Искусственные разведывательные методологии для ранней диагностики точности и индивидуализированных терапевтических стратегий в нейро-офтальмических и нейродегенеративных патологиях.

1. Introduction

The early diagnosis and prognosis of neurodegenerative diseases, such as Alzheimer’s disease (AD), Parkinson’s disease (PD), and amyotrophic lateral sclerosis (ALS), as well as neuro-ophthalmic disorders like multiple sclerosis (MS), neuromyelitis optica (NMO), and myelin oligodendrocyte glycoprotein (MOG) antibody disease, represent some of the most pressing challenges in clinical neurology and ophthalmology [ 1 , 2 , 3 ]. These diseases typically progress insidiously, with subtle signs appearing long before significant clinical manifestations become evident [ 4 , 5 ]. In particular, conditions affecting both the central and peripheral nervous systems, including those impacting the visual pathways and ocular structures, often present with early symptoms such as optic neuritis or visual field defects that are frequently overlooked or misdiagnosed [ 6 , 7 ]. Early detection is critical to slowing or halting disease progression and improving patient outcomes.

Despite significant advancements in diagnostic tools, many of these conditions are diagnosed only after substantial neurological or visual decline has occurred, reducing the effectiveness of treatments [ 8 , 9 , 10 ]. Thus, identifying reliable biomarkers for early detection remains crucial in enabling timely intervention and improving the prognosis for affected patients [ 11 , 12 ]. Recent advancements in neuroimaging, particularly ultra-high-field magnetic resonance imaging (UHF-MRI) at 7 Tesla (T) and beyond, have significantly enhanced our ability to detect abnormalities with unprecedented precision [ 13 , 14 ]. These cutting-edge imaging systems can identify subtle structural changes, such as hippocampal atrophy in Alzheimer’s disease, nigral degeneration in Parkinson’s disease, or optic nerve atrophy in MS and NMO, long before they become clinically apparent [ 15 , 16 ]. Similarly, advanced diffusion tensor imaging (DTI) allows for the assessment of white matter integrity, revealing early microstructural damage in both brain and optic nerve tissues that previously went undetected [ 17 , 18 ].

These technologies provide critical insights for early diagnosis, but their effectiveness is often limited by the sheer complexity and volume of the data they generate. Artificial intelligence (AI) is revolutionizing the field of neuroimaging by offering sophisticated solutions to this data complexity [ 19 , 20 , 21 ]. Deep learning algorithms, including convolutional neural networks (CNNs) and transformer-based models, are increasingly capable of performing tasks such as brain and optic nerve segmentation, volume measurement, and pathology identification with exceptional accuracy—often surpassing human capabilities [ 22 , 23 , 24 ]. AI’s integration with neuroimaging has unlocked new possibilities, particularly through the fusion of multimodal data—combining structural and functional MRI, positron emission tomography (PET), and genetic markers—into unified diagnostic models [ 25 , 26 ]. This approach allows for the early identification of neurodegenerative and neuro-ophthalmic changes in asymptomatic individuals, facilitating earlier interventions and potentially improving patient outcomes [ 27 , 28 ].

Furthermore, the development of next-generation PET tracers targeting amyloid plaques, tau, alpha-synuclein aggregates, and inflammatory markers has provided molecular insights into the pathological processes driving diseases like Alzheimer’s, Parkinson’s, and MS [ 29 , 30 ]. The synergy between advanced neuroimaging techniques and AI analytics enhances diagnostic accuracy and supports the development of personalized treatment strategies tailored to individual patients’ neurobiological profiles [ 31 , 32 ]. While the potential of these technologies is substantial, their clinical implementation is still hindered by challenges such as data heterogeneity, the need for large-scale validation studies, and ethical concerns related to AI-driven systems [ 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 ]. This review explores the current landscape of advanced neuroimaging and AI technologies, highlighting their potential to transform the early detection, prognosis, and treatment of both neurodegenerative and neuro-ophthalmic disorders, while also addressing the obstacles that must be overcome to integrate these innovations into routine clinical practice.

2. Advances in Neuroimaging and AI Integration

Diffusion MRI Techniques

Diffusion tensor imaging (DTI) has been widely used for assessing the integrity of white matter [ 41 , 42 , 43 , 44 ], providing valuable insights into microstructural changes occurring in neurodegenerative [ 45 , 46 , 47 , 48 , 49 , 50 ] and associated disorders [ 51 , 52 ]. DTI operates by measuring the anisotropic diffusion of water molecules along axonal fibers, serving as a proxy for the coherence and structural integrity of white matter tracts [ 53 ]. However, the limitations of DTI lie in its inability to disentangle overlapping microstructural changes in different tissue compartments, particularly in regions where axonal or cellular complexity is higher, such as in optic nerve and visual pathway structures. This shortfall has driven the evolution of more sophisticated diffusion imaging techniques [ 54 ].

Neurite Orientation Dispersion and Density Imaging (NODDI) builds upon DTI by employing a multi-compartment biophysical model to separately quantify neurite density and orientation dispersion [ 55 ]. This allows for a more detailed assessment of tissue microarchitecture and has proven especially useful in distinguishing subtle changes within structurally complex regions, such as those impacted by inflammatory and degenerative processes. NODDI enables the isolation of intracellular, extracellular, and isotropic diffusion components, facilitating the identification of early pathological changes. For example, in Parkinson’s disease, NODDI has demonstrated higher sensitivity than DTI in detecting alterations in the substantia nigra, a key motor-related structure, and similar sensitivity may extend to optic radiations and visual cortex regions where early changes can parallel motor-related pathophysiology [ 56 , 57 , 58 , 59 ].

Diffusion Kurtosis Imaging (DKI), another advanced diffusion MRI technique, quantifies the non-Gaussian behavior of water diffusion, enabling a more detailed characterization of tissue complexity and heterogeneity [ 60 ]. DKI provides metrics such as mean kurtosis (MK), which reflect microstructural complexity and can capture subtle tissue changes not visible through conventional diffusion metrics. In Alzheimer’s and Parkinson’s diseases, DKI has identified early gray matter changes, such as those in the hippocampus or cortical regions, and its sensitivity has similarly been extended to white matter pathways critical for sensory and integrative processing [ 61 , 62 , 63 ]. The ability of DKI to detect preclinical tissue changes makes it a potential biomarker for monitoring both neural and peripheral axonal integrity.

AI models, particularly machine learning techniques such as random forest classifiers, have been instrumental in leveraging the multidimensional data generated by NODDI and DKI for enhanced diagnostic precision [ 64 ]. By integrating neurite density and dispersion metrics with kurtosis-derived features, these algorithms can identify subtle patterns of pathology across brain regions and visual sensory pathways. For instance, studies training models on multimodal diffusion data have achieved up to 94% classification accuracy in distinguishing early-stage Alzheimer’s from healthy controls [ 65 ]. Such applications underscore the potential of these imaging modalities when paired with AI to dissect intricate, region-specific changes in diseases with diffuse pathophysiology. The fusion of these advanced techniques highlights their promise in enabling earlier intervention and in offering mechanistic insights into diseases affecting both central and peripheral nervous systems, including the optic nerve and its connections [ 66 ].

Next-Generation Positron Emission Tomography (PET) Tracers

Positron Emission Tomography (PET) has remained a cornerstone of molecular neuroimaging, offering an unparalleled ability to visualize and quantify the in vivo accumulation of pathological proteins central to neurodegenerative and inflammatory processes [ 67 ]. The advent of next-generation PET tracers has markedly enhanced the sensitivity and specificity of PET imaging, particularly in disorders characterized by the aggregation of misfolded proteins such as tau, amyloid-beta, and alpha-synuclein, as well as in conditions marked by neuroinflammatory activity [ 30 , 68 ].

Second-generation tau PET tracers, including 18F-PI-2620 and 18F-MK-6240, have demonstrated superior binding selectivity compared to their predecessors, enabling more accurate quantification of tau pathology [ 69 , 70 , 71 ]. Tau PET imaging has proven instrumental not only in diagnosing Alzheimer’s disease but also in distinguishing tauopathies from other forms of dementia with sensitivities and specificities exceeding 90% [ 72 , 73 , 74 ]. The precision of these tracers has implications for detecting subtle tau-related changes, including those within the visual pathways, where tau pathology can manifest in early neurodegenerative or ocular-related conditions. These high-fidelity tracers provide insights into disease progression, particularly when tau pathology begins to affect structures like the visual cortex or optic radiations, enabling earlier intervention [ 75 , 76 , 77 ].

For synucleinopathies, such as Parkinson’s disease and Lewy body dementia, the development of PET tracers targeting α-synuclein aggregates represents a groundbreaking advancement [ 78 , 79 , 80 ]. Although still under clinical evaluation, tracers like 11C-MODAG-001 have shown promise in preclinical studies, with the potential to visualize synuclein deposits in regions critical to motor and sensory processing, including structures implicated in visual–motor integration [ 81 , 82 ]. These advancements could pave the way for pre-symptomatic detection of α-synucleinopathies, broadening the applicability of PET imaging to conditions where early sensory or visual deficits emerge [ 83 , 84 , 85 ].

AI-driven analysis tools, particularly deep learning algorithms, are further enhancing the diagnostic utility of PET imaging by automating and refining image interpretation [ 86 , 87 , 88 ]. Convolutional neural networks (CNNs), including advanced 3D CNN architectures, have been effectively applied to PET datasets, achieving diagnostic accuracies that rival expert interpretation. For example, AI models analyzing 18F-flortaucipir PET scans for Alzheimer’s detection have reported diagnostic accuracy rates as high as 98.8% [ 89 , 90 , 91 , 92 , 93 ]. These technologies can also facilitate the integration of PET data with structural and diffusion imaging modalities, creating multimodal frameworks capable of capturing early changes in both cortical and subcortical structures, including those relevant to visual processing.

By automating PET scan analysis, AI significantly reduces the reliance on manual interpretation, accelerating clinical workflows and enabling more widespread adoption of PET imaging [ 28 , 94 , 95 ]. This is particularly relevant for conditions where dynamic or multimodal imaging is required to monitor disease progression or response to targeted therapies. The integration of PET imaging with advanced AI systems holds tremendous potential for unraveling complex pathologies that affect interconnected brain and sensory systems, enabling personalized diagnostic and therapeutic approaches.

Multi-Modal Integration

One of the most transformative advancements in the application of AI to neuroimaging is its ability to integrate data from multiple imaging modalities—such as structural MRI, functional MRI (fMRI), PET, and genetic data—into unified diagnostic frameworks [ 96 , 97 ]. This multimodal approach provides a comprehensive understanding of diseases that affect interconnected systems, such as neurodegenerative and neuro-ophthalmic disorders, by capturing structural, functional, and molecular insights that single-modality imaging often misses [ 19 , 98 ]. For example, in diseases like MS, NMO, and MOG antibody disease, where the visual system is frequently involved, such integration enables the detection of both central and peripheral pathology. Transformer-based AI models, such as the Vision Transformer (ViT), have demonstrated remarkable utility in processing multimodal neuroimaging data [ 99 , 100 ]. While inspired by the transformer architecture originally developed for natural language processing, ViTs were specifically designed for image-based tasks and have been successfully adapted for 3D medical imaging. This adaptation enables ViTs to capture long-range dependencies within neural and visual structures [ 101 ]. For multimodal integration, the use of standardized brain map structures, such as MNI or Talairach templates, is essential and commonly employed in neuroimaging studies to align and normalize data from various modalities. This ensures consistency in analyzing regions like the optic radiations, lateral geniculate nucleus (LGN), and visual cortex while mitigating variability due to differences in patient positioning or scanningprotocols. This also reduces variability due to differences in patient positioning and scanning protocols, allowing AI models to more accurately detect subtle alterations associated with early inflammatory or degenerative changes. For example, a study using 3D ViT models to classify Alzheimer’s disease from healthy controls achieved an accuracy of 96.7%, outperforming traditional CNN-based models [ 102 ]. In neuro-ophthalmic applications, ViT models can analyze the optic radiations, lateral geniculate nucleus (LGN), and visual cortex, detecting subtle alterations associated with early inflammatory or degenerative changes.

