Artificial Intelligence in Fetal MRI: Principles, Applications, Limitations, and Future Directions.
Authors
Affiliations (4)
Affiliations (4)
- EA fetus 7328 and LUMIERE Platform, University of Paris.
- Department of Obstetrics, Lille University Hospital, Lille, France.
- Department of Obstetrics, Fetal Medicine and Surgery, Necker-Enfants Malades Hospital, APHP.
- Department of Radiology, Necker-Enfants Malades Hospital, APHP, Paris.
Abstract
Artificial intelligence (AI) offers solutions to overcome limitations of fetal MRI, including motion, low signal-to-noise ratio, and slice misregistration. This review summarizes current AI applications in fetal MRI, focusing on image enhancement, automated segmentation, quantitative analysis, and emerging multimodal approaches. AI improves reconstruction, denoising, motion correction, and volumetric assessment, and supports tasks such as gestational-age estimation and anomaly detection. However, most studies rely on small, single-center data sets with limited external validation. Robust multicenter data, standardized protocols, and transparent evaluation frameworks are required before AI can be reliably integrated into routine prenatal imaging.