A comprehensive analysis of the current computational approaches employed for the diagnosis of five major neurological disorders, including Alzheimer’s disease, Parkinson’s disease, Epilepsy, Huntington’s disease, Huntington’s disease, and Amyotrophic Lateral Sclerosis is provided.
Early diagnosis of neurodegenerative diseases remains essential for improving patient management because pathological brain changes often precede clinical manifestations. This review evaluates the role of magnetic resonance imaging (MRI) in the early detection and characterization of Alzheimer's disease, Parkinson's disease, multiple sclerosis, frontotemporal dementia, and Huntington's disease. The objective was to analyse recent advances in conventional and advanced MRI techniques and their contribution to diagnostic accuracy. A comprehensive literature review was performed focusing on structural MRI, diffusion tensor imaging, functional MRI, susceptibility-weighted imaging, magnetic resonance spectroscopy, and artificial intelligence (AI)-based image analysis. The reviewed evidence indicates that advanced MRI techniques can identify microstructural, functional, and metabolic abnormalities before overt brain atrophy becomes apparent, while AI improves image interpretation, disease classification, and prognostic assessment. The novelty of this review is the integration of advanced MRI modalities with AI-based analytical approaches into a unified framework for the early diagnosis of neurodegenerative diseases. These findings support the growing role of multiparametric MRI as a biomarker platform for early diagnosis, disease differentiation, and personalized clinical management, although further standardization and multicenter validation are required for routine clinical implementation.
Ранняя диагностика нейродегенеративных заболеваний остаётся ключевым фактором в улучшении ведения пациентов, поскольку патологические изменения в мозге часто возникают ещё до появления клинических симптомов. В этом обзорном исследовании оценивается роль магнитно-резонансной томографии (МРТ) в раннем выявлении и характеристике болезни Альцгеймера, болезни Паркинсона, рассеянного склероза, лобно-височной деменции и болезни Хантингтона. Цель работы – проанализировать современные достижения в области традиционных и перспективных методов МРТ и их влияние на диагностическую точность. Был проведён комплексный обзор литературы с акцентом на структурную МРТ, диффузионно-тензорную визуализацию, функциональную МРТ, визуализацию с учётом магнитной восприимчивости, магнитно-резонансную спектроскопию и анализ изображений на основе искусственного интеллекта (ИИ). Представленные данные свидетельствуют, что перспективные методы МРТ позволяют выявлять микроструктурные, функциональные и метаболические нарушения ещё до появления заметной атрофии мозга, а ИИ способствует улучшению интерпретации изображений, классификации заболеваний и прогнозированию. Новизна обзорного исследования заключается в интеграции перспективных модальностей МРТ с методами анализа на основе ИИ в единую платформу для ранней диагностики нейродегенеративных заболеваний. Эти результаты подтверждают возрастающую роль многопараметрической МРТ как платформы биомаркеров для ранней диагностики, дифференциации заболеваний и персонализированного ведения пациентов, хотя для внедрения в рутинную клиническую практику требуется дальнейшая стандартизация и проверка в многоцентровых исследованиях.
Niranjani Lakshana Venugopal, Varsha Jayant More, Mani Bharathi Omprakash· Clinical and Fundamental Med...· 0 citations
This editorial introduces a special issue detailing the rapid evolution of multimodal neuroimaging biomarkers for Parkinson's disease (PD) and related movement disorders. Advances in MRI, including quantitative susceptibility mapping for iron dysregulation, neuromelanin-sensitive MRI, diffusion tensor imaging for free water quantification, metabolic spectroscopy, and functional network mapping, are reviewed. The integrated application of these modalities demonstrates that PD neurodegeneration cannot be captured by a single biomarker. Instead, these complementary tools define overlapping biological dimensions of the disease, spanning dopaminergic neuronal integrity, microstructural injury, glymphatic impairment, vascular abnormalities, and large-scale network reorganization. Furthermore, the integration of artificial intelligence and machine learning allows for the extraction of multidimensional patterns, improving the differential diagnosis between PD and atypical parkinsonian syndromes like multiple system atrophy and progressive supranuclear palsy. We conclude that while these multimodal biomarkers offer unprecedented mechanistic insights into disease progression and therapeutic response, their ultimate value depends on successful clinical translation. Moving forward, it would be essential for the field to prioritize standardized acquisition protocols, automated post-processing pipelines, and accessible reporting frameworks to implement these powerful research tools into routine clinical environments.
