern due to its high prevalence and the continued lack of established treatments. Early diagnosis is required as a preventive intervention to modify the disease's progression. In our previous study, we performed peptidomic analysis of serum samples obtained from AD patients and age-matched healthy subjects to seek peptide biomarker candidates for AD by using BLOTCHIP-MS analysis, and identified four peptides as AD biomarker candidates.

Objective

The objective was to validate the serum biomarker peptides to distinguish mild cognitive impairment (MCI) and AD in comparison to cognitively healthy controls using a new peptidome technology, the Dementia Risk Test.

Methods

We enrolled 195 subjects with normal cognitive function (NC; n = 70), MCI (n = 55), and AD (n = 70), The concentrations of cognitive impairment marker peptides (Fibrinogen α chain (FAC), Fibrinogen β chain (FBC), Plasma protease C1 inhibitor (PPC1I), α2-HS-glycoprotein (AHSG)) were quantified by using a selected reaction monitoring assay based on liquid chromatography-MS/MS.

Results

The present study confirmed that three peptides, FAC, FBC, and PPC1I, were significantly upregulated during the onset of AD. This three-peptide set was both highly sensitive in determining AD (sensitivity: 85.7%, specificity: 95.7%, AUC: 0.900) and useful in distinguishing MCI (sensitivity: 61.8%, specificity: 98.6%, AUC: 0.824) from NC.

Conclusions

In this validation study, we confirmed the high diagnostic potential of the three peptides identified in our previous study as candidate serum biomarkers for AD. The Dementia Risk Test may be a powerful tool for detecting AD-related pathological changes.

Data-Driven Thresholding Statistically Biases ATN Profiling across Cohort Datasets

BACKGROUND

While the amyloid/tau/neurodegeneration (ATN) framework has found wide application in Alzheimer's disease research, it is unclear if thresholds obtained using distinct thresholding methods are concordant within the same dataset and interchangeable across cohorts.

OBJECTIVES

To investigate the robustness of data-driven thresholding methods and ATN profiling across cohort datasets.

DESIGN AND SETTING

We evaluated the impact of thresholding methods on ATN profiles by applying five commonly-used methodologies across cohort datasets. We assessed the generalizability of disease patterns discovered within ATN profiles by clustering individuals from different cohorts who were assigned to the same ATN profile.

PARTICIPANTS AND MEASUREMENTS

Participants with available CSF amyloid-β 1-42, phosphorylated tau, and total tau measurements were included from eleven AD cohort studies.

RESULTS

We observed high variability among obtained ATN thresholds, both across methods and datasets that impacted the resulting profile assignments of participants significantly. Clustering participants from different cohorts within the same ATN category indicated that identified disease patterns were comparable across most cohorts and biases introduced through distinct thresholding and data representations remained insignificant in most ATN profiles.

CONLUSION

Thresholding method selection is a decision of statistical relevance that will inevitably bias the resulting profiling and affect its sensitivity and specificity. Thresholds are likely not directly interchangeable between independent cohorts. To apply the ATN framework as an actionable and robust profiling scheme, a comprehensive understanding of the impact of used thresholding methods, their statistical implications, and a validation of results is crucial.

Semantic Harmonization of Alzheimer's Disease Datasets Using AD-Mapper

Background

Despite numerous past endeavors for the semantic harmonization of Alzheimer's disease (AD) cohort studies, an automatic tool has yet to be developed.

Objective

As cohort studies form the basis of data-driven analysis, harmonizing them is crucial for cross-cohort analysis. We aimed to accelerate this task by constructing an automatic harmonization tool.

Methods

We created a common data model (CDM) through cross-mapping data from 20 cohorts, three CDMs, and ontology terms, which was then used to fine-tune a BioBERT model. Finally, we evaluated the model using three previously unseen cohorts and compared its performance to a string-matching baseline model.

Results

Here, we present our AD-Mapper interface for automatic harmonization of AD cohort studies, which outperformed a string-matching baseline on previously unseen cohort studies. We showcase our CDM comprising 1218 unique variables.

