Hippocampal representations for deep learning on Alzheimer's disease

Sex- and region-specific cortical and hippocampal whole genome transcriptome profiles from control and APP/PS1 Alzheimer's disease mice

A variety of Alzheimer's disease (AD) mouse models has been established and characterized within the last decades. To get an integrative view of the sophisticated etiopathogenesis of AD, whole genome transcriptome studies turned out to be indispensable. Here we carried out microarray data collection based on RNA extracted from the retrosplenial cortex and hippocampus of age-matched, eight months old male and female APP/PS1 AD mice and control animals to perform sex- and brain region specific analysis of transcriptome profiles. The results of our studies reveal novel, detailed insight into differentially expressed signature genes and related fold changes in the individual APP/PS1 subgroups. Gene ontology and Venn analysis unmasked that intersectional, upregulated genes were predominantly involved in, e.g., activation of microglial, astrocytic and neutrophilic cells, innate immune response/immune effector response, neuroinflammation, phagosome/proteasome activation, and synaptic transmission. The number of (intersectional) downregulated genes was substantially less in the different subgroups and related GO categories included, e.g., the synaptic vesicle docking/fusion machinery, synaptic transmission, rRNA processing, ubiquitination, proteasome degradation, histone modification and cellular senescence. Importantly, this is the first study to systematically unravel sex- and brain region-specific transcriptome fingerprints/signature genes in APP/PS1 mice. The latter will be of central relevance in future preclinical and clinical AD related studies, biomarker characterization and personalized medicinal approaches.

Early Diagnosing and Transformation Prediction of Alzheimer's Disease Using Multi-Scaled Self-Attention Network on Structural MRI Images with Occlusion Sensitivity Analysis

BACKGROUND

Structural magnetic resonance imaging (sMRI) is vital for early Alzheimer's disease (AD) diagnosis, though confirming specific biomarkers remains challenging. Our proposed Multi-Scale Self-Attention Network (MUSAN) enhances classification of cognitively normal (CN) and AD individuals, distinguishing stable (sMCI) from progressive mild cognitive impairment (pMCI).

OBJECTIVE

This study leverages AD structural atrophy properties to achieve precise AD classification, combining different scales of brain region features. The ultimate goal is an interpretable algorithm for this method.

METHODS

The MUSAN takes whole-brain sMRI as input, enabling automatic extraction of brain region features and modeling of correlations between different scales of brain regions, and achieves personalized disease interpretation of brain regions. Furthermore, we also employed an occlusion sensitivity algorithm to localize and visualize brain regions sensitive to disease.

RESULTS

Our method is applied to ADNI-1, ADNI-2, and ADNI-3, and achieves high performance on the classification of CN from AD with accuracy (0.93), specificity (0.82), sensitivity (0.96), and area under curve (AUC) (0.95), as well as notable performance on the distinguish of sMCI from pMCI with accuracy (0.85), specificity (0.84), sensitivity (0.74), and AUC (0.86). Our sensitivity masking algorithm identified key regions in distinguishing CN from AD: hippocampus, amygdala, and vermis. Moreover, cingulum, pallidum, and inferior frontal gyrus are crucial for sMCI and pMCI discrimination. These discoveries align with existing literature, confirming the dependability of our model in AD research.

CONCLUSION

Our method provides an effective AD diagnostic and conversion prediction method. The occlusion sensitivity algorithm enhances deep learning interpretability, bolstering AD research reliability.

Reinforcement-Learning-Based Localization of Hippocampus for Alzheimer's Disease Detection

Alzheimer's disease (AD) is a progressive neurodegenerative disorder primarily impacting memory and cognitive functions. The hippocampus serves as a key biomarker associated with AD. In this study, we present an end-to-end automated approach for AD detection by introducing a reinforcement-learning-based technique to localize the hippocampus within structural MRI images. Subsequently, this localized hippocampus serves as input for a deep convolutional neural network for AD classification. We model the agent-environment interaction using a Deep Q-Network (DQN), encompassing both a convolutional Target Net and Policy Net. Furthermore, we introduce an integrated loss function that combines cross-entropy and contrastive loss to effectively train the classifier model. Our approach leverages a single optimal slice extracted from each subject's 3D sMRI, thereby reducing computational complexity while maintaining performance comparable to volumetric data analysis methods. To evaluate the effectiveness of our proposed localization and classification framework, we compare its performance to the results achieved by supervised models directly trained on ground truth hippocampal regions as input. The proposed approach demonstrates promising performance in terms of classification accuracy, F1-score, precision, and recall. It achieves an F1-score within an error margin of 3.7% and 1.1% and an accuracy within an error margin of 6.6% and 1.6% when compared to the supervised models trained directly on ground truth masks, all while achieving the highest recall score.