E. Haacke, S. Buch, N. He et al.· NeuroImage· 0 citations
Parkinson’s disease (PD) is an increasingly developing neurological disorder that affects both motor and non-motor functions, resulting in a reduction of quality of life. Early detection of PD is highly challenging, as the occurrence of noticeable symptoms happens only after considerable neurodegeneration. Similarly, conventional diagnostic techniques rely more on subjective clinical judgment. To overcome these problems, non-invasive biomarkers based on speech, sensor, retinal, and neuroimage modalities are extensively investigated using computational techniques. A wide variety of analytical techniques, including conventional machine learning, ensemble, hybrid, and optimization-based approaches, are employed for the identification of significant patterns associated with PD. To this purpose, an extensive evaluation of existing algorithms and multimodal diagnostic techniques to assess their effectiveness, advantages, and limitations across different data modalities. Deep neural network models further improve the diagnostic process by automatically learning hierarchical and high-level representations directly from data. By using this ability, complex and nonlinear patterns of Parkinson’s disease progression can be effectively captured for accurate feature learning and early diagnosis.
Anuradha Komati, T. Reddy· 2026 7th International Confe...· 0 citations
The progressive nature and overlapping clinical features of neurodegenerative diseases like Alzheimer's disease, Parkinson's disease, Frontotemporal Dementia, Huntington's disease, Dementia with Lewy Bodies and Amyotrophic lateral sclerosis make them tough to diagnose. While AI has shown great accuracy in diagnosis, it has the drawback of being hard for users to interpret, making it difficult to be broadly adopted in clinical practice. The current review aims at analyzing the state-of-the-art on the use of Explainable Artificial Intelligence (XAI) for the diagnosis of neurodegenerative diseases, focusing on AI models, explainability methods, datasets, validation methods, clinical applications, and implementation challenges. The review was conducted according to PRISMA 2020 guidelines and included the PubMed, IEEE Xplore and ScienceDirect databases of research articles published from 2018 to 2026. A total of 25 studies were included for qualitative synthesis from 454 retrieved studies. The results showed that convolutional neural networks and hybrid deep learning models are more widely studied than other methods, and that Grad-CAM, SHAP, LIME, and attention mechanisms are the most common explainability methods. The dataset of the Alzheimer's Disease Neuroimaging Initiative (ADNI) is widely used in existing studies, which is why Alzheimer's disease is still the major focus of study. While diagnostic capability is excellent, the translation to clinical practice is hampered by limited external validation, retrospective data sets, small sample sizes and regulatory issues. Future studies should focus on multimodal learning, prospective multi-center and various datasets along with trustworthy XAI frameworks to enable the routine clinical implementation.
Jasmine Chifurumnanya Nnabue, V. Nwaocha, Emmanuel Ejembi· Nature Journal of Emerging S...· 0 citations
Background: The eye provides a valuable window for the identification of neurological diseases, as pathological changes may involve both the retina and the optic nerve. Standard imaging of the retina and the optic nerve are non-invasive and are useful tools in investigating the integrity of the visual pathways. With population aging and the increasing burden of neuro-ophthalmic diseases, there is a growing need for tools that can assist clinicians in achieving rapid and reliable diagnoses. AI may facilitate the detection of specific neuro-ophthalmological conditions. Methods: This article presents a narrative review of previously published studies addressing the current applications of AI in selected neuro-ophthalmic conditions, with emphasis on their advantages, limitations, and challenges in screening, diagnosis, and disease progression assessment. Results: AI-based approaches provide valuable opportunities for the screening, characterization, and monitoring of optic nerve head abnormalities in neuro-ophthalmology. Recent advancements, particularly in deep learning and convolutional neural networks, have shown notable potential in interpreting fundus photography, optical coherence tomography and magnetic resonance imaging, supporting a comprehensive assessment of optic nerve structure and function. These systems are particularly promising because they can extract quantitative information from routine imaging modalities and may assist clinicians in detecting structural damage that is difficult to identify through conventional evaluation alone. Conclusions: AI-assisted ophthalmic imaging has shown promising diagnostic performance in identifying ONH abnormalities and retinal or optic nerve changes associated with neurological disease. At present, however, most applications remain within research, retrospective validation, or proof-of-concept settings, and evidence that AI consistently improves early diagnosis or clinical outcomes beyond conventional assessment remains limited. Accordingly, AI should currently be regarded as a complementary tool that may support screening, image interpretation, disease characterization, and referral decisions rather than replace established clinical evaluation.
R. Iorga, Vlad-Constantin Donica, Ciprian Danielescu et al.· Medical Science· 0 citations
In the future, MRI is expected to achieve breakthroughs by combining artificial intelligence, developing new contrast agents, and upgrading hardware, further expanding its applications in the medical field.
Junwen Chen, Xinyi Liu, Yanghongyu Qian et al.· 0 citations