Conclusion

AD-Mapper leverages semantic similarities in naming conventions across cohorts to improve mapping performance.

The Alzheimer's Disease Neuroimaging Initiative in the era of Alzheimer's disease treatment: A review of ADNI studies from 2021 to 2022

The Alzheimer's Disease Neuroimaging Initiative (ADNI) aims to improve Alzheimer's disease (AD) clinical trials. Since 2006, ADNI has shared clinical, neuroimaging, and cognitive data, and biofluid samples. We used conventional search methods to identify 1459 publications from 2021 to 2022 using ADNI data/samples and reviewed 291 impactful studies. This review details how ADNI studies improved disease progression understanding and clinical trial efficiency. Advances in subject selection, detection of treatment effects, harmonization, and modeling improved clinical trials and plasma biomarkers like phosphorylated tau showed promise for clinical use. Biomarkers of amyloid beta, tau, neurodegeneration, inflammation, and others were prognostic with individualized prediction algorithms available online. Studies supported the amyloid cascade, emphasized the importance of neuroinflammation, and detailed widespread heterogeneity in disease, linked to genetic and vascular risk, co-pathologies, sex, and resilience. Biological subtypes were consistently observed. Generalizability of ADNI results is limited by lack of cohort diversity, an issue ADNI-4 aims to address by enrolling a diverse cohort.

Associations Between Hyperactive Neuropsychiatric Symptoms and Brain Morphology in Mild Cognitive Impairment and Alzheimer's Disease

BACKGROUND

Hyperactive neuropsychiatric symptoms (NPS) (i.e., agitation, disinhibition, and irritability) are among the most challenging symptoms to manage in Alzheimer's disease (AD). However, their underlying brain correlates have been poorly studied.

OBJECTIVE

We aimed to investigate the associations between the total score of hyperactive NPS and brain structures in participants with AD, mild cognitive impairment (MCI), and cognitively normal older adults (CN).

METHODS

Neuropsychiatric and 3T MRI data from 216 AD, 564 MCI, and 660 CN participants were extracted from the Alzheimer's Disease Neuroimaging Initiative database. To define NPS and brain structures' associations, we fitted a general linear model (GLM) in two ways: 1) an overall GLM including all three groups (AD, MCI, CN) and 2) three pair-wise GLMs (AD versus MCI, MCI versus CN, AD versus CN). The cortical changes as a function of NPS total score were investigated using multiple regression analyses.

RESULTS

Results from the overall GLM include associations between 1) agitation and the right parietal supramarginal surface area in the MCI-CN contrast, 2) disinhibition and the cortical thickness of the right frontal pars opercularis and temporal inferior in the AD-MCI contrast, and 3) irritability and the right frontal pars opercularis, frontal superior, and temporal superior volumes in the MCI-CN contrast.

CONCLUSIONS

Our study shows that each hyperactive NPS is associated with distinct brain regions in AD, MCI, and CN (groups with different levels of cognitive performance). This suggests that each NPS is associated with a unique signature of brain morphology, including variations in volume, thickness, or area.

Risk, protective, and biomarkers of dementia in Indigenous peoples: A systematic review

INTRODUCTION

Dementia is an emergent health priority for Indigenous peoples worldwide, yet little is known about disease drivers and protective factors.

METHODS

Database searches were conducted in March 2022 to identify original publications on risk, protective, genetic, neuroradiological, and biological factors related to dementia and cognitive impairment involving Indigenous peoples.

RESULTS

Modifiable risk factors featured across multiple studies include childhood adversity, hearing loss, low education attainment, unskilled work history, stroke, head injury, epilepsy, diabetes, hypertension, hyperlipidemia, depression, low BMI, poor mobility, and continence issues. Non-modifiable risk factors included increasing age, sex, and genetic polymorphisms. Education, ex-smoking, physical and social activity, and engagement with cultural or religious practices were highlighted as potential protective factors. There is a paucity of research on dementia biomarkers involving Indigenous peoples.