Multimodal Transformer networks, such as the Multimodal Transformer for Alzheimer’s Disease (MT-AD), similarly exemplify the power of integrating diverse datasets. The MT-AD framework fuses data from structural MRI, fMRI, PET imaging, and genetic profiles, achieving a remarkable area under the receiver operating characteristic curve (AUC) of 0.98 in early Alzheimer’s detection [ 25 , 94 ]. In neuro-ophthalmic disorders, this integration could detect disruptions in the visual pathway, including optic nerve damage (as seen in MS, NMO, and MOG antibody disease) or cortical involvement in the visual cortex, which may precede overt clinical symptoms. By capturing cross-modal patterns of structural degeneration and metabolic changes, AI systems can identify early biomarkers in both the brain and the visual system [ 90 , 92 , 93 ].

Graph Neural Networks (GNNs) further enhance multimodal analysis by modeling connectivity patterns across brain networks [ 103 , 104 ]. The Brain Connectivity Graph Neural Network (BC-GNN) integrates data from MRI, PET, and diffusion tensor imaging (DTI) to map functional and structural networks with exceptional precision [ 105 ]. For example, BC-GNN has been shown to distinguish early-stage Parkinson’s disease from healthy controls with an accuracy of 92% [ 106 , 107 ]. When applied to neuro-ophthalmic diseases, GNNs could reveal disruptions in connectivity between the visual cortex, LGN, and other sensory processing regions. This approach enables the identification of subtle connectivity changes that traditional imaging methods might miss, particularly in diseases where the visual system serves as a critical early indicator of broader neurological dysfunction.

The integration of multimodal imaging, driven by AI, holds significant potential for transforming the diagnosis and management of neuro-ophthalmic disorders ( Table 1 ). To ensure consistency across modalities, spatial normalization techniques and uniform brain map structures, such as MNI or Talairach templates, are crucial. For example, in MS, the combination of structural MRI to assess optic nerve integrity, fMRI to evaluate visual cortex activity, and PET to detect inflammatory markers along the visual pathway benefits from the alignment of all modalities to a common brain template. This unified framework enhances the reliability of the integrated data, providing a clearer understanding of disease progression.

Translational Impact

The clinical translation of these advanced neuroimaging and AI technologies is rapidly advancing, with significant implications for the diagnosis, prognosis, and treatment of neurodegenerative diseases [ 31 , 32 ]. The integration of AI-driven systems with neuroimaging has the potential to revolutionize not only early detection but also personalized medicine in neurology ( Table 2 ), offering a more tailored and effective approach to patient care [ 33 , 34 ]. One notable example of translational research is the development of adaptive deep brain stimulation (DBS) systems for Parkinson’s disease [ 108 , 109 ]. Traditional DBS therapy uses a fixed stimulation pattern, which can provide symptomatic relief but does not account for the dynamic nature of the disease [ 110 ]. Adaptive DBS systems leverage real-time feedback from neuroimaging and AI algorithms to adjust stimulation parameters based on the patient’s current brain state [ 111 , 112 ]. By continuously monitoring brain activity and adjusting the stimulation in real time, these systems can optimize therapeutic effects, improving motor function while reducing side effects such as dyskinesia [ 113 , 114 ]. Some studies have reported up to a 30% improvement in motor symptoms when using adaptive DBS systems compared to conventional methods [ 115 ]. AI-enhanced retinal imaging is another area where significant advancements are being made in the non-invasive detection of neurodegenerative diseases [ 45 , 48 ]. Optical coherence tomography (OCT) imaging of the retina has gained traction as a low-cost, easily accessible method for identifying early neurodegenerative changes [ 47 , 116 ]. Machine learning algorithms trained on OCT images can detect subtle changes in retinal morphology that correlate with brain pathology, offering a potential diagnostic tool for early-stage disease detection [ 117 , 118 ]. Studies have reported sensitivities and specificities exceeding 90% for detecting early-stage Alzheimer’s disease (AD) and Parkinson’s disease (PD) using AI models applied to OCT data [ 119 , 120 ].

Privacy and Data Sharing

Further advancements in federated learning have the potential to address the privacy and data-sharing challenges inherent in medical research, particularly in neuroimaging studies [ 121 , 122 ]. Federated learning enables AI models to be trained on decentralized datasets across multiple institutions without the need to centralize sensitive patient data [ 123 ]. This approach could accelerate the development of AI-driven diagnostic tools by providing access to larger, more diverse datasets while maintaining patient privacy [ 124 , 125 ]. Federated learning has already shown promise in enabling collaborative research across medical institutions and could be particularly valuable for creating AI models capable of generalizing across diverse populations and clinical settings [ 126 , 127 ]. Another emerging frontier is the integration of neuroimaging biomarkers with liquid biopsy techniques, such as blood-based assays for amyloid-β, tau, and other neurodegenerative proteins [ 128 , 129 ]. Combining neuroimaging data with molecular markers from blood samples could provide a more comprehensive, non-invasive method for diagnosing and tracking disease progression [ 130 , 131 ]. AI models could be used to integrate these data streams, enhancing their predictive power and enabling a more personalized approach to monitoring disease progression [ 132 , 133 ]. Early detection through blood biomarkers, combined with neuroimaging, holds great potential for detecting diseases like Alzheimer’s and Parkinson’s in their pre-symptomatic stages, allowing for earlier interventions that may slow disease progression [ 134 , 135 ].

The integration of AI-driven multimodal imaging systems with advanced neurophysiological monitoring also opens up new possibilities for the real-time assessment of brain function in clinical settings [ 136 , 137 ]. For example, coupling structural and functional MRI with electrophysiological data from techniques such as electroencephalography (EEG) or magnetoencephalography (MEG) could provide real-time insights into brain activity and connectivity [ 138 , 139 ]. AI models trained on these multimodal data could detect changes in brain networks that precede clinical symptoms, allowing for early intervention and potentially slowing the onset of neurodegenerative diseases [ 140 , 141 ].

Impact on Neurorehabilitation

Beyond diagnosis and monitoring, these technologies also have great potential to transform neurorehabilitation. For example, functional MRI (fMRI) can be used to track changes in brain activity as patients engage in rehabilitative tasks [ 142 , 143 , 144 ]. When combined with real-time AI analysis, fMRI data could guide adaptive neurorehabilitation strategies, providing personalized feedback to patients and clinicians to enhance recovery [ 145 , 146 ]. Similarly, AI-driven analysis of diffusion MRI could identify regions of the brain that are most vulnerable to neurodegeneration, allowing for targeted rehabilitative interventions aimed at preserving brain function [ 147 , 148 ]. Further, while transcranial stimulation, including techniques like transcranial magnetic stimulation (TMS) and transcranial direct current stimulation (tDCS), has shown promise in modulating brain activity, its application in AI-directed neurostimulation remains an emerging field [ 149 , 150 ]. Current studies focus on using AI to optimize stimulation parameters, but direct evidence supporting its clinical efficacy in neurodegenerative diseases is limited. Further research is needed to validate these methods in controlled settings before widespread adoption [ 151 , 152 , 153 ].

3. Challenges in Integrating AI into Clinical Practice for Diagnosis and Treatment

The application of AI faces significant technical challenges, primarily due to the inherent variability of neuroimaging data [ 21 , 35 , 154 , 155 , 156 , 157 ]. This variability stems from multiple sources, such as differences in MRI scanners, imaging protocols, and patient positioning, all of which introduce inconsistencies that can impact AI model accuracy and generalizability [ 158 ]. To mitigate position-related challenges, the use of uniform brain map structures, such as MNI or Talairach templates, is critical and widely adopted in neuroimaging studies. These standardized coordinate systems ensure consistent alignment of brain regions across scans and subjects, even when using the same scanner. By applying spatial normalization techniques based on these templates, positional variability is significantly reduced, enhancing the reliability of AI models and supporting cross-study comparisons in diverse clinical settings.

4. Technical Challenges: Variability in Neuroimaging Data and Its Impact on AI Models

Scanner variability is a key challenge in neuroimaging, particularly when comparing MRI systems with different field strengths (e.g., 1.5 T vs. 3 T) [ 159 , 160 , 161 , 162 , 163 , 164 ]. Even within the same manufacturer, MRI scanners can exhibit variations in image characteristics due to differences in gradient performance [ 121 , 122 , 154 , 165 , 166 ], radiofrequency coil designs [ 155 , 163 , 164 , 165 , 167 , 168 , 169 ], and reconstruction algorithms [ 35 , 164 , 165 , 170 , 171 , 172 , 173 ]. These physical differences in field strength and hardware configurations can result in inconsistencies in image contrast, resolution, and signal-to-noise ratio, complicating the application of AI algorithms trained on data from specific scanner types [ 174 ]. While advancements in scanner technology can reduce certain artifacts, the fundamental physical changes associated with varying field strengths cannot be completely eliminated through manufacturing strategies alone. These inherent differences must be accounted for during data analysis to maintain accurate and consistent AI model performance.

Protocol variability presents a significant challenge in neuroimaging. Imaging protocols can vary significantly between institutions and even within the same institution over time. Differences in pulse sequences, acquisition parameters (such as repetition time [TR], echo time [TE], and flip angle), contrast agent usage, and image plane orientation contribute to disparities in tissue contrasts and artifact patterns [ 175 ]. These variations can negatively impact the generalizability of AI models, especially when trained on data from specific protocols that may not perform well across a range of imaging settings. However, the use of mapping data, such as standardized brain templates or spatial normalization techniques, can significantly minimize these protocol-related issues. By aligning data from different scanners and protocols to a common coordinate system, mapping data ensures consistency across diverse imaging protocols, improving the reliability and generalizability of AI models in clinical applications [ 176 ].

Patient positioning and motion during scans introduce significant challenges in neuroimaging, as variations in head orientation, motion artifacts, and physiological noise (e.g., respiratory and cardiac cycles) can cause distortions and misalignments in images, potentially compromising AI model performance [ 177 , 178 ]. However, the use of a uniform brain map structure—such as standardized brain atlases (e.g., MNI or Talairach)—can help mitigate these challenges. By applying spatial normalization techniques, individual brain scans can be aligned to a common template, reducing the variability caused by differences in patient positioning. Advanced registration algorithms further correct for head position differences, ensuring consistent alignment across subjects and scans. Additionally, probabilistic atlases and statistical parametric mapping (SPM) can account for inter-subject variability, providing a more robust framework for analyzing neuroimaging data. These approaches, when integrated with AI models, enhance the accuracy and reliability of neuroimaging analysis in clinical settings, helping to overcome the inevitable variability inherent in patient positioning and motion during scans [ 178 ].

Another source of variability arises in image preprocessing. Different preprocessing pipelines used to prepare neuroimaging data for analysis can introduce inconsistencies in the final images. Techniques such as bias field correction, skull stripping, registration, normalization, and intensity standardization can all vary, potentially affecting AI model performance if not consistently applied [ 179 , 180 ].

Longitudinal changes present additional challenges in studies tracking disease progression over time. Factors such as scanner upgrades, protocol updates, or patient-specific changes unrelated to the disease being studied can introduce confounding variables that AI models must account for in order to accurately track disease progression [ 181 ].

Finally, multi-site data integration introduces complexities that AI models must overcome to ensure their robustness. Data from different sites can differ in terms of patient demographics, clinical assessment protocols, and data quality control measures. Such site-specific biases can hinder the generalizability of AI models, necessitating careful strategies to ensure that models are effective across diverse clinical environments [ 182 , 183 ].

