Developmental Brain Age Estimation From MRI Data: A Systematic Review of Deep Learning Approaches and Open Datasets

Area of Science:

• Neuroimaging
• Developmental Neuroscience
• Artificial Intelligence in Medicine

Background:

• Brain age estimation using MRI is crucial for identifying deviations in neurodevelopment.
• Data-driven models, especially deep learning, show promise in pediatric neuroimaging.
• Accurate age estimation serves as a biomarker for early diagnosis and improved outcomes.

Purpose of the Study:

• To comprehensively review deep learning applications for developmental brain age estimation (fetal to 2 years) using MRI.
• To detail clinical and technical aspects, datasets, and model performance.
• To discuss applications, challenges, and future directions in the field.

Main Methods:

• Review of current literature on deep learning methodologies for developmental brain age estimation.
• Analysis of clinical and technical aspects of MRI-based brain age estimation.
• Comparison of model performance using established evaluation metrics.

Main Results:

• Deep learning approaches offer state-of-the-art performance in estimating developmental brain age.
• The review covers open-access datasets and performance metrics for various models.
• Brain age estimation is vital for understanding neurodevelopmental disorders.

Conclusions:

• Deep learning-based MRI brain age estimation is a powerful tool for pediatric neurodevelopmental research.
• Further research is needed to address current challenges and advance practical applications.
• This review provides insights for researchers and practitioners in the field.