Clinical Grading of Artificial Intelligence-Based 3D Fetal Brain Segmentations: A Cross-Vendor Evaluation of Deep Learning in Fetal Neuroimaging.

Key Points

• The study aims to assess the performance of deep learning techniques in segmenting fetal brain structures across different ultrasound vendors.
• Evaluated deep learning methods for 3D segmentation of fetal brain structures.
• Used a novel dataset acquired from different ultrasound vendors.
• Incorporated visual assessments along with quantitative metrics.
• Deep learning methods successfully segmented (sub)cortical brain structures across vendors.
• Demonstrated robustness in segmentation accuracy with different ultrasound equipment.
• Visual assessment provided valuable insights into clinical usability.