DISCUSSION

Greater understanding of modifiable factors and biomarkers of dementia can assist in strength-based models to promote healthy ageing and cognition for Indigenous peoples.

HCS-Net: Multi-level deformation strategy combined with quadruple attention for image registration

BACKGROUND AND OBJECTIVE

Non-rigid image registration plays a significant role in computer-aided diagnosis and surgical navigation for brain diseases. Registration methods that utilize convolutional neural networks (CNNs) have shown excellent accuracy when applied to brain magnetic resonance images (MRI). However, CNNs have limitations in understanding long-range spatial relationships in images, which makes it challenging to incorporate contextual information. And in intricate image registration tasks, it is difficult to achieve a satisfactory dense prediction field, resulting in poor registration performance.

METHODS

This paper proposes a multi-level deformable unsupervised registration model that combines Transformer and CNN to achieve non-rigid registration of brain MRI. Firstly, utilizing a dual encoder structure to establish the dependency relationship between the global features of two images and to merge features of varying scales, as well as to preserve the relative spatial position information of feature maps at different scales. Then the proposed multi-level deformation strategy utilizes different deformable fields of varying resolutions generated by the decoding structure to progressively deform the moving image. Ultimately, the proposed quadruple attention module is incorporated into the decoding structure to merge feature information from various directions and emphasize the spatial features in the dominant channels.

RESULTS

The experimental results on multiple brain MR datasets demonstrate that the promising network could provide accurate registration and is comparable to state-of-the-art methods.

CONCLUSION

The proposed registration model can generate superior deformable fields and achieve more precise registration effects, enhancing the auxiliary role of medical image registration in various fields and advancing the development of computer-aided diagnosis, surgical navigation, and related domains.

Standardized brain tumor imaging protocols for clinical trials: current recommendations and tips for integration

Standardized MRI acquisition protocols are crucial for reducing the measurement and interpretation variability associated with response assessment in brain tumor clinical trials. The main challenge is that standardized protocols should ensure high image quality while maximizing the number of institutions meeting the acquisition requirements. In recent years, extensive effort has been made by consensus groups to propose different "ideal" and "minimum requirements" brain tumor imaging protocols (BTIPs) for gliomas, brain metastases (BM), and primary central nervous system lymphomas (PCSNL). In clinical practice, BTIPs for clinical trials can be easily integrated with additional MRI sequences that may be desired for clinical patient management at individual sites. In this review, we summarize the general concepts behind the choice and timing of sequences included in the current recommended BTIPs, we provide a comparative overview, and discuss tips and caveats to integrate additional clinical or research sequences while preserving the recommended BTIPs. Finally, we also reflect on potential future directions for brain tumor imaging in clinical trials.

Three-dimensional histology reveals dissociable human hippocampal long axis gradients of Alzheimer's pathology

INTRODUCTION

Three-dimensional (3D) histology analyses are essential to overcome sampling variability and understand pathological differences beyond the dissection axis. We present Path2MR, the first pipeline allowing 3D reconstruction of sparse human histology without an MRI reference. We implemented Path2MR with post-mortem hippocampal sections to explore pathology gradients in Alzheimer's Disease.

METHODS

Blockface photographs of brain hemisphere slices are used for 3D reconstruction, from which an MRI-like image is generated using machine learning. Histology sections are aligned to the reconstructed hemisphere and subsequently to an atlas in standard space.

RESULTS

Path2MR successfully registered histological sections to their anatomical position along the hippocampal longitudinal axis. Combined with histopathology quantification, we found an expected peak of tau pathology at the anterior end of the hippocampus, while amyloid-β displayed a quadratic anterior-posterior distribution.

CONCLUSION

Path2MR, which enables 3D histology using any brain bank dataset, revealed significant differences along the hippocampus between tau and amyloid-β.

