Large, multi-site, heterogeneous brain imaging datasets are increasingly required for the training, validation, and testing of advanced deep learning (DL)-based automated tools, including structural magnetic resonance (MR) image-based diagnostic and treatment monitoring approaches. When assembling a number of smaller datasets to form a larger dataset, understanding the underlying variability between different acquisition and processing protocols across the aggregated dataset (termed “batch effects”) is critical. The presence of variation in the training dataset is important as it more closely reflects the true underlying data distribution and, thus, may enhance the overall generalizability of the tool. However, the impact of batch effects must be carefully evaluated in order to avoid undesirable effects that, for example, may reduce performance measures. Batch effects can result from many sources, including differences in acquisition equipment, imaging technique and parameters, as well as applied processing methodologies. Their impact, both beneficial and adversarial, must be considered when developing tools to ensure that their outputs are related to the proposed clinical or research question (i.e., actual disease-related or pathological changes) and are not simply due to the peculiarities of underlying batch effects in the aggregated dataset. We reviewed applications of DL in structural brain MR imaging that aggregated images from neuroimaging datasets, typically acquired at multiple sites. We examined datasets containing both healthy control participants and patients that were acquired using varying acquisition protocols. First, we discussed issues around Data Access and enumerated the key characteristics of some commonly used publicly available brain datasets. Then we reviewed methods for correcting batch effects by exploring the two main classes of approaches: Data Harmonization that uses data standardization, quality control protocols or other similar algorithms and procedures to explicitly understand and minimize unwanted batch effects; and Domain Adaptation that develops DL tools that implicitly handle the batch effects by using approaches to achieve reliable and robust results. In this narrative review, we highlighted the advantages and disadvantages of both classes of DL approaches, and described key challenges to be addressed in future studies.

Summary: Objectives: Alzheimer's Disease (AD) is one of the most common neurodegenerative diseases, resulting in progressive cognitive decline, and so accurate and timely AD diagnosis is of critical importance. To this end, various medical technologies and computer-aided diagnosis (CAD), ranging from biosensors and raw signals to medical imaging, have been used to provide information about the state of AD. In this survey, we aim to provide a review on CAD systems for automated AD detection, focusing on different data types: namely, signals and sensors, medical imaging, and electronic medical records (EMR). Methods: We explored the literature on automated AD detection from 2022-2023. Specifically, we focused on various data resources and reviewed several preprocessing and learning methodologies applied to each data type, as well as evaluation metrics for model performance evaluation. Further, we focused on challenges, future perspectives, and recommendations regarding automated AD diagnosis. Results: Compared to other modalities, medical imaging was the most common data type. The prominent modality was Magnetic Resonance Imaging (MRI). In contrast, studies based on EMR data type were marginal because EMR is mostly used for AD prediction rather than detection. Several challenges were identified: data scarcity and bias, imbalanced datasets, missing information, anonymization, lack of standardization, and explainability. Conclusion: Despite recent developments in automated AD detection, improving the trustworthiness and performance of these models, and combining different data types will improve usability and reliability of CAD tools for early AD detection in the clinical practice.

Brain aging is a regional phenomenon, a facet that remains relatively under-explored within the realm of brain age prediction research using machine learning methods. Voxel-level predictions can provide localized brain age estimates that can provide granular insights into the regional aging processes. This is essential to understand the differences in aging trajectories in healthy versus diseased subjects. In this work, a deep learning-based multitask model is proposed for voxel-level brain age prediction from T1-weighted magnetic resonance images. The proposed model outperforms the models existing in the literature and yields valuable clinical insights when applied to both healthy and diseased populations. Regional analysis is performed on the voxel-level brain age predictions to understand aging trajectories of known anatomical regions in the brain and show that there exist disparities in regional aging trajectories of healthy subjects compared to ones with underlying neurological disorders such as Dementia and more specifically, Alzheimer’s disease. Our code is available at https://github.com/nehagianchandani/Voxel-level-brain-age-prediction