Regulatory and Legal Barriers: Ensuring Compliance and Addressing Liability

These technical challenges directly tie into regulatory concerns. The U.S. Food and Drug Administration (FDA) requires substantial evidence that AI-based diagnostic devices maintain performance across diverse conditions, including variations in scanner types, protocols, and patient populations [ 184 , 185 ]. This requirement poses significant hurdles for AI developers, as they must demonstrate the ability of their models to remain reliable and accurate across different clinical settings. The FDA requires AI models to be validated under regulatory pathways such as the 510(k) pathway or Premarket Approval (PMA) processes [ 171 , 186 ]. For example, AI models must be robust to scanner variability, requiring validation studies using data from multiple scanner models and manufacturers to ensure consistent performance [ 49 ]. Similarly, AI models must be able to handle protocol variability, potentially requiring the development of protocol-agnostic architectures or extensive fine-tuning capabilities to maintain performance across different imaging protocols [ 187 ]. AI systems may also need to demonstrate resilience to motion artifacts, possibly requiring the integration of motion correction algorithms or the ability to flag highly motion-corrupted images for manual review [ 188 ]. Furthermore, the FDA may mandate preprocessing standardization or require models to be robust to variations in preprocessing methods, which could drive the development of industry-wide standards for neuroimaging AI applications [ 189 ]. For AI systems designed to track disease progression, the FDA may require evidence of longitudinal consistency, ensuring that the model performs effectively despite scanner upgrades, protocol changes, or other temporal variations [ 190 ]. Lastly, the FDA is likely to require validation of AI model performance across multiple sites and diverse patient populations to ensure multi-site generalizability, which may involve extensive multi-center validation studies [ 158 ].

Liability for misdiagnosis due to image variability is also a primary concern. If an AI system misdiagnoses a patient because of such variability, questions about responsibility arise. Determining liability—whether it lies with the AI developer, healthcare provider, or imaging facility—may require new legal frameworks to address AI-assisted diagnoses [ 169 ]. Additionally, data sharing and privacy are critical concerns. Sharing medical imaging data across institutions is necessary to develop robust AI models, but it raises privacy issues and must comply with regulations like HIPAA in the United States and GDPR in the European Union. This creates a tension between the need for diverse training datasets and the protection of patient privacy rights [ 122 ]. Informed consent also becomes a crucial issue. Patients must be informed that AI systems are being used in their diagnosis, including the potential for errors due to variability in the data. Communicating the risks and benefits of AI-assisted diagnosis to patients is a legal challenge in itself [ 35 ]. Furthermore, existing FDA regulatory approval pathways, such as the 510(k) and PMA processes, may not be well-suited to the unique characteristics of AI systems that continuously learn and adapt. New regulatory frameworks may be necessary to address these concerns [ 186 ]. Post-market surveillance is another area where traditional methods may be inadequate. AI systems that evolve over time must be monitored to ensure they do not introduce new risks or errors, which may require new approaches to post-market monitoring and regulation [ 171 ]. Finally, international harmonization of regulations becomes increasingly important as AI systems are deployed globally. Different regulations across countries regarding medical AI and data privacy could complicate the widespread adoption of AI tools, necessitating efforts toward international regulatory alignment [ 164 ].

Future Directions: Addressing Variability Through AI Innovations

Several potential solutions and future directions are being explored to address the challenges currently faced in the application of artificial intelligence (AI) in healthcare and neuroimaging ( Table 3 ). One promising approach is adaptive neuroimaging harmonization (ANH), which utilizes transfer learning and domain adaptation techniques to mitigate issues related to scanner and protocol variability. While ANH holds great promise, regulatory concerns remain regarding how these adaptive techniques fit into current clinical frameworks [ 191 , 192 , 193 ]. Another important direction is federated learning, which enables AI models to be trained on distributed datasets without centralizing sensitive patient data. This approach addresses privacy concerns while maintaining access to diverse training data, ensuring that models are robust and applicable across varied patient populations [ 121 , 168 , 194 , 195 ].

As AI models become increasingly integrated into healthcare settings, Explainable AI (XAI) has emerged as a critical component for the adoption and acceptance of AI technologies. The “black box” nature of many AI models, particularly deep learning systems, has raised concerns over transparency and accountability in clinical practice. XAI addresses this challenge by providing mechanisms to interpret and understand AI model predictions, ensuring that clinicians can trust AI-generated decisions and integrate them confidently into patient care. A key challenge in XAI development is to provide clinically relevant, interpretable models that allow healthcare professionals to understand how AI systems arrive at their conclusions. Local interpretability methods, such as LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive exPlanations), enable the generation of explanations that highlight the key features influencing AI predictions. These techniques have demonstrated success in enhancing the transparency of AI models applied to complex neuroimaging tasks, such as brain tumor detection and early diagnosis of neurodegenerative diseases.

Moreover, XAI is increasingly being integrated with advanced models that combine rule-based systems, gradient-based techniques, and attention mechanisms. These hybrid frameworks offer a more nuanced approach to explaining AI decisions, enabling clinicians to gain deeper insights into the reasoning behind each prediction. Such developments are particularly valuable in medical imaging, where accurate and interpretable results are critical for clinical decision-making. The application of XAI is especially important in neuroimaging, where AI systems must demonstrate transparency to gain regulatory approval and clinician acceptance. The integration of domain knowledge and expert input into XAI frameworks will help ensure that AI tools remain aligned with clinical workflows and are trusted by medical professionals. Furthermore, as AI becomes more embedded in healthcare applications like AI of Medical Things (AIoMT), XAI will play a key role in ensuring that these systems are both reliable and understandable.

Looking ahead, several challenges remain for XAI in healthcare. One significant hurdle is balancing the complexity of AI models with their interpretability, ensuring that explanations do not oversimplify but still remain clinically relevant. Establishing standardized metrics for evaluating the quality and effectiveness of XAI explanations is another crucial task, as it will make it easier to compare different approaches and select the most suitable ones for specific clinical applications. Additionally, ensuring that XAI methods can be effectively integrated into clinical workflows is essential, providing explanations that are actionable and enhance decision-making processes. Mitigating bias in AI models through explainability is also a critical concern, as it helps ensure fair and equitable outcomes across diverse patient populations.

In conclusion, the development of explainable AI is essential for the continued adoption of AI in healthcare. By providing transparency, improving model trustworthiness, and ensuring that AI tools align with clinical practices, XAI will be crucial in overcoming the regulatory, ethical, and practical challenges of implementing AI technologies in neuroimaging and healthcare. As XAI continues to evolve, it will enable AI to make a significant impact in precision medicine, ensuring that these technologies are both effective and ethical in their application. The ongoing research and development in XAI will not only enhance the interpretability of AI models but also foster greater trust and collaboration between AI systems and healthcare professionals, ultimately leading to improved patient outcomes and more efficient healthcare delivery.

5. Discussion

The convergence of advanced neuroimaging and AI in the diagnosis and treatment of neurodegenerative diseases has the potential to significantly alter the clinical landscape. However, while the promise of these technologies is vast, their integration into routine clinical practice presents both opportunities and challenges that require careful consideration.

At the heart of this transformation is the ability to detect subtle, early changes in the brain that were previously undetectable. Advanced imaging techniques like diffusion MRI (e.g., NODDI and DKI) offer clinicians a powerful tool to observe microstructural alterations before cognitive or motor symptoms appear. Early detection could mean that interventions are started at a point where they are more effective, potentially delaying disease progression or improving quality of life. This shift from reactive to proactive healthcare is a paradigm shift that clinicians can take advantage of, allowing for more targeted, timely interventions. The real challenge for clinicians, however, is in translating these early imaging findings into actionable clinical decisions.

The real-world application of these technologies goes beyond simply diagnosing disease earlier; it is about enhancing the precision and personalization of treatment. Imagine a scenario where a clinician is able to combine advanced neuroimaging findings with AI-driven insights to not only detect the disease but also predict its trajectory based on individual brain structure and function. AI tools can help clinicians identify the subtle distinctions in disease progression that might otherwise go unnoticed, allowing for more personalized therapeutic approaches. For example, AI-enhanced models could suggest whether a patient with early Alzheimer’s is likely to experience rapid cognitive decline or whether their disease might remain relatively stable for an extended period. This level of precision allows for more informed treatment plans and the ability to tailor interventions to each patient’s unique presentation, ensuring that patients receive the most appropriate care based on their specific needs.

While the potential for personalized care is tremendous, the integration of these advanced technologies into clinical practice is not without its challenges. One of the most significant hurdles is ensuring that clinicians can trust and understand the outputs of AI models. AI systems excel at processing complex data and detecting patterns, but the clinical decision-making process requires context—an understanding of the patient’s full medical history, symptoms, and personal circumstances. AI can provide invaluable insights, but clinicians must remain at the forefront of the decision-making process, using AI as a tool to augment their expertise, not replace it. The integration of AI into clinical practice should not lead to a dehumanization of care, where patients become data points in a system, but rather should enhance the clinician’s ability to make well-informed, empathetic decisions.

Moreover, the successful use of AI and neuroimaging in clinical practice requires clinicians to have the appropriate training and support. AI systems are powerful, but they are only as effective as the people using them. The current medical education system, which primarily trains clinicians in traditional methods of diagnosis and treatment, must evolve to ensure that healthcare providers are equipped with the skills to work alongside advanced AI technologies. This could mean more emphasis on data literacy, AI ethics, and the interpretation of complex neuroimaging data as part of medical training. Additionally, clinicians must have the infrastructure and tools necessary to integrate these technologies into their daily workflows. This includes having access to AI-driven diagnostic tools, real-time neuroimaging feedback, and seamless systems for managing and interpreting multimodal data.

Another key consideration is the ethical and regulatory landscape. The widespread use of AI in healthcare raises questions about data privacy, algorithmic bias, and accountability. Who is responsible if an AI system makes an error in diagnosis or treatment? What safeguards are in place to protect patient data when it is processed by machine learning models? These are critical questions that clinicians must be prepared to answer as they begin to incorporate AI into their practice. Furthermore, as AI models are continuously trained on new data, they may evolve in ways that are not immediately predictable. This raises concerns about the long-term reliability and consistency of AI systems. Clinicians need to feel confident that the systems they rely on are safe, transparent, and governed by ethical principles that prioritize patient welfare.

6. Conclusions

Looking to the future, the combination of AI and advanced neuroimaging offers a vision of personalized medicine that was once unimaginable. It holds the potential to revolutionize not only how we diagnose and treat neurodegenerative diseases, but also how we think about patient care as a whole. The ability to tailor treatments to individual patients, predict disease progression, and intervene at earlier stages could significantly alter the course of neurodegenerative diseases. However, for this vision to be realized, several challenges must be overcome.

While AI’s potential in healthcare is vast, its integration into clinical practice requires careful attention to several critical issues. Data limitations, including the need for large, high-quality, and diverse datasets, remain a significant challenge. AI models rely on comprehensive datasets to provide accurate predictions, but these datasets are not always available, particularly in underserved or underrepresented patient populations. Additionally, bias in AI models, arising from skewed or unrepresentative data, can exacerbate existing healthcare disparities, making it essential to address fairness in data collection and model training.

Another key challenge is the interpretability of AI models. Many AI systems, especially those based on deep learning, function as “black boxes”, where even experts cannot easily understand how a decision was made. This lack of transparency raises concerns about the trustworthiness of AI-generated diagnoses. For AI to gain widespread adoption in healthcare, it is critical to develop explainable AI (XAI) frameworks that allow clinicians to interpret AI predictions and make informed decisions based on these insights. Explainability is not only necessary for clinical confidence but also for ensuring regulatory compliance and ethical accountability in AI-assisted decision-making.

Moreover, regulatory hurdles remain a significant barrier to the widespread deployment of AI in clinical settings. AI systems must meet rigorous standards before they can be integrated into healthcare workflows, and these standards must ensure that AI tools are both effective and safe for patient care. Addressing these regulatory challenges will require ongoing collaboration between AI developers, healthcare providers, and regulatory bodies.

Ethical concerns regarding data privacy and patient consent also need to be resolved. As AI systems rely on large amounts of patient data, ensuring that data is handled securely and ethically is crucial. This involves maintaining compliance with privacy regulations (such as GDPR and HIPAA) while balancing the need for diverse data to train robust AI models.

