Artificial Intelligence in Fetal MRI: Principles, Applications, Limitations, and Future Directions

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Fetal Medicine

Background:

• Fetal MRI faces challenges like motion artifacts, low signal-to-noise ratio, and slice misregistration.
• Existing fetal MRI techniques have limitations in accuracy and efficiency for prenatal diagnostics.

Purpose of the Study:

• To review current applications of artificial intelligence (AI) in fetal MRI.
• To highlight AI's role in addressing fetal MRI limitations and enhancing diagnostic capabilities.

Main Methods:

• Literature review of AI applications in fetal MRI.
• Focus on AI for image enhancement, segmentation, and quantitative analysis.
• Exploration of multimodal AI approaches in prenatal imaging.

Main Results:

• AI demonstrates potential in improving fetal MRI reconstruction, denoising, and motion correction.
• Automated segmentation and quantitative analysis using AI aid in volumetric assessment.
• AI assists in tasks like gestational-age estimation and fetal anomaly detection.

Conclusions:

• AI significantly improves fetal MRI quality and analytical tasks, offering solutions to current limitations.
• Most AI studies in fetal MRI lack external validation and rely on small datasets.
• Standardized protocols, multicenter data, and transparent evaluation are crucial for integrating AI into routine prenatal imaging.