Preserving cognitive function in patients with Alzheimer's disease: The Alzheimer's disease neuroprotection research initiative (ADNRI)

The global trend toward aging populations has resulted in an increase in the occurrence of Alzheimer's disease (AD) and associated socioeconomic burdens. Abnormal metabolism of amyloid-β (Aβ) has been proposed as a significant pathomechanism in AD, supported by results of recent clinical trials using anti-Aβ antibodies. Nonetheless, the cognitive benefits of the current treatments are limited. The etiology of AD is multifactorial, encompassing Aβ and tau accumulation, neuroinflammation, demyelination, vascular dysfunction, and comorbidities, which collectively lead to widespread neurodegeneration in the brain and cognitive impairment. Hence, solely removing Aβ from the brain may be insufficient to combat neurodegeneration and preserve cognition. To attain effective treatment for AD, it is necessary to (1) conduct extensive research on various mechanisms that cause neurodegeneration, including advances in neuroimaging techniques for earlier detection and a more precise characterization of molecular events at scales ranging from cellular to the full system level; (2) identify neuroprotective intervention targets against different neurodegeneration mechanisms; and (3) discover novel and optimal combinations of neuroprotective intervention strategies to maintain cognitive function in AD patients. The Alzheimer's Disease Neuroprotection Research Initiative's objective is to facilitate coordinated, multidisciplinary efforts to develop systemic neuroprotective strategies to combat AD. The aim is to achieve mitigation of the full spectrum of pathological processes underlying AD, with the goal of halting or even reversing cognitive decline.

Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review

INTRODUCTION

Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis and prognosis of dementia.

METHODS

We systematically reviewed studies reporting AI for neuroimaging in diagnosis and/or prognosis of cognitive neurodegenerative diseases.

RESULTS

A total of 255 studies were identified. Most studies relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers were the most commonly used AI method (48%) and discriminative models performed best for differentiating Alzheimer's disease from controls. The accuracy of algorithms varied with the patient cohort, imaging modalities, and stratifiers used. Few studies performed validation in an independent cohort.

DISCUSSION

The literature has several methodological limitations including lack of sufficient algorithm development descriptions and standard definitions. We make recommendations to improve model validation including addressing key clinical questions, providing sufficient description of AI methods and validating findings in independent datasets. Collaborative approaches between experts in AI and medicine will help achieve the promising potential of AI tools in practice.

HIGHLIGHTS

There has been a rapid expansion in the use of machine learning for diagnosis and prognosis in neurodegenerative disease Most studies (71%) relied on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with no other individual dataset used more than five times There has been a recent rise in the use of more complex discriminative models (e.g., neural networks) that performed better than other classifiers for classification of AD vs healthy controls We make recommendations to address methodological considerations, addressing key clinical questions, and validation We also make recommendations for the field more broadly to standardize outcome measures, address gaps in the literature, and monitor sources of bias.

Differential Study of Retinal Thicknesses in the Eyes of Alzheimer's Patients, Multiple Sclerosis Patients and Healthy Subjects

Multiple sclerosis (MS) and Alzheimer's disease (AD) cause retinal thinning that is detectable in vivo using optical coherence tomography (OCT). To date, no papers have compared the two diseases in terms of the structural differences they produce in the retina. The purpose of this study is to analyse and compare the neuroretinal structure in MS patients, AD patients and healthy subjects using OCT. Spectral domain OCT was performed on 21 AD patients, 33 MS patients and 19 control subjects using the Posterior Pole protocol. The area under the receiver operating characteristic (AUROC) curve was used to analyse the differences between the cohorts in nine regions of the retinal nerve fibre layer (RNFL), ganglion cell layer (GCL), inner plexiform layer (IPL) and outer nuclear layer (ONL). The main differences between MS and AD are found in the ONL, in practically all the regions analysed (AUROCFOVEAL = 0.80, AUROCPARAFOVEAL = 0.85, AUROCPERIFOVEAL = 0.80, AUROC_PMB = 0.77, AUROCPARAMACULAR = 0.85, AUROCINFERO_NASAL = 0.75, AUROCINFERO_TEMPORAL = 0.83), and in the paramacular zone (AUROCPARAMACULAR = 0.75) and infero-temporal quadrant (AUROCINFERO_TEMPORAL = 0.80) of the GCL. In conclusion, our findings suggest that OCT data analysis could facilitate the differential diagnosis of MS and AD.