In light of these challenges, the future success of AI in healthcare depends on collaboration between clinicians, researchers, and AI developers. Only by working together can we ensure that AI technologies are implemented in ways that enhance, rather than disrupt, patient care. This collaborative effort will not only address the technical and ethical challenges AI presents but also promote a patient-centered approach, ensuring that AI tools support clinicians in their efforts to provide the best possible care.

Ultimately, the integration of AI and advanced neuroimaging into clinical practice requires a balanced approach—one that combines technological innovation, clinical expertise, ethical oversight, and patient-centered care. By addressing the challenges of data quality, interpretability, bias, and regulatory compliance, we can ensure that AI not only improves diagnostic accuracy and treatment outcomes but also fosters greater trust and transparency. Embracing these tools thoughtfully and carefully will pave the way for a new era of personalized, data-driven healthcare, ensuring that AI is used responsibly to improve patient outcomes and transform the healthcare landscape.

Acknowledgments

We would like to express our sincere gratitude to Skyler Wu for her generous consideration in granting the APC waiver for our manuscript. The authors declare that no generative AI was used in producing this manuscript, and take all credit for the work.

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Author Contributions

Conceptualization: R.K., E.W. and J.O. Methodology: E.W., J.Y. and A.T. Software: A.T. and R.J. Validation: A.T., J.O. and P.P. Formal Analysis: E.W. and D.A. Investigation: P.P., R.N. and J.S. Resources: J.O., R.J. and D.A. Data Curation: Not applicable, as no primary data collection was performed. Writing—Original Draft Preparation: R.K., E.W. and D.A. Writing—Review and Editing: R.K., E.W., J.O., P.P., D.A., J.S., J.Y., R.N., R.J. and A.T. Visualization: J.Y. and A.T. Supervision: J.O., R.J. and P.P. Project Administration: J.O. and P.P. Funding Acquisition: Not applicable. All authors have read and agreed to the published version of the manuscript.

Conflicts of Interest

The authors declare no conflict of interest.

References

1. Dugger B.N. Dickson D.W. Pathology of neurodegenerative diseases Cold Spring Harb. Perspect. Biol. 2017 9 a028035 10.1101/cshperspect.a028035 28062563 PMC5495060

2. Hou Y. Dan X. Babbar M. Wei Y. Hasselbalch S.G. Croteau D.L. Bohr V.A. Ageing as a risk factor for neurodegenerative disease Nat. Rev. Neurol. 2019 15 565 581 10.1038/s41582-019-0244-7 31501588

3. Erkkinen M.G. Kim M.O. Geschwind M.D. Clinical neurology and epidemiology of the major neurodegenerative diseases Cold Spring Harb. Perspect. Biol. 2018 10 a033118 10.1101/cshperspect.a033118 28716886 PMC5880171

4. Sperling R.A. Aisen P.S. Beckett L.A. Craft S. Fagan A.M. Iwatsubo T. Jack C.R. Jr. Kaye J. Montine T.J. Park D.C. Toward defining the preclinical stages of Alzheimer’s disease: Recommendations from the National Institute on Aging-Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer’s disease Alzheimers Dement. 2011 7 280 292 10.1016/j.jalz.2011.03.003 21514248 PMC3220946

5. Postuma R.B. Berg D. Prodromal Parkinson’s disease: The decade past, the decade to come Mov. Disord. 2019 34 665 675 10.1002/mds.27670 30919499

6. London A. Benhar I. Schwartz M. The retina as a window to the brain-from eye research to CNS disorders Nat. Rev. Neurol. 2013 9 44 53 10.1038/nrneurol.2012.227 23165340

7. Albers M.W. Gilmore G.C. Kaye J. Murphy C. Wingfield A. Bennett D.A. Boxer A.L. Buchman A.S. Cruickshanks K.J. Devanand D.P. At the interface of sensory and motor dysfunctions and Alzheimer’s disease Alzheimers Dement. 2015 11 70 98 10.1016/j.jalz.2014.04.514 25022540 PMC4287457

8. Scheltens P. De Strooper B. Kivipelto M. Holstege H. Chételat G. Teunissen C.E. Cummings J. van der Flier W.M. Alzheimer’s disease Lancet 2021 397 1577 1590 10.1016/S0140-6736(20)32205-4 33667416 PMC8354300

9. Malek N. Grosset D.G. Improving the diagnosis of Parkinson’s disease Practitioner 2015 259 15 19

10. Bateman R.J. Xiong C. Benzinger T.L. Fagan A.M. Goate A. Fox N.C. Marcus D.S. Cairns N.J. Xie X. Blazey T.M. Clinical and biomarker changes in dominantly inherited Alzheimer’s disease N. Engl. J. Med. 2012 367 795 804 10.1056/NEJMoa1202753 22784036 PMC3474597

11. Jack C.R. Jr. Bennett D.A. Blennow K. Carrillo M.C. Dunn B. Haeberlein S.B. Holtzman D.M. Jagust W. Jessen F. Karlawish J. NIA-AA Research Framework: Toward a biological definition of Alzheimer’s disease Alzheimers Dement. 2018 14 535 562 10.1016/j.jalz.2018.02.018 29653606 PMC5958625

12. Hampel H. O’Bryant S.E. Molinuevo J.L. Zetterberg H. Masters C.L. Lista S. Kiddle S.J. Batrla R. Blennow K. Blood-based biomarkers for Alzheimer disease: Mapping the road to the clinic Nat. Rev. Neurol. 2018 14 639 652 10.1038/s41582-018-0079-7 30297701 PMC6211654

13. Trattnig S. Bogner W. Gruber S. Szomolanyi P. Juras V. Robinson S. Zbýň Š. Haneder S. Clinical applications at ultrahigh field (7 T). Where does it make the difference? NMR Biomed. 2016 29 1316 1334 10.1002/nbm.3272 25762432

14. Duyn J.H. The future of ultra-high field MRI and fMRI for study of the human brain Neuroimage 2012 62 1241 1248 10.1016/j.neuroimage.2011.10.065 22063093 PMC3389184

15. Wisse L.E.M. Biessels G.J. Geerlings M.I. A critical appraisal of the hippocampal subfield segmentation package in FreeSurfer Front. Aging Neurosci. 2014 6 261 10.3389/fnagi.2014.00261 25309437 PMC4174865

16. Lehéricy S. Bardinet E. Poupon C. Vidailhet M. François C. 7 Tesla magnetic resonance imaging: A closer look at substantia nigra anatomy in Parkinson’s disease Mov. Disord. 2014 29 1574 1581 10.1002/mds.26043 25308960

17. Alexander A.L. Lee J.E. Lazar M. Field A.S. Diffusion tensor imaging of the brain Neurotherapeutics 2007 4 316 329 10.1016/j.nurt.2007.05.011 17599699 PMC2041910

18. Acosta-Cabronero J. Nestor P.J. Diffusion tensor imaging in Alzheimer’s disease: Insights into the limbic-diencephalic network and methodological considerations Front. Aging Neurosci. 2014 6 266 10.3389/fnagi.2014.00266 25324775 PMC4183111

19. Rathore S. Habes M. Iftikhar M.A. Shacklett A. Davatzikos C. A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer’s disease and its prodromal stages Neuroimage 2017 155 530 548 10.1016/j.neuroimage.2017.03.057 28414186 PMC5511557

20. Shen D. Wu G. Suk H.I. Deep learning in medical image analysis Annu. Rev. Biomed. Eng. 2017 19 221 248 10.1146/annurev-bioeng-071516-044442 28301734 PMC5479722

21. Litjens G. Kooi T. Bejnordi B.E. Setio A.A.A. Ciompi F. Ghafoorian M. van der Laak J.A.W.M. van Ginneken B. Sánchez C.I. A survey on deep learning in medical image analysis Med. Image Anal. 2017 42 60 88 10.1016/j.media.2017.07.005 28778026

22. Lundervold A.S. Lundervold A. An overview of deep learning in medical imaging focusing on MRI Z. Med. Phys. 2019 29 102 127 10.1016/j.zemedi.2018.11.002 30553609

23. Akkus Z. Galimzianova A. Hoogi A. Rubin D.L. Erickson B.J. Deep learning for brain MRI segmentation: State of the art and future directions J. Digit Imaging 2017 30 449 459 10.1007/s10278-017-9983-4 28577131 PMC5537095

24. Varoquaux G. Schwartz Y. Poldrack R.A. Gauthier B. Bzdok D. Poline J.B. Thirion B. Atlases of cognition with large-scale human brain mapping PLoS Comput. Biol. 2018 14 e1006565 10.1371/journal.pcbi.1006565 30496171 PMC6289578

25. Zhang D. Wang Y. Zhou L. Yuan H. Shen D. Multimodal classification of Alzheimer’s disease and mild cognitive impairment Neuroimage 2011 55 856 867 10.1016/j.neuroimage.2011.01.008 21236349 PMC3057360

26. Rieke J. Eitel F. Weygandt M. Haynes J.D. Ritter K. Visualizing convolutional networks for MRI-based diagnosis of Alzheimer’s disease Understanding and Interpreting Machine Learning in Medical Image Computing Applications Springer Berlin/Heidelberg, Germany 2018 24 31

27. Wen J. Thibeau-Sutre E. Diaz-Melo M. Samper-González J. Routier A. Bottani S. Dormont D. Durrleman S. Burgos N. Colliot O. Convolutional neural networks for classification of Alzheimer’s disease: Overview and reproducible evaluation Med. Image Anal. 2020 63 101694 10.1016/j.media.2020.101694 32417716

28. Jo T. Nho K. Saykin A.J. Deep learning in Alzheimer’s disease: Diagnostic classification and prognostic prediction using neuroimaging data Front. Aging Neurosci. 2019 11 220 10.3389/fnagi.2019.00220 31481890 PMC6710444

29. Villemagne V.L. Doré V. Burnham S.C. Masters C.L. Rowe C.C. Imaging tau and amyloid-β proteinopathies in Alzheimer disease and other conditions Nat. Rev. Neurol. 2018 14 225 236 10.1038/nrneurol.2018.9 29449700

30. Leuzy A. Chiotis K. Lemoine L. Gillberg P.G. Almkvist O. Rodriguez-Vieitez E. Nordberg A. Tau PET imaging in neurodegenerative tauopathies—Still a challenge Mol. Psychiatry 2019 24 1112 1134 10.1038/s41380-018-0342-8 30635637 PMC6756230

31. Arbabshirani M.R. Plis S. Sui J. Calhoun V.D. Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls Neuroimage 2017 145 Pt B 137 165 10.1016/j.neuroimage.2016.02.079 27012503 PMC5031516

32. Woo C.W. Chang L.J. Lindquist M.A. Wager T.D. Building better biomarkers: Brain models in translational neuroimaging Nat. Neurosci. 2017 20 365 377 10.1038/nn.4478 28230847 PMC5988350

33. Klöppel S. Abdulkadir A. Jack C.R. Jr. Koutsouleris N. Mourão-Miranda J. Vemuri P. Diagnostic neuroimaging across diseases Neuroimage 2012 61 457 463 10.1016/j.neuroimage.2011.11.002 22094642 PMC3420067

34. Bzdok D. Altman N. Krzywinski M. Statistics versus machine learning Nat. Methods 2018 15 233 234 10.1038/nmeth.4642 30100822 PMC6082636

35. Char D.S. Shah N.H. Magnus D. Implementing machine learning in health care-addressing ethical challenges N. Engl. J. Med. 2018 378 981 983 10.1056/NEJMp1714229 29539284 PMC5962261

36. Trattnig S. Springer E. Bogner W. Hangel G. Strasser B. Dymerska B. Cardoso P.L. Robinson S.D. Key clinical benefits of neuroimaging at 7T Neuroimage 2018 168 477 489 10.1016/j.neuroimage.2016.11.031 27851995 PMC5832016

37. Uğurbil K. Imaging at ultrahigh magnetic fields: History, challenges, and solutions Neuroimage 2018 168 7 32 10.1016/j.neuroimage.2017.07.007 28698108 PMC5758441

38. van der Zwaag W. Schäfer A. Marques J.P. Turner R. Trampel R. Recent applications of UHF-MRI in the study of human brain function and structure: A review NMR Biomed. 2016 29 1274 1288 10.1002/nbm.3275 25762497

