Fully automated planning for anatomical fetal brain MRI on 0.55T

TL;DR

This study presents a fully automated, real-time planning system for fetal brain MRI at 0.55T, enabling easier and more accessible fetal imaging through deep learning-based landmark detection and automatic plane planning.

Contribution

The paper introduces a novel deep learning pipeline for automatic fetal brain MRI planning that operates in real-time and has been prospectively validated on clinical subjects.

Findings

Automatic planning was performed in real-time without latency.

Landmark detection accuracy was within a few millimeters.

Planning quality was comparable to manual planning.

Abstract

Purpose: Widening the availability of fetal MRI with fully automatic real-time planning of radiological brain planes on 0.55T MRI. Methods: Deep learning-based detection of key brain landmarks on a whole-uterus EPI scan enables the subsequent fully automatic planning of the radiological single-shot Turbo Spin Echo acquisitions. The landmark detection pipeline was trained on over 120 datasets from varying field strength, echo times and resolutions and quantitatively evaluated. The entire automatic planning solution was tested prospectively in nine fetal subjects between 20 and 37 weeks. Comprehensive evaluation of all steps, the distance between manual and automatic landmarks, the planning quality and the resulting image quality was conducted. Results: Prospective automatic planning was performed in real-time without latency in all subjects. The landmark detection accuracy was 4.21+-2.56 mm for the fetal eyes and 6.47+-3.23 for the cerebellum, planning quality was 2.44/3 (compared to 2.56/3 for manual planning) and diagnostic image quality was 2.14 compared to 2.07 for manual planning. Conclusions: Real-time automatic planning of all three key fetal brain planes was successfully achieved and will pave the way towards simplifying the acquisition of fetal MRI thereby widening the availability of this modality in non-specialist centres.