A limbic-predominant amnestic neurodegenerative syndrome associated with TDP-43 pathology

Limbic-predominant age-related TDP-43 encephalopathy (LATE) is a neuropathologically-defined disease that affects 40% of persons in advanced age, but its associated neurological syndrome is not defined. LATE neuropathological changes (LATE-NC) are frequently comorbid with Alzheimer's disease neuropathologic changes (ADNC). When seen in isolation, LATE-NC have been associated with a predominantly amnestic profile and slow clinical progression. We propose a set of clinical criteria for a limbic-predominant amnestic neurodegenerative syndrome (LANS) that is highly associated with LATE-NC but also other pathologic entities. The LANS criteria incorporate core, standard and advanced features that are measurable in vivo, including older age at evaluation, mild clinical syndrome, disproportionate hippocampal atrophy, impaired semantic memory, limbic hypometabolism, absence of neocortical degenerative patterns and low likelihood of neocortical tau, with degrees of certainty (highest, high, moderate, low). We operationalized this set of criteria using clinical, imaging and biomarker data to validate its associations with clinical and pathologic outcomes. We screened autopsied patients from Mayo Clinic (n = 922) and ADNI (n = 93) cohorts and applied the LANS criteria to those with an antemortem predominant amnestic syndrome (Mayo, n = 165; ADNI, n = 53). ADNC, ADNC/LATE-NC and LATE-NC accounted for 35%, 37% and 4% of cases in the Mayo cohort, respectively, and 30%, 22%, and 9% of cases in the ADNI cohort, respectively. The LANS criteria effectively categorized these cases, with ADNC having the lowest LANS likelihoods, LATE-NC patients having the highest likelihoods, and ADNC/LATE-NC patients having intermediate likelihoods. A logistic regression model using the LANS features as predictors of LATE-NC achieved a balanced accuracy of 74.6% in the Mayo cohort, and out-of-sample predictions in the ADNI cohort achieved a balanced accuracy of 73.3%. Patients with high LANS likelihoods had a milder and slower clinical course and more severe temporo-limbic degeneration compared to those with low likelihoods. Stratifying ADNC/LATE-NC patients from the Mayo cohort according to their LANS likelihood revealed that those with higher likelihoods had more temporo-limbic degeneration and a slower rate of cognitive decline, and those with lower likelihoods had more lateral temporo-parietal degeneration and a faster rate of cognitive decline. The implementation of LANS criteria has implications to disambiguate the different driving etiologies of progressive amnestic presentations in older age and guide prognosis, treatment, and clinical trials. The development of in vivo biomarkers specific to TDP-43 pathology are needed to refine molecular associations between LANS and LATE-NC and precise antemortem diagnoses of LATE.

Explainable Machine Learning with Pairwise Interactions for Predicting Conversion from Mild Cognitive Impairment to Alzheimer's Disease Utilizing Multi-Modalities Data

BACKGROUND

Predicting cognition decline in patients with mild cognitive impairment (MCI) is crucial for identifying high-risk individuals and implementing effective management. To improve predicting MCI-to-AD conversion, it is necessary to consider various factors using explainable machine learning (XAI) models which provide interpretability while maintaining predictive accuracy. This study used the Explainable Boosting Machine (EBM) model with multimodal features to predict the conversion of MCI to AD during different follow-up periods while providing interpretability.

METHODS

This retrospective case-control study is conducted with data obtained from the ADNI database, with records of 1042 MCI patients from 2006 to 2022 included. The exposures included in this study were MRI biomarkers, cognitive scores, demographics, and clinical features. The main outcome was AD conversion from aMCI during follow-up. The EBM model was utilized to predict aMCI converting to AD based on three feature combinations, obtaining interpretability while ensuring accuracy. Meanwhile, the interaction effect was considered in the model. The three feature combinations were compared in different follow-up periods with accuracy, sensitivity, specificity, and AUC-ROC. The global and local explanations are displayed by importance ranking and feature interpretability plots.