39. Düzel E. Acosta-Cabronero J. Berron D. Biessels G.J. Björkman-Burtscher I. Bottlaender M. Bowtell R. Buchem M. Cardenas-Blanco A. Boumezbeur F. European Ultrahigh-Field Imaging Network for Neurodegenerative Diseases (EUFIND) Alzheimers Dement. 2019 11 538 549 10.1016/j.dadm.2019.04.010 PMC6675944 31388558

40. Marques J.P. Norris D.G. How to choose the right MR sequence for your research question at 7T and above? Neuroimage 2018 168 119 140 10.1016/j.neuroimage.2017.04.044 28438666

41. Wisse L.E.M. Chételat G. Daugherty A.M. de Flores R. la Joie R. Mueller S.G. Stark C.E.L. Wang L. Yushkevich P.A. Berron D. Hippocampal subfield volumetry from structural isotropic 1 mm3 MRI scans: A note of caution Hum. Brain Mapp. 2021 42 539 550 10.1002/hbm.25234 33058385 PMC7775994

42. Haast R.A.M. Ivanov D. Uludağ K. The impact of B1+ correction on MP2RAGE cortical T1 and apparent cortical thickness at 7T Hum. Brain Mapp. 2018 39 2412 2425 10.1002/hbm.24011 29457319 PMC5969159

43. Cho Z.H. Oh S.H. Kim J.M. Park S.Y. Kwon D.H. Jeong H.J. Kim Y.B. Chi J.G. Park C.W. Huston J. Direct visualization of Parkinson’s disease by in vivo human brain imaging using 7.0T magnetic resonance imaging Mov. Disord. 2011 26 713 718 10.1002/mds.23465 21506148

44. Bourne R.R.A. Jonas J.B. Bron A.M. Cicinelli M.V. Das A. Flaxman S.R. Friedman D.S. Keeffe J.E. Kempen J.H. Leasher J. Prevalence and causes of vision loss in high-income countries and in Eastern and Central Europe in 2015: Magnitude, temporal trends and projections Br. J. Ophthalmol. 2018 102 575 585 10.1136/bjophthalmol-2017-311258 29545417 PMC5909755

45. den Haan J. Verbraak F.D. Visser P.J. Bouwman F.H. Retinal thickness in Alzheimer’s disease: A systematic review and meta-analysis Alzheimers Dement. 2017 6 162 170 10.1016/j.dadm.2016.12.014 PMC5328759 28275698

46. Zeineh M.M. Chen Y. Kitzler H.H. Hammond R. Vogel H. Rutt B.K. Activated iron-containing microglia in the human hippocampus identified by magnetic resonance imaging in Alzheimer disease Neurobiol. Aging. 2015 36 2483 2500 10.1016/j.neurobiolaging.2015.05.022 26190634 PMC4839298

47. Ting D.S.W. Pasquale L.R. Peng L. Campbell J.P. Lee A.Y. Raman R. Tan G.S.W. Schmetterer L. Keane P.A. Wong T.Y. Artificial intelligence and deep learning in ophthalmology Br. J. Ophthalmol. 2019 103 167 175 10.1136/bjophthalmol-2018-313173 30361278 PMC6362807

48. Cheung C.Y. Ikram M.K. Chen C. Wong T.Y. Imaging retina to study dementia and stroke Prog. Retin Eye Res. 2017 57 89 107 10.1016/j.preteyeres.2017.01.001 28057562

49. Kamnitsas K. Ledig C. Newcombe V.F.J. Simpson J.P. Kane A.D. Menon D.K. Rueckert D. Glocker B. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation Med. Image Anal. 2017 36 61 78 10.1016/j.media.2016.10.004 27865153

50. Wachinger C. Reuter M. Klein T. DeepNAT: Deep convolutional neural network for segmenting neuroanatomy Neuroimage 2018 170 434 445 10.1016/j.neuroimage.2017.02.035 28223187 PMC5563492

51. Basser P.J. Mattiello J. LeBihan D. MR diffusion tensor spectroscopy and imaging Biophys. J. 1994 66 259 267 10.1016/S0006-3495(94)80775-1 8130344 PMC1275686

52. Le Bihan D. Mangin J.F. Poupon C. Clark C.A. Pappata S. Molko N. Chabriat H. Diffusion tensor imaging: Concepts and applications J. Magn. Reson Imaging 2001 13 534 546 10.1002/jmri.1076 11276097

53. Assaf Y. Pasternak O. Diffusion tensor imaging (DTI)-based white matter mapping in brain research: A review J. Mol. Neurosci. 2008 34 51 61 10.1007/s12031-007-0029-0 18157658

54. Jones D.K. Knösche T.R. Turner R. White matter integrity, fiber count, and other fallacies: The do’s and don’ts of diffusion MRI Neuroimage 2013 73 239 254 10.1016/j.neuroimage.2012.06.081 22846632

55. Zhang H. Schneider T. Wheeler-Kingshott C.A. Alexander D.C. NODDI: Practical in vivo neurite orientation dispersion and density imaging of the human brain Neuroimage 2012 61 1000 1016 10.1016/j.neuroimage.2012.03.072 22484410

56. Jelescu I.O. Veraart J. Adisetiyo V. Milla S.S. Novikov D.S. Fieremans E. One diffusion acquisition and different white matter models: How does microstructure predict fractional anisotropy? Neuroimage 2015 107 242 252 10.1016/j.neuroimage.2014.12.009 25498427 PMC4300243

57. Grussu F. Schneider T. Tur C. Yates R.L. Tachrount M. Ianuş A. Yiannakas M.C. Newcombe J. Zhang H. Alexander D.C. Neurite dispersion: A new marker of multiple sclerosis spinal cord pathology? Ann. Clin. Transl. Neurol. 2017 4 663 679 10.1002/acn3.445 28904988 PMC5590517

58. Kamagata K. Hatano T. Okuzumi A. Motoi Y. Abe O. Shimoji K. Kamiya K. Suzuki M. Hori M. Kumamaru K.K. Neurite orientation dispersion and density imaging in the substantia nigra in idiopathic Parkinson disease Eur. Radiol. 2016 26 2567 2577 10.1007/s00330-015-4066-8 26515546

59. Andica C. Kamagata K. Hatano T. Okuzumi A. Saito A. Nakazawa M. Ueda R. Motoi Y. Kamiya K. Hori M. Neurite orientation dispersion and density imaging of the nigrostriatal pathway in Parkinson’s disease: Retrograde degeneration observed by tract-profile analysis Parkinsonism Relat. Disord. 2018 51 55 60 10.1016/j.parkreldis.2018.02.046 29525556

60. Jensen J.H. Helpern J.A. Ramani A. Lu H. Kaczynski K. Diffusional kurtosis imaging: The quantification of non-gaussian water diffusion by means of magnetic resonance imaging Magn. Reson. Med. 2005 53 1432 1440 10.1002/mrm.20508 15906300

61. Fieremans E. Jensen J.H. Helpern J.A. White matter characterization with diffusional kurtosis imaging Neuroimage 2011 58 177 188 10.1016/j.neuroimage.2011.06.006 21699989 PMC3136876

62. Falangola M.F. Jensen J.H. Babb J.S. Hu C. Castellanos F.X. Di Martino A. Ferris S.H. Helpern J.A. Age-related non-Gaussian diffusion patterns in the prefrontal brain J. Magn. Reson. Imaging 2008 28 1345 1350 10.1002/jmri.21604 19025941 PMC2669671

63. Wang J.J. Lin W.Y. Lu C.S. Weng Y.H. Ng S.H. Wang C.H. Liu H.L. Hsieh R.H. Wan Y.L. Wai Y.Y. Parkinson disease: Diagnostic utility of diffusion kurtosis imaging Radiology 2011 261 210 217 10.1148/radiol.11102277 21771952

64. Timmers I. Zhang H. Bastiani M. Jansma B.M. Roebroeck A. Rubio-Gozalbo M.E. White matter microstructure from nonparametric axon diameter distribution mapping Neuroimage 2015 111 530 541

65. Nir T.M. Jahanshad N. Villalon-Reina J.E. Toga A.W. Jack C.R. Weiner M.W. Thompson P.M. Alzheimer’s Disease Neuroimaging Initiative (ADNI) Effectiveness of regional DTI measures in distinguishing Alzheimer’s disease, MCI, and normal aging Neuroimage Clin. 2013 3 180 195 10.1016/j.nicl.2013.07.006 24179862 PMC3792746

66. Dyrba M. Barkhof F. Fellgiebel A. Filippi M. Hausner L. Hauenstein K. Kirste T. Teipel S.J. Predicting prodromal Alzheimer’s disease in subjects with mild cognitive impairment using machine learning classification of multimodal multicenter diffusion-tensor and magnetic resonance imaging data J. Neuroimaging 2015 25 738 747 10.1111/jon.12214 25644739

67. Villemagne V.L. Okamura N. In vivo tau imaging: Obstacles and progress Alzheimers Dement. 2014 10 (Suppl. S3) S254 S264 10.1016/j.jalz.2014.04.013 24924676

68. Okamura N. Harada R. Furumoto S. Arai H. Yanai K. Kudo Y. PET imaging of tau pathology in mild cognitive impairment and Alzheimer’s disease with [18F]THK5351 J. Nucl. Med. 2016 57 221 226

69. Kroth H. Oden F. Molette J. Schieferstein H. Capotosti F. Mueller A. Berndt M. Schmitt-Willich H. Darmency V. Gabellieri E. Discovery and preclinical characterization of [18F]PI-2620, a next-generation tau PET tracer for the assessment of tau pathology in Alzheimer’s disease and other tauopathies Eur. J. Nucl. Med. Mol. Imaging 2019 46 2178 2189 10.1007/s00259-019-04397-2 31264169 PMC6667408

70. Betthauser T.J. Cody K.A. Zammit M.D. Murali D. Converse A.K. Barnhart T.E. Stone C.K. Rowley H.A. Johnson S.C. Christian B.T. In vivo characterization and quantification of neurofibrillary tau PET radioligand 18F-MK-6240 in humans from Alzheimer disease dementia to young controls J. Nucl. Med. 2019 60 93 99 10.2967/jnumed.118.209650 29777006 PMC6354223

71. Lohith T.G. Bennacef I. Vandenberghe R. Vandenbulcke M. Salinas C.A. Declercq R. Reynders T. Telan-Choing N.F. Riffel K. Celen S. Brain imaging of Alzheimer dementia patients and elderly controls with 18F-MK-6240, a PET tracer targeting neurofibrillary tangles J. Nucl. Med. 2019 60 107 114 10.2967/jnumed.118.208215 29880509

72. Ossenkoppele R. Rabinovici G.D. Smith R. Cho H. Schöll M. Strandberg O. Palmqvist S. Mattsson N. Janelidze S. Santillo A. Discriminative accuracy of [18F]flortaucipir positron emission tomography for Alzheimer disease vs other neurodegenerative disorders JAMA 2018 320 1151 1162 10.1001/jama.2018.12917 30326496 PMC6233630

73. Fleisher A.S. Pontecorvo M.J. Devous M.D. Sr. Lu M. Arora A.K. Truocchio S.P. Aldea P. Flitter M. Locascio T. Devine M. Positron emission tomography imaging with [18F]flortaucipir and postmortem assessment of Alzheimer disease neuropathologic changes JAMA Neurol. 2020 77 829 839 10.1001/jamaneurol.2020.0528 32338734 PMC7186920

74. Leuzy A. Smith R. Ossenkoppele R. Santillo A. Borroni E. Klein G. Ohlsson T. Jögi J. Palmqvist S. Mattsson-Carlgren N. Diagnostic performance of RO948 F 18 tau positron emission tomography in the differentiation of Alzheimer disease from other neurodegenerative disorders JAMA Neurol. 2020 77 955 965 10.1001/jamaneurol.2020.0989 32391858 PMC7215644

