Real-time MRI-based fetal femur length measurement

TL;DR

This study develops and validates a real-time, automated MRI pipeline for planning and measuring fetal femur length using a 0.55T scanner. A two-stage neural network localizes femur endpoints, which then drive real-time in-plane EPI planning via a FIRE-enabled workflow; PCA-based landmark extraction yields FL as the distance between endpoints. Retrospective results show endpoint localization mean error of $5.5\pm2.0$ mm and FL error of $3.0\pm2.4$ mm with strong gestational-age correlations ($r\approx0.9$), while prospective testing demonstrates reliable, real-time plane prescription in most cases and competitive accuracy against ultrasound. Overall, the method offers motion-robust, operator-independent growth assessment with potential for large-scale clinical adoption in growth-constrained pregnancies.

Abstract

Purpose: To develop and evaluate a real-time method for automatic planning and measurement of fetal femur length - an important indicator of antenatal growth - during MRI. While routinely assessed by ultrasound, MRI-based femur length measurements remain challenging due to bone-slice misalignment, fetal motion, and the need for manual assessment. Methods: A low-latency 3D U-Net was trained on 59 scans acquired at 0.55T (gestational age 18-40 weeks) to localise the proximal and distal endpoints of the femur. These coordinates were employed to automatically adapt a 30-second EPI sequence for in-plane femur coverage in real-time. Retrospective evaluation was performed in 72 scans (19-39 weeks, including 19 pathological cases), and real-time testing in 24 cases (17-39 weeks). Automated results were compared with manual expert annotations and, in 57/72 cases, with matched clinical ultrasound measurements. Precision was evaluated against inter-observer variability and analysed across gestational age and maternal BMI. Furthermore, bilateral femur length consistency was evaluated. Results: Retrospective analysis demonstrated a mean endpoint localisation error of 5.5 mm and femur length deviation of 3.0 mm. Among the 49/72 cases with both femora automatically extracted, the left-right difference was 2.8+-2.7 mm. Precision was unaffected by maternal BMI (p>0.05), but correlated with gestational age (p<0.05). Real-time planning and assessment were successful in 22/24 cases, with a mean deviation of 4.2 mm. Conclusions: A real-time, automated method for MRI-based femur length measurement was developed, enabling precise, motion-robust, and operator-independent growth assessment, supporting future large-scale evaluation in growth-compromised pregnancies.

Figures (6)

• Figure 1: Automated pipeline for MR-based femur length assessment. Step 1: initial scout acquisition and femur localisation; step 2: real-time computation of the optimal scan plane aligning the femur in-plane; step 3: adapted short-TE EPI scan with femur in-plane, enabling accurate length measurement.
• Figure 2: Illustration of the length measurement. (A) On ultrasound, the femur length is measured between the proximal and distal ends of the diaphysis. (B) In MRI, this corresponds to the hypo-intense ossified part of the bone. (C) Femoral landmarks are identified using Principal Component Analysis (PCA) on the generated network segmentation. The first principal component (white arrow) points in the direction of greatest variance and is used as the best-fit approximation of the anatomical axis. (D) The femur length was estimated as the distance between the points with the largest and smallest projection values (green cross).
• Figure 3: Evaluation of 72 retrospective cases. (A) Comparison of relative measurement errors in the second- and third-trimester datasets. (B) Difference in femur length measurements between manual annotations by two observers (M1, M2) and the automatic method (A). (C) Overlay of automatic and manual endpoints on the image acquired at the first echo time.
• Figure 4: Illustrative results of the complete pipeline in 4 prospectively acquired fetuses (23-39 weeks gestational age). (Step 1) Landmark detection was performed on the initial scout scan and enabled full coverage of the femur in plane during the (Step 2) re-planned acquisition.
• Figure 5: Quantitative results shown for the entire retrospective cohort from 19 to 40 weeks of gestational age (left) and with a zoom into the last 5 weeks of pregnancy (right). The automatic MRI results are shown in green, the manual MRI results in yellow and the ultrasound comparison measurements in red for all cases where available. Cases with pathologies are indicated by a cross. The ultrasound-based percentile lines are highlighted in grey.