RESULTS

The five-years prediction accuracy reached 85% (AUC = 0.92) using both cognitive scores and MRI markers. Apart from accuracies, we obtained features' importance in different follow-up periods. In early stage of AD, the MRI markers play a major role, while for middle-term, the cognitive scores are more important. Feature risk scoring plots demonstrated insightful nonlinear interactive associations between selected factors and outcome. In one-year prediction, lower right inferior temporal volume (<9000) is significantly associated with AD conversion. For two-year prediction, low left inferior temporal thickness (<2) is most critical. For three-year prediction, higher FAQ scores (>4) is the most important. During four-year prediction, APOE4 is the most critical. For five-year prediction, lower right entorhinal volume (<1000) is the most critical feature.

CONCLUSIONS

The established glass-box model EBMs with multimodal features demonstrated a superior ability with detailed interpretability in predicting AD conversion from MCI. Multi features with significant importance were identified. Further study may be of significance to determine whether the established prediction tool would improve clinical management for AD patients.

Piecing it together: atrophy profiles of hippocampal subfields relate to cognitive impairment along the Alzheimer's disease spectrum

Introduction

People with Alzheimer's disease (AD) experience more rapid declines in their ability to form hippocampal-dependent memories than cognitively normal healthy adults. Degeneration of the whole hippocampal formation has previously been found to covary with declines in learning and memory, but the associations between subfield-specific hippocampal neurodegeneration and cognitive impairments are not well characterized in AD. To improve prognostic procedures, it is critical to establish in which hippocampal subfields atrophy relates to domain-specific cognitive declines among people along the AD spectrum. In this study, we examine high-resolution structural magnetic resonance imaging (MRI) of the medial temporal lobe and extensive neuropsychological data from 29 amyloid-positive people on the AD spectrum and 17 demographically-matched amyloid-negative healthy controls.

Methods

Participants completed a battery of neuropsychological exams including select tests of immediate recollection, delayed recollection, and general cognitive status (i.e., performance on the Mini-Mental State Examination [MMSE] and Montreal Cognitive Assessment [MoCA]). Hippocampal subfield volumes (CA1, CA2, CA3, dentate gyrus, and subiculum) were measured using a dedicated MRI slab sequence targeting the medial temporal lobe and used to compute distance metrics to quantify AD spectrum-specific atrophic patterns and their impact on cognitive outcomes.

Results

Our results replicate prior studies showing that CA1, dentate gyrus, and subiculum hippocampal subfield volumes were significantly reduced in AD spectrum participants compared to amyloid-negative controls, whereas CA2 and CA3 did not exhibit such patterns of atrophy. Moreover, degeneration of the subiculum along the AD spectrum was linked to a significant decline in general cognitive status measured by the MMSE, while degeneration scores of the CA1 and dentate gyrus were more widely associated with declines on the MMSE and tests of learning and memory.

Discussion

These findings provide evidence that subfield-specific patterns of hippocampal degeneration, in combination with cognitive assessments, may constitute a sensitive prognostic approach and could be used to better track disease trajectories among individuals on the AD spectrum.

A comparison of neuroelectrophysiology databases

As data sharing has become more prevalent, three pillars - archives, standards, and analysis tools - have emerged as critical components in facilitating effective data sharing and collaboration. This paper compares four freely available intracranial neuroelectrophysiology data repositories: Data Archive for the BRAIN Initiative (DABI), Distributed Archives for Neurophysiology Data Integration (DANDI), OpenNeuro, and Brain-CODE. The aim of this review is to describe archives that provide researchers with tools to store, share, and reanalyze both human and non-human neurophysiology data based on criteria that are of interest to the neuroscientific community. The Brain Imaging Data Structure (BIDS) and Neurodata Without Borders (NWB) are utilized by these archives to make data more accessible to researchers by implementing a common standard. As the necessity for integrating large-scale analysis into data repository platforms continues to grow within the neuroscientific community, this article will highlight the various analytical and customizable tools developed within the chosen archives that may advance the field of neuroinformatics.