75. Jack C.R. Jr. Wiste H.J. Schwarz C.G. Lowe V.J. Senjem M.L. Vemuri P. Weigand S.D. Therneau T.M. Knopman D.S. Gunter J.L. Longitudinal tau PET in ageing and Alzheimer’s disease Brain 2018 141 1517 1528 10.1093/brain/awy059 29538647 PMC5917767

76. Ossenkoppele R. Schonhaut D.R. Schöll M. Lockhart S.N. Ayakta N. Baker S.L. O’Neil J.P. Janabi M. Lazaris A. Cantwell A. Tau PET patterns mirror clinical and neuroanatomical variability in Alzheimer’s disease Brain 2016 139 Pt 5 1551 1567 10.1093/brain/aww027 26962052 PMC5006248

77. Pontecorvo M.J. Devous M.D. Sr. Kennedy I. Navitsky M. Lu M. Galante N. Salloway S. Doraiswamy P.M. Southekal S. Arora A.K. A multicentre longitudinal study of flortaucipir (18F) in normal ageing, mild cognitive impairment and Alzheimer’s disease dementia Brain 2019 142 1723 1735 10.1093/brain/awz090 31009046 PMC6536847

78. Koga S. Ono M. Sahara N. Higuchi M. Dickson D.W. Fluorescence and autoradiographic evaluation of tau PET ligand PBB3 to α-synuclein pathology Mov. Disord. 2017 32 884 892 10.1002/mds.27013 28440890 PMC5577807

79. Kuebler L. Buss S. Leonov A. Ryazanov S. Schmidt F. Maurer A. Weckbecker D. Landau A.M. Lillethorup T.P. Knudsen K. [11C]MODAG-001—Towards a PET tracer targeting α-synuclein aggregates Eur. J. Nucl. Med. Mol. Imaging 2020 47 3116 3128 10.1007/s00259-020-05133-x PMC8113290 33369690

80. Marek K. Jennings D. Lasch S. Siderowf A. Tanner C. Simuni T. Coffey C. Kieburtz K. Flagg E. Chowdhury S. The Parkinson Progression Marker Initiative (PPMI) Prog. Neurobiol. 2011 95 629 635 10.1016/j.pneurobio.2011.09.005 21930184 PMC9014725

81. Hooshyar Yousefi B. Shi K. Arzberger T. Wester H.J. Schwaiger M. Yakushev I. Drzezga A. Haass C. Okamura N. Scheiblich H. Translational study of a novel alpha-synuclein PET tracer designed for first-in-human investigating Nucl. Med. Biol. 2021 92 158 170

82. Verdurand M. Levigoureux E. Zeinyeh W. Berthier L. Mendjel-Herda M. Cadarossanesaib F. Bouillot C. Iecker T. Terreux R. Lancelot S. In silico, in vitro, and in vivo evaluation of new candidates for α-synuclein PET imaging Mol. Pharm. 2018 15 3153 3166 10.1021/acs.molpharmaceut.8b00229 29989823

83. Mach R.H. Focused review: Recent developments in the search for alpha-synuclein PET radiotracers J. Nucl. Med. 2021 62 1207 1214

84. Chu W. Zhou D. Gaba V. Liu J. Li S. Peng X. Xu J. Dhavale D. Bagchi D.P. d’Avignon A. Design, synthesis, and characterization of 3-(benzylidene)indolin-2-one derivatives as ligands for α-synuclein fibrils J. Med. Chem. 2015 58 6002 6017 10.1021/acs.jmedchem.5b00571 26177091 PMC4624220

85. Kotzbauer P.T. Tu Z. Mach R.H. Current status of the development of PET radiotracers for imaging alpha synuclein aggregates in Lewy bodies and Lewy neurites Clin. Transl. Imaging 2017 5 3 14 10.1007/s40336-016-0217-4

86. Ding Y. Sohn J.H. Kawczynski M.G. Trivedi H. Harnish R. Jenkins N.W. Lituiev D. Copeland T.P. Aboian M.S. Mari Aparici C. A deep learning model to predict a diagnosis of Alzheimer disease by using 18F-FDG PET of the brain Radiology 2019 290 456 464 10.1148/radiol.2018180958 30398430 PMC6358051

87. Liu M. Cheng D. Wang K. Wang Y. Alzheimer’s Disease Neuroimaging Initiative Multi-modality cascaded convolutional neural networks for Alzheimer’s disease diagnosis Neuroinformatics 2018 16 295 308 10.1007/s12021-018-9370-4 29572601

88. Kang S.K. Seo S. Shin S.A. Byun M.S. Lee D.Y. Kim Y.K. Lee Y. Lee D.S. Lee J.S. Adaptive template generation for amyloid PET using a deep learning approach Hum. Brain Mapp. 2018 39 3769 3778 10.1002/hbm.24210 29752765 PMC6866631

89. Cattell L. Platsch G. Pfeiffer R. Declerck J. Schnabel J.A. Hutton C. Classification of amyloid status using machine learning with histograms of oriented 3D gradients Neuroimage Clin. 2016 12 990 1003 10.1016/j.nicl.2016.05.004 27995065 PMC5153608

90. Lu D. Popuri K. Ding G.W. Balachandar R. Beg M.F. Alzheimer’s Disease Neuroimaging Initiative Multimodal and multiscale deep neural networks for the early diagnosis of Alzheimer’s disease using structural MR and FDG-PET images Sci. Rep. 2018 8 5697 10.1038/s41598-018-22871-z 29632364 PMC5890270

91. Choi H. Jin K.H. Alzheimer’s Disease Neuroimaging Initiative Predicting cognitive decline with deep learning of brain metabolism and amyloid imaging Behav. Brain Res. 2018 344 103 109 10.1016/j.bbr.2018.02.017 29454006

92. Marinescu R.V. Oxtoby N.P. Young A.L. Bron E.E. Toga A.W. Weiner M.W. Barkhof F. Fox N.C. Klein S. Alexander D.C. TADPOLE Challenge: Prediction of longitudinal evolution in Alzheimer’s disease arXiv 2018 1805.03909 10.1007/978-3-030-32281-6_1 PMC7315046 32587957

93. Bhagwat N. Viviano J.D. Voineskos A.N. Chakravarty M.M. Alzheimer’s Disease Neuroimaging Initiative Modeling and prediction of clinical symptom trajectories in Alzheimer’s disease using longitudinal data PLoS Comput. Biol. 2018 14 e1006376 10.1371/journal.pcbi.1006376 30216352 PMC6157905

94. Spasov S. Passamonti L. Duggento A. Liò P. Toschi N. Alzheimer’s Disease Neuroimaging Initiative A parameter-efficient deep learning approach to predict conversion from mild cognitive impairment to Alzheimer’s disease Neuroimage 2019 189 276 287 10.1016/j.neuroimage.2019.01.031 30654174

95. Suk H.I. Lee S.W. Shen D. Alzheimer’s Disease Neuroimaging Initiative Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis Neuroimage 2014 101 569 582 10.1016/j.neuroimage.2014.06.077 25042445 PMC4165842

96. Sui J. Jiang R. Bustillo J. Calhoun V. Neuroimaging-based individualized prediction of cognition and behavior for mental disorders and health: Methods and promises Biol. Psychiatry 2020 88 818 828 10.1016/j.biopsych.2020.02.016 32336400 PMC7483317

97. Plis S.M. Sarwate A.D. Wood D. Dieringer C. Landis D. Reed C. Panta S.R. Turner J.A. Shoemaker J.M. Carter K.W. COINSTAC: A privacy enabled model and prototype for leveraging and processing decentralized brain imaging data Front. Neurosci. 2016 10 365 10.3389/fnins.2016.00365 27594820 PMC4990563

98. Vieira S. Pinaya W.H. Mechelli A. Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: Methods and applications Neurosci. Biobehav. Rev. 2017 74 Pt A 58 75 10.1016/j.neubiorev.2017.01.002 28087243

99. Dosovitskiy A. Beyer L. Kolesnikov A. Weissenborn D. Zhai X. Unterthiner T. Dehghani M. Minderer M. Heigold G. Gelly S. An image is worth 16x16 words: Transformers for image recognition at scale arXiv 2020 2010.11929

100. Khan S. Naseer M. Hayat M. Zamir S.W. Khan F.S. Shah M. Transformers in vision: A survey ACM Comput. Surv. 2022 54 1 41 10.1145/3505244

101. Matsoukas C. Haslum J.F. Söderberg M. Övrelid L. Is it possible to perform “free-viewing” eye-tracking experiments on a smartphone? PeerJ Comput. Sci. 2021 7 e628

102. Nanni L. Ghidoni S. Brahnam S. Handcrafted vs. non-handcrafted features for computer vision classification Pattern Recognit. 2017 71 158 172 10.1016/j.patcog.2017.05.025

103. Parisot S. Ktena S.I. Ferrante E. Lee M. Guerrero R. Glocker B. Rueckert D. Disease prediction using graph convolutional networks: Application to Autism Spectrum Disorder and Alzheimer’s disease Med. Image Anal. 2018 48 117 130 29890408 10.1016/j.media.2018.06.001

104. Li X. Zhou Y. Dvornek N.C. Zhang M. Zhuang J. Ventola P. Duncan J.S. BrainGNN: Interpretable brain graph neural network for fMRI analysis Med. Image Anal. 2021 74 102233 10.1016/j.media.2021.102233 34655865 PMC9916535

105. Ktena S.I. Parisot S. Ferrante E. Rajchl M. Lee M. Glocker B. Rueckert D. Metric learning with spectral graph convolutions on brain connectivity networks Neuroimage 2018 169 431 442 10.1016/j.neuroimage.2017.12.052 29278772

106. Arya D. Olij R. Gupta D.K. Galy-Fajou T. Knoll A. Wulff S. Gallwitz B. Stierstorfer B. Stiller D. Wersching H. Fusing structural and functional MRIs using graph convolutional networks for autism classification Med. Image Anal. 2022 75 102308

107. Zhao Y. Dong Q. Zhang S. Zhang W. Chen H. Jiang X. Guo L. Hu X. Han J. Liu T. Automatic recognition of fMRI-derived functional networks using 3D convolutional neural networks IEEE Trans. Biomed. Eng. 2018 65 1975 1984 10.1109/TBME.2017.2715281 28641239 PMC6146395

108. Little S. Brown P. What brain signals are suitable for feedback control of deep brain stimulation in Parkinson’s disease? Ann. N. Y. Acad. Sci. 2012 1265 9 24 22830645 10.1111/j.1749-6632.2012.06650.x PMC3495297

109. Meidahl A.C. Tinkhauser G. Herz D.M. Cagnan H. Debarros J. Brown P. Adaptive deep brain stimulation for movement disorders: The long road to clinical therapy Mov. Disord. 2017 32 810 819 10.1002/mds.27022 28597557 PMC5482397

110. Parastarfeizabadi M. Kouzani A.Z. Advances in closed-loop deep brain stimulation devices J. Neuroeng. Rehabil. 2017 14 79 28800738 10.1186/s12984-017-0295-1 PMC5553781

111. Swann N.C. de Hemptinne C. Thompson M.C. Miocinovic S. Miller A.M. Gilron R. Ostrem J.L. Chizeck H.J. Starr P.A. Adaptive deep brain stimulation for Parkinson’s disease using motor cortex sensing J. Neural Eng. 2018 15 046006 29741160 10.1088/1741-2552/aabc9b PMC6021210

112. Arlotti M. Marceglia S. Foffani G. Volkmann J. Lozano A.M. Moro E. Cogiamanian F. Prenassi M. Bocci T. Cortese F. Eight-hours adaptive deep brain stimulation in patients with Parkinson disease Neurology 2018 90 e971 e976 10.1212/WNL.0000000000005121 29444973 PMC5858949

113. Tinkhauser G. Pogosyan A. Little S. Beudel M. Herz D.M. Tan H. Brown P. The modulatory effect of adaptive deep brain stimulation on beta bursts in Parkinson’s disease Brain 2017 140 1053 1067 10.1093/brain/awx010 28334851 PMC5382944

