Real-time fetal brain tracking for functional fetal MRI

Abstract

Purpose: To improve motion robustness of functional fetal MRI scans by developing an intrinsic real-time motion correction method. MRI provides an ideal tool to characterize fetal brain development and growth. It is, however, a relatively slow imaging technique and therefore extremely susceptible to subject motion, particularly in functional MRI experiments acquiring multiple Echo-Planar-Imaging-based repetitions, for example, diffusion MRI or blood-oxygen-level-dependency MRI.

Methods: A 3D UNet was trained on 125 fetal datasets to track the fetal brain position in each repetition of the scan in real time. This tracking, inserted into a Gadgetron pipeline on a clinical scanner, allows updating the position of the field of view in a modified echo-planar imaging sequence. The method was evaluated in real-time in controlled-motion phantom experiments and ten fetal MR studies (17 + 4-34 + 3 gestational weeks) at 3T. The localization network was additionally tested retrospectively on 29 low-field (0.55T) datasets.

Results: Our method achieved real-time fetal head tracking and prospective correction of the acquisition geometry. Localization performance achieved Dice scores of 84.4% and 82.3%, respectively for both the unseen 1.5T/3T and 0.55T fetal data, with values higher for cephalic fetuses and increasing with gestational age.

Conclusions: Our technique was able to follow the fetal brain even for fetuses under 18 weeks GA in real-time at 3T and was successfully applied "offline" to new cohorts on 0.55T. Next, it will be deployed to other modalities such as fetal diffusion MRI and to cohorts of pregnant participants diagnosed with pregnancy complications, for example, pre-eclampsia and congenital heart disease.

Keywords: BOLD; T2* relaxometry; diffusion MRI; fetal MRI; fetal brain development; motion correction; motion detection; tracking.

FIGURE 1

Schematic overview of the complete pipeline illustrating data acquisition, image reconstruction, fetal brain localization, and the real‐time change in the field of view (FOV).

FIGURE 2

Pipeline for localization of fetal brain in MRI images.

FIGURE 3

Images of five fetal subjects (25/18.6/15.7/26/21 gestational weeks) obtained at five echo‐times (10/52/98/142.5/240 ms) with brain masks predicted by the network (red) and corresponding manually drawn masks (yellow).

FIGURE 4

(A) Histogram of Dice similarity coefficient results obtained from brain masks automatically extracted from images of 16 fetal subjects at five echo times. (B) Density plot representing the distribution of Dice coefficient scores across five echo times. (C) Dice coefficient values were calculated and plotted individually for each fetus at each echo time.

FIGURE 5

Images of Fetus 5 at TE1/TE2/TE3/TE4/TE5 = 13.8/70.4/127/183.6/240.2 ms with respective ground‐truth (yellow) and predicted (red) brain masks.

FIGURE 6

Images of five fetal subjects (26.5/20.7/21/27/36 gestational weeks) obtained at 0.55T and at 5 echo‐times (46/120/194/268/342 ms) with brain masks predicted by the network (red) and corresponding manually drawn masks (yellow).

FIGURE 7

Coronal, sagittal and axial views with regard to the brain from all ten prospectively acquired fetal datasets illustrating the automatically achieved segmentation in red.

FIGURE 8

The calculated center‐of‐mass coordinates in all three axes are depicted for the phantom experiment. Yellow arrows indicate the detected motion, and purple arrows the corresponding resulting automatic Field‐of‐View correction as applied two repetitions after the movement.

FIGURE 9

Consecutive repetitions from one plane acquired with real‐time fetal brain motion correction are illustrated for four fetal subjects.