Recent diagnostic techniques for the detection of Alzheimer's disease: a short review

Alzheimer's disease (AD) is a neurological condition that affects millions of individuals around the world and for which there are few effective therapies. Dementia is characterized by the formation of senile plaques and neurofibrillary tangles, which is followed by neurotoxicity, which results in memory loss and mortality. Pathogenesis occurs several years before the onset of disease. As the disease-modifying drugs are most effective in the early stages of Alzheimer's disease, biomarkers for early detection of disease and their development are crucial. This review discusses the diagnostic utility, benefits, and limitations of traditional techniques such as neuroimaging, cognitive testing, positron emission tomography, and biomarkers, as well as the novel techniques such as artificial intelligence, machine learning, immunotherapy, and blood test approaches for early detection, understanding, and treatment of AD.

Identifying underlying patterns in Alzheimer's disease trajectory: a deep learning approach and Mendelian randomization analysis

Background

Alzheimer's disease (AD) is a heterogeneously progressive neurodegeneration disorder with varied rates of deterioration, either between subjects or within different stages of a certain subject. Estimating the course of AD at early stages has treatment implications. We aimed to analyze disease progression to identify distinct patterns in AD trajectory.

Methods

We proposed a deep learning model to identify underlying patterns in the trajectory from cognitively normal (CN) to a state of mild cognitive impairment (MCI) to AD dementia, by jointly predicting time-to-conversion and clustering out distinct subgroups characterized by comprehensive features as well as varied progression rates. We designed and validated our model on the ADNI dataset (1370 participants). Prediction of time-to-conversion in AD trajectory was used to validate the expression of the identified patterns. Causality between patterns and time-to-conversion was further inferred using Mendelian randomization (MR) analysis. External validation was performed on the AIBL dataset (233 participants).

Findings

The proposed model clustered out patterns characterized by significantly different biomarkers and varied progression rates. The discovered patterns also showed a strong prediction ability, as indicated by hazard ratio (CN→MCI, HR = 3.51, p < 0.001; MCI→AD, HR = 8.11, p < 0.001), C-Index (CN→MCI, 0.618; MCI→AD, 0.718), and AUC (CN→MCI, 3 years 0.802, 5 years 0.876; MCI→AD, 3 years 0.914, 5 years 0.957). In the external validation cohort, our model demonstrated competitive performance on conversion time prediction (CN→MCI, C-Index = 0.693; MCI→AD, C-Index = 0.752). Moreover, suggestive associations between CN→MCI/MCI→AD patterns with four/three SNPs were mediated and MR analysis indicated a causal link between MCI→AD patterns and time-to-conversion in the first three years.

Interpretation

Our proposed model identifies biologically and clinically meaningful patterns from real-world data and provides promising performance on time-to-conversion prediction in AD trajectory, which could promote the understanding of disease progression, facilitate clinical trial design, and provide potential for decision-making.

Funding

The National Key Research and Development Program of China, the Key R&D Program of Zhejiang, and the National Nature Science Foundation of China.

Modulation of associations between education years and cortical volume in Alzheimer's disease vulnerable brain regions by Aβ deposition and APOE ε4 carrier status in cognitively normal older adults

Background

Education years, as a measure of cognitive reserve, have been shown to affect the progression of Alzheimer's disease (AD), both pathologically and clinically. However, inconsistent results have been reported regarding the association between years of education and intermediate structural changes in AD-vulnerable brain regions, particularly when AD risk factors were not considered during the preclinical phase.

Objective

This study aimed to examine how Aβ deposition and APOE ε4 carrier status moderate the relationship between years of education and cortical volume in AD-vulnerable regions among cognitively normal older adults.