114. Velisar A. Syrkin-Nikolau J. Blumenfeld Z. Trager M.H. Afzal M.F. Prabhakar V. Bronte-Stewart H. Dual threshold neural closed loop deep brain stimulation in Parkinson disease patients Brain Stimul. 2019 12 868 876 10.1016/j.brs.2019.02.020 30833216

115. Petrucci M.N. Neuville R.S. Afzal M.F. Velisar A. Anidi C.M. Anderson R.W. Parker J.E. O’Day J.J. Wilkins K.B. Bronte-Stewart H.M. Neural closed-loop deep brain stimulation for freezing of gait Brain Stimul. 2020 13 1320 1322 10.1016/j.brs.2020.06.018 32634599 PMC8189032

116. Sharafi S.M. Sylvestre J.P. Chevrefils C. Soucy J.P. Beaulieu S. Pascoal T.A. Rosa-Neto P. Arbour J.D. Rheaume M.A. Robillard A. Vascular retinal biomarkers improves the detection of the likely cerebral amyloid status from hyperspectral retinal images Alzheimers Dement. 2019 5 610 617 10.1016/j.trci.2019.09.006 31650017 PMC6804547

117. Wisely C.E. Wang D. Henao R. Grewal D.S. Robbins C.B. Whitson H.E. Cousins S.W. Lad E.M. Convolutional neural network to identify symptomatic Alzheimer’s disease using multimodal retinal imaging Br. J. Ophthalmol. 2021 105 990 995 10.1136/bjophthalmol-2020-317659 33243829

118. Koronyo Y. Biggs D. Barron E. Boyer D.S. Pearlman J.A. Au W.J. Kile S.J. Blanco A. Fuchs D.T. Ashfaq A. Retinal amyloid pathology and proof-of-concept imaging trial in Alzheimer’s disease JCI Insight 2017 2 e93621 10.1172/jci.insight.93621 28814675 PMC5621887

119. Shi Z. Zhu Y. Dong M. Yang W. Liu F. Huang Y. Zheng L. Hu Y. Zhu W. The utility of retinal imaging in Alzheimer’s disease Front Neurosci. 2021 15 642208 10.3389/fnins.2021.731614

120. Mahajan D. Votruba M. Can the retina be used to diagnose and plot the progression of Alzheimer’s disease? Acta Ophthalmol. 2017 95 768 777 10.1111/aos.13472 29220126

121. Rieke N. Hancox J. Li W. Milletarì F. Roth H.R. Albarqouni S. Bakas S. Galtier M.N. Landman B.A. Maier-Hein K. The future of digital health with federated learning NPJ Digit. Med. 2020 3 119 10.1038/s41746-020-00323-1 33015372 PMC7490367

122. Kaissis G.A. Makowski M.R. Rückert D. Braren R.F. Secure, privacy-preserving and federated machine learning in medical imaging Nat. Mach. Intell. 2020 2 305 311 10.1038/s42256-020-0186-1

123. Li T. Sahu A.K. Talwalkar A. Smith V. Federated learning: Challenges, methods, and future directions IEEE Signal Process Mag. 2020 37 50 60 10.1109/MSP.2020.2975749

124. Sheller M.J. Edwards B. Reina G.A. Martin J. Pati S. Kotrotsou A. Milchenko M. Xu W. Marcus D. Colen R.R. Federated learning in medicine: Facilitating multi-institutional collaborations without sharing patient data Sci. Rep. 2020 10 12598 10.1038/s41598-020-69250-1 32724046 PMC7387485

125. Xu J. Wang F. Federated learning for healthcare informatics J. Healthc. Inform. Res. 2021 5 1 19 10.1007/s41666-020-00082-4 33204939 PMC7659898

126. Dayan I. Roth H.R. Zhong A. Harouni A. Gentili A. Abidin A.Z. Liu A. Costa A.B. Wood B.J. Tsai C.S. Federated learning for predicting clinical outcomes in patients with COVID-19 Nat. Med. 2021 27 1735 1743 10.1038/s41591-021-01506-3 34526699 PMC9157510

127. Sarma K.V. Harmon S. Sanford T. Roth H.R. Xu Z. Tetreault J. Xu D. Flores M.G. Raman A.G. Kulkarni R. Federated learning improves site performance in multicenter deep learning without data sharing J. Am. Med. Inform. Assoc. 2021 28 1259 1264 10.1093/jamia/ocaa341 33537772 PMC8200268

128. Nakamura A. Kaneko N. Villemagne V.L. Kato T. Doecke J. Doré V. Fowler C. Li Q.X. Martins R. Rowe C. High performance plasma amyloid-β biomarkers for Alzheimer’s disease Nature 2018 554 249 254 10.1038/nature25456 29420472

129. Janelidze S. Mattsson N. Palmqvist S. Smith R. Beach T.G. Serrano G.E. Chai X. Proctor N.K. Eichenlaub U. Zetterberg H. Plasma P-tau181 in Alzheimer’s disease: Relationship to other biomarkers, differential diagnosis, neuropathology and longitudinal progression to Alzheimer’s dementia Nat. Med. 2020 26 379 386 10.1038/s41591-020-0755-1 32123385

130. Palmqvist S. Janelidze S. Stomrud E. Zetterberg H. Karl J. Zink K. Bittner T. Mattsson N. Eichenlaub U. Blennow K. Performance of Fully Automated Plasma Assays as Screening Tests for Alzheimer Disease-Related β-Amyloid Status JAMA Neurol. 2019 76 1060 1069 10.1001/jamaneurol.2019.1632 31233127 PMC6593637

131. Thijssen E.H. La Joie R. Wolf A. Strom A. Wang P. Iaccarino L. Bourakova V. Cobigo Y. Heuer H. Spina S. Diagnostic value of plasma phosphorylated tau181 in Alzheimer’s disease and frontotemporal lobar degeneration Nat. Med. 2020 26 387 397 10.1038/s41591-020-0762-2 32123386 PMC7101073

132. Schindler S.E. Bollinger J.G. Ovod V. Mawuenyega K.G. Li Y. Gordon B.A. Holtzman D.M. Morris J.C. Benzinger T.L.S. Xiong C. High-precision plasma β-amyloid 42/40 predicts current and future brain amyloidosis Neurology 2019 93 e1647 e1659 10.1212/WNL.0000000000008081 31371569 PMC6946467

133. Karikari T.K. Pascoal T.A. Ashton N.J. Janelidze S. Benedet A.L. Rodriguez J.L. Chamoun M. Savard M. Kang M.S. Therriault J. Blood phosphorylated tau 181 as a biomarker for Alzheimer’s disease: A diagnostic performance and prediction modelling study using data from four prospective cohorts Lancet Neurol. 2020 19 422 433 10.1016/S1474-4422(20)30071-5 32333900

134. Preische O. Schultz S.A. Apel A. Kuhle J. Kaeser S.A. Barro C. Gräber S. Kuder-Buletta E. LaFougere C. Laske C. Serum neurofilament dynamics predicts neurodegeneration and clinical progression in presymptomatic Alzheimer’s disease Nat. Med. 2019 25 277 283 10.1038/s41591-018-0304-3 30664784 PMC6367005

135. Mattsson N. Cullen N.C. Andreasson U. Zetterberg H. Blennow K. Association Between Longitudinal Plasma Neurofilament Light and Neurodegeneration in Patients With Alzheimer Disease JAMA Neurol. 2019 76 791 799 10.1001/jamaneurol.2019.0765 31009028 PMC6583067

136. Uhlhaas P.J. Singer W. Neuronal dynamics and neuropsychiatric disorders: Toward a translational paradigm for dysfunctional large-scale networks Neuron 2012 75 963 980 10.1016/j.neuron.2012.09.004 22998866

137. Sitaram R. Ros T. Stoeckel L. Haller S. Scharnowski F. Lewis-Peacock J. Weiskopf N. Blefari M.L. Rana M. Oblak E. Closed-loop brain training: The science of neurofeedback Nat. Rev. Neurosci. 2017 18 86 100 10.1038/nrn.2016.164 28003656

138. Babiloni C. Del Percio C. Lizio R. Noce G. Cordone S. Lopez S. Soricelli A. Ferri R. Pascarelli M.T. Nobili F. Abnormalities of cortical neural synchronization mechanisms in patients with dementia due to Alzheimer’s and Lewy body diseases: An EEG study Neurobiol. Aging 2017 55 143 158 10.1016/j.neurobiolaging.2017.03.030 28454845

139. Mandal P.K. Banerjee A. Tripathi M. Sharma A. A Comprehensive Review of Magnetoencephalography (MEG) Studies for Brain Functionality in Healthy Aging and Alzheimer’s Disease (AD) Front. Comput. Neurosci. 2018 12 60 10.3389/fncom.2018.00060 30190674 PMC6115612

140. Kocagoncu E. Quinn A. Firouzian A. Cooper E. Greve A. Gunn R. Green G. Woolrich M.W. Henson R.N. Lovestone S. Tau pathology in early Alzheimer’s disease is linked to selective disruptions in neurophysiological network dynamics Neurobiol. Aging 2020 92 141 152 10.1016/j.neurobiolaging.2020.03.009 32280029 PMC7269692

141. Canuet L. Pusil S. López M.E. Bajo R. Pineda-Pardo J.Á. Cuesta P. Gálvez G. Gaztelu J.M. Lourido D. García-Ribas G. Network Disruption and Cerebrospinal Fluid Amyloid-Beta and Phospho-Tau Levels in Mild Cognitive Impairment J. Neurosci. 2015 35 10325 10330 10.1523/JNEUROSCI.0704-15.2015 26180207 PMC6605340

142. Ward N.S. Restoring brain function after stroke-bridging the gap between animals and humans Nat. Rev. Neurol. 2017 13 244 255 10.1038/nrneurol.2017.34 28303914

143. Cramer S.C. Sur M. Dobkin B.H. O’Brien C. Sanger T.D. Trojanowski J.Q. Rumsey J.M. Hicks R. Cameron J. Chen D. Harnessing neuroplasticity for clinical applications Brain 2011 134 Pt 6 1591 1609 10.1093/brain/awr039 21482550 PMC3102236

144. Johansen-Berg H. Dawes H. Guy C. Smith S.M. Wade D.T. Matthews P.M. Correlation between motor improvements and altered fMRI activity after rehabilitative therapy Brain 2002 125 Pt 12 2731 2742 10.1093/brain/awf282 12429600

145. Sitaram R. Veit R. Stevens B. Caria A. Gerloff C. Birbaumer N. Hummel F. Acquired control of ventral premotor cortex activity by feedback training: An exploratory real-time FMRI and TMS study Neurorehabil. Neural Repair. 2012 26 256 265 10.1177/1545968311418345 21903976

146. Ramos-Murguialday A. Broetz D. Rea M. Läer L. Yilmaz O. Brasil F.L. Liberati G. Curado M.R. Garcia-Cossio E. Vyziotis A. Brain-machine interface in chronic stroke rehabilitation: A controlled study Ann. Neurol. 2013 74 100 108 10.1002/ana.23879 23494615 PMC3700597

147. Kuceyeski A. Navi B.B. Kamel H. Relkin N. Villanueva M. Raj A. Toglia J. O’Dell M. Iadecola C. Segal A.Z. Exploring the brain’s structural connectome: A quantitative stroke lesion-dysfunction mapping study Hum. Brain Mapp. 2015 36 2147 2160 10.1002/hbm.22761 25655204 PMC4414746

148. Pustina D. Coslett H.B. Turkeltaub P.E. Tustison N. Schwartz M.F. Avants B. Automated segmentation of chronic stroke lesions using LINDA: Lesion identification with neighborhood data analysis Hum. Brain Mapp. 2016 37 1405 1421 10.1002/hbm.23110 26756101 PMC4783237

149. Lefaucheur J.P. Aleman A. Baeken C. Benninger D.H. Brunelin J. Di Lazzaro V. Filipović S.R. Grefkes C. Hasan A. Hummel F.C. Evidence-based guidelines on the therapeutic use of repetitive transcranial magnetic stimulation (rTMS): An update (2014-2018) Clin. Neurophysiol. 2020 131 474 528 10.1016/j.clinph.2019.11.002 31901449

