AI-assisted identification of novel multimodal imaging markers and underlying mechanisms in PD

This Collection supports and amplifies research related to SDG 3 and SDG 9.

Artificial intelligence (AI) is revolutionizing neuroimaging in Parkinson's disease (PD), offering unprecedented opportunities for early diagnosis, accurate prognosis, and personalized treatment monitoring. This research article collection aims to showcase cutting-edge AI applications in PD imaging, exploring how these technologies are transforming our understanding and management of the disease. We welcome submissions across a broad spectrum of topics, including:

1. AI-enhanced Neuroimaging Techniques: Articles focusing on advanced image acquisition, reconstruction and analysis. This includes deep learning approaches for PET/MRI image reconstruction to detect PD related changes such as dopaminergic, cholinergic, inflammatory, mitochondrial/metabolic deficits. Studies exploring iron- and neuromelanin-sensitive MRI for qualitative changes in the substantia nigra are of particular interest.

2. Early Detection and Differential Diagnosis: Research on machine learning approaches for identifying early PD biomarkers in neuroimaging data, AI-assisted differentiation between prodromal PD, healthy controls, and atypical parkinsonisms, as well as predictive modeling of prodromal PD.

3. Disease Progression Monitoring: Studies on AI-based tracking of structural and functional brain changes in PD. This includes quantifying molecular degeneration like dopamine transporter loss over time, automated assessment of microstructural and network alterations in PD progression.

4. Treatment Response Prediction: Investigations into AI models for predicting response to PD therapy based on imaging features, machine learning algorithms for optimizing deep brain stimulation parameters, and AI-guided personalized treatment planning using neuroimaging data.

5. Multimodal Data Integration: Research on AI approaches for combining imaging with clinical, genetic, and molecular data in PD, and machine learning models for integrating structural and functional imaging in PD analysis.

6. AI in Clinical Trials and Drug Development: Research on AI-powered imaging endpoints for PD clinical trials, machine learning for patient stratification using neuroimaging data.

This collection will highlight how AI is advancing our ability to detect, monitor, and treat Parkinson's disease through sophisticated imaging analysis. We encourage submissions that demonstrate novel AI applications, validate existing approaches, or provide critical perspectives on the challenges and future directions of AI in PD imaging. By bringing together these diverse topics, we aim to provide a comprehensive overview of the current state and future potential of AI in PD neuroimaging.