Methods

A total of 121 participants underwent structural MRI, [18F] flutemetamol PET-CT imaging, and neuropsychological battery assessment. Multiple regression analysis was conducted to examine the interaction between years of education and the effects of potential modifiers on cortical volume. The associations between cortical volume and neuropsychological performance were further explored in subgroups categorized based on AD risk factors.

Results

The cortical volume of the left lateral occipital cortex and bilateral fusiform gyrus demonstrated a significant differential association with years of education, depending on the presence of Aβ deposition and APOE ε4 carrier status. Furthermore, a significant relationship between the cortical volume of the bilateral fusiform gyrus and AD-nonspecific cognitive function was predominantly observed in individuals without AD risk factors.

Conclusion

AD risk factors exerted varying influences on the association between years of education and cortical volume during the preclinical phase. Further investigations into the long-term implications of these findings would enhance our understanding of cognitive reserves in the preclinical stages of AD.

Automated Learning for Deformable Medical Image Registration by Jointly Optimizing Network Architectures and Objective Functions

Deformable image registration plays a critical role in various tasks of medical image analysis. A successful registration algorithm, either derived from conventional energy optimization or deep networks, requires tremendous efforts from computer experts to well design registration energy or to carefully tune network architectures with respect to medical data available for a given registration task/scenario. This paper proposes an automated learning registration algorithm (AutoReg) that cooperatively optimizes both architectures and their corresponding training objectives, enabling non-computer experts to conveniently find off-the-shelf registration algorithms for various registration scenarios. Specifically, we establish a triple-level framework to embrace the searching for both network architectures and objectives with a cooperating optimization. Extensive experiments on multiple volumetric datasets and various registration scenarios demonstrate that AutoReg can automatically learn an optimal deep registration network for given volumes and achieve state-of-the-art performance. The automatically learned network also improves computational efficiency over the mainstream UNet architecture from 0.558 to 0.270 seconds for a volume pair on the same configuration.

Multi-Group Tensor Canonical Correlation Analysis

Tensor Canonical Correlation Analysis (TCCA) is a commonly employed statistical method utilized to examine linear associations between two sets of tensor datasets. However, the existing TCCA models fail to adequately address the heterogeneity present in real-world tensor data, such as brain imaging data collected from diverse groups characterized by factors like sex and race. Consequently, these models may yield biased outcomes. In order to surmount this constraint, we propose a novel approach called Multi-Group TCCA (MG-TCCA), which enables the joint analysis of multiple subgroups. By incorporating a dual sparsity structure and a block coordinate ascent algorithm, our MG-TCCA method effectively addresses heterogeneity and leverages information across different groups to identify consistent signals. This novel approach facilitates the quantification of shared and individual structures, reduces data dimensionality, and enables visual exploration. To empirically validate our approach, we conduct a study focused on investigating correlations between two brain positron emission tomography (PET) modalities (AV-45 and FDG) within an Alzheimer's disease (AD) cohort. Our results demonstrate that MG-TCCA surpasses traditional TCCA in identifying sex-specific cross-modality imaging correlations. This heightened performance of MG-TCCA provides valuable insights for the characterization of multimodal imaging biomarkers in AD.

Recent progress in transformer-based medical image analysis

The transformer is primarily used in the field of natural language processing. Recently, it has been adopted and shows promise in the computer vision (CV) field. Medical image analysis (MIA), as a critical branch of CV, also greatly benefits from this state-of-the-art technique. In this review, we first recap the core component of the transformer, the attention mechanism, and the detailed structures of the transformer. After that, we depict the recent progress of the transformer in the field of MIA. We organize the applications in a sequence of different tasks, including classification, segmentation, captioning, registration, detection, enhancement, localization, and synthesis. The mainstream classification and segmentation tasks are further divided into eleven medical image modalities. A large number of experiments studied in this review illustrate that the transformer-based method outperforms existing methods through comparisons with multiple evaluation metrics. Finally, we discuss the open challenges and future opportunities in this field. This task-modality review with the latest contents, detailed information, and comprehensive comparison may greatly benefit the broad MIA community.