150. Lefaucheur J.P. Antal A. Ayache S.S. Benninger D.H. Brunelin J. Cogiamanian F. Cotelli M. De Ridder D. Ferrucci R. Langguth B. Evidence-based guidelines on the therapeutic use of transcranial direct current stimulation (tDCS) Clin. Neurophysiol. 2017 128 56 92 10.1016/j.clinph.2016.10.087 27866120

151. Huang Y.Z. Lu M.K. Antal A. Classen J. Nitsche M. Ziemann U. Ridding M. Hamada M. Ugawa Y. Jaberzadeh S. Plasticity induced by non-invasive transcranial brain stimulation: A position paper Clin. Neurophysiol. 2017 128 2318 2329 10.1016/j.clinph.2017.09.007 29040922

152. Bergmann T.O. Karabanov A. Hartwigsen G. Thielscher A. Siebner H.R. Combining non-invasive transcranial brain stimulation with neuroimaging and electrophysiology: Current approaches and future perspectives Neuroimage 2016 140 4 19 10.1016/j.neuroimage.2016.02.012 26883069

153. Thut G. Bergmann T.O. Fröhlich F. Soekadar S.R. Brittain J.S. Valero-Cabré A. Sack A.T. Miniussi C. Antal A. Siebner H.R. Guiding transcranial brain stimulation by EEG/MEG to interact with ongoing brain activity and associated functions: A position paper Clin. Neurophysiol. 2017 128 843 857 10.1016/j.clinph.2017.01.003 28233641 PMC5385293

154. He J. Baxter S.L. Xu J. Xu J. Zhou X. Zhang K. The practical implementation of artificial intelligence technologies in medicine Nat. Med. 2019 25 30 36 10.1038/s41591-018-0307-0 30617336 PMC6995276

155. Topol E.J. High-performance medicine: The convergence of human and artificial intelligence Nat. Med. 2019 25 44 56 10.1038/s41591-018-0300-7 30617339

156. Vayena E. Blasimme A. Cohen I.G. Machine learning in medicine: Addressing ethical challenges PLoS Med. 2018 15 e1002689 10.1371/journal.pmed.1002689 30399149 PMC6219763

157. Guo Y. Liu Y. Oerlemans A. Lao S. Wu S. Lew M.S. Deep learning for visual understanding: A review Neurocomputing 2016 187 27 48 10.1016/j.neucom.2015.09.116

158. Zech J.R. Badgeley M.A. Liu M. Costa A.B. Titano J.J. Oermann E.K. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study PLoS Med. 2018 15 e1002683 10.1371/journal.pmed.1002683 30399157 PMC6219764

159. U.S. Food and Drug Administration Software as a Medical Device (SaMD) U.S. Food and Drug Administration Silver Spring, MD, USA 2017

160. U.S. Food and Drug Administration Artificial Intelligence and Machine Learning in Software as a Medical Device U.S. Food and Drug Administration Silver Spring, MD, USA 2021

161. Babic B. Gerke S. Evgeniou T. Cohen I.G. Algorithms on regulatory lockdown in medicine Science 2019 366 1202 1204 10.1126/science.aay9547 31806804

162. Sherman R.E. Anderson S.A. Dal Pan G.J. Gray G.W. Gross T. Hunter N.L. LaVange L. Marinac-Dabic D. Marks P.W. Robb M.A. Real-World Evidence-What Is It and What Can It Tell Us? N. Engl. J. Med. 2016 375 2293 2297 10.1056/NEJMsb1609216 27959688

163. Price W.N. 2nd Artificial Intelligence in Health Care: Applications and Legal Implications SciTech Lawyer 2017 14 10 13

164. Gerke S. Minssen T. Cohen G. Ethical and legal challenges of artificial intelligence-driven healthcare Artificial Intelligence in Healthcare Academic Press Cambridge, MA, USA 2020 295 336

165. Cohen I.G. Evgeniou T. Gerke S. Minssen T. The European artificial intelligence strategy: Implications and challenges for digital health Lancet Digit Health 2020 2 e376 e379 10.1016/S2589-7500(20)30112-6 33328096

166. Price W.N. 2nd Cohen I.G. Privacy in the age of medical big data Nat. Med. 2019 25 37 43 10.1038/s41591-018-0272-7 30617331 PMC6376961

167. Lehne M. Sass J. Essenwanger A. Schepers J. Thun S. Why digital medicine depends on interoperability NPJ Digit. Med. 2019 2 79 10.1038/s41746-019-0158-1 31453374 PMC6702215

168. Wilkinson M.D. Dumontier M. Aalbersberg I.J. Appleton G. Axton M. Baak A. Blomberg N. Boiten J.W. da Silva Santos L.B. Bourne P.E. The FAIR Guiding Principles for scientific data management and stewardship Sci. Data 2016 3 160018 10.1038/sdata.2016.18 26978244 PMC4792175

169. Price W.N. 2nd Gerke S. Cohen I.G. Potential Liability for Physicians Using Artificial Intelligence JAMA 2019 322 1765 1766 10.1001/jama.2019.15064 31584609

170. U.S. Food and Drug Administration Postmarket Management of Cybersecurity in Medical Devices U.S. Food and Drug Administration Silver Spring, MD, USA 2016

171. Challen R. Denny J. Pitt M. Gompels L. Edwards T. Tsaneva-Atanasova K. Artificial intelligence, bias and clinical safety BMJ Qual. Saf. 2019 28 231 237 10.1136/bmjqs-2018-008370 30636200 PMC6560460

172. U.S. Food and Drug Administration Medical Device Reporting (MDR) U.S. Food and Drug Administration Silver Spring, MD, USA 2020

173. Jovicich J. Czanner S. Greve D. Haley E. van der Kouwe A. Gollub R. Kennedy D. Schmitt F. Brown G. Macfall J. Reliability in multi-site structural MRI studies: Effects of gradient non-linearity correction on phantom and human data Neuroimage 2006 30 436 443 10.1016/j.neuroimage.2005.09.046 16300968

174. Keshavan A. Datta E. McDonough I.M. Madan C.R. Jordan K. Henry R.G. Mindcontrol: A web application for brain segmentation quality control Neuroimage 2018 170 365 372 10.1016/j.neuroimage.2017.03.055 28365419

175. Reuter M. Rosas H.D. Fischl B. Highly accurate inverse consistent registration: A robust approach Neuroimage 2010 53 1181 1196 10.1016/j.neuroimage.2010.07.020 20637289 PMC2946852

176. Esteban O. Birman D. Schaer M. Koyejo O.O. Poldrack R.A. Gorgolewski K.J. MRIQC: Advancing the automatic prediction of image quality in MRI from unseen sites PLoS ONE 2017 12 e0184661 10.1371/journal.pone.0184661 28945803 PMC5612458

177. Power J.D. Barnes K.A. Snyder A.Z. Schlaggar B.L. Petersen S.E. Spurious but systematic correlations in functional connectivity MRI networks arise from subject motion Neuroimage 2012 59 2142 2154 10.1016/j.neuroimage.2011.10.018 22019881 PMC3254728

178. Tisdall M.D. Reuter M. Qureshi A. Buckner R.L. Fischl B. van der Kouwe A.J.W. Prospective motion correction with volumetric navigators (vNavs) reduces the bias and variance in brain morphometry induced by subject motion Neuroimage 2016 127 11 22 10.1016/j.neuroimage.2015.11.054 26654788 PMC4754677

179. Esteban O. Markiewicz C.J. Blair R.W. Moodie C.A. Isik A.I. Erramuzpe A. Kent J.D. Goncalves M. DuPre E. Snyder M. fMRIPrep: A robust preprocessing pipeline for functional MRI Nat. Methods 2019 16 111 116 10.1038/s41592-018-0235-4 30532080 PMC6319393

180. Gorgolewski K.J. Auer T. Calhoun V.D. Craddock R.C. Das S. Duff E.P. Flandin G. Ghosh S.S. Glatard T. Halchenko Y.O. The brain imaging data structure, a format for organizing and describing outputs of neuroimaging experiments Sci. Data 2016 3 160044 10.1038/sdata.2016.44 27326542 PMC4978148

181. Reuter M. Schmansky N.J. Rosas H.D. Fischl B. Within-subject template estimation for unbiased longitudinal image analysis Neuroimage 2012 61 1402 1418 10.1016/j.neuroimage.2012.02.084 22430496 PMC3389460

182. Fortin J.P. Cullen N. Sheline Y.I. Taylor W.D. Aselcioglu I. Cook P.A. Adams P. Cooper C. Fava M. McGrath P.J. Harmonization of cortical thickness measurements across scanners and sites Neuroimage 2018 167 104 120 10.1016/j.neuroimage.2017.11.024 29155184 PMC5845848

183. Yu M. Linn K.A. Cook P.A. Phillips M.L. McInnis M. Fava M. Trivedi M.H. Weissman M.M. Shinohara R.T. Sheline Y.I. Statistical harmonization corrects site effects in functional connectivity measurements from multi-site fMRI data Hum. Brain Mapp. 2018 39 4213 4227 10.1002/hbm.24241 29962049 PMC6179920

184. U.S. Food and Drug Administration Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD) Action Plan U.S. Food and Drug Administration Silver Spring, MD, USA 2021

185. Benjamens S. Dhunnoo P. Meskó B. The state of artificial intelligence-based FDA-approved medical devices and algorithms: An online database NPJ Digit. Med. 2020 3 118 10.1038/s41746-020-00324-0 32984550 PMC7486909

186. U.S. Food and Drug Administration Proposed Regulatory Framework for Modifications to Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD) U.S. Food and Drug Administration Silver Spring, MD, USA 2019

187. Isensee F. Jaeger P.F. Kohl S.A.A. Petersen J. Maier-Hein K.H. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation Nat. Methods 2021 18 203 211 10.1038/s41592-020-01008-z 33288961

188. Shen L. Zhao W. Xing L. Patient-specific reconstruction of volumetric computed tomography images from a single projection view via deep learning Nat. Biomed. Eng. 2019 3 880 888 10.1038/s41551-019-0466-4 31659306 PMC6858583

189. Schlemper J. Caballero J. Hajnal J.V. Price A.N. Rueckert D. A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction IEEE Trans. Med. Imaging 2018 37 491 503 10.1109/TMI.2017.2760978 29035212

190. Chen K.T. Schürer M. Ouyang J. Koran M.E.I. Davidzon G. Mormino E. Tiepolt S. Hoffmann K.T. Sabri O. Zaharchuk G. Generalization of deep learning models for ultra-low-count amyloid PET/MRI using transfer learning Eur. J. Nucl. Med. Mol. Imaging 2020 47 2998 3007 10.1007/s00259-020-04897-6 32535655 PMC7680289

191. Finlayson S.G. Bowers J.D. Ito J. Zittrain J.L. Beam A.L. Kohane I.S. Adversarial attacks on medical machine learning Science 2019 363 1287 1289 10.1126/science.aaw4399 30898923 PMC7657648

192. Glocker B. Robinson R. Castro D.C. Dou Q. Konukoglu E. Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects arXiv 2019 1910.04597

193. Wachinger C. Reuter M. Domain adaptation for Alzheimer’s disease diagnostics Neuroimage 2016 139 470 479 10.1016/j.neuroimage.2016.05.053 27262241 PMC4983466

194. Lundberg S.M. Lee S.I. A Unified Approach to Interpreting Model Predictions Adv. Neural Inf. Process Syst. 2017 30 4765 4774

195. Shin H.C. Tenenholtz N.A. Rogers J.K. Schwarz C.G. Senjem M.L. Gunter J.L. Andriole K.P. Michalski M. Medical Image Synthesis for Data Augmentation and Anonymization Using Generative Adversarial Networks Simulation and Synthesis in Medical Imaging—Third International Workshop, SASHIMI 2018, Held in Conjunction with MICCAI 2018, Proceedings Lecture Notes in Computer Science; Springer Cham, Switzerland 2018 Volume 11037 1 11