Head circumference assessment in pediatric MRI: a pilot study of manual measurement methods and automated...

Head circumference (HC) is an important clinical parameter in neuropediatrics, but it is often missing or outdated in referral information. This can lead to subjective, reader-dependent estimation during MRI interpretation. We first aimed to compare magnetic resonance imaging (MRI)-based methods for HC measurement against the tape measure (ground truth), and second to establish an automated alternative.

In 23 children (mean age 4.5 years, range 0.5-17 years), HC was prospectively measured with a tape measure (ground truth) on the day of MRI. MRI-based HC measurements were derived from 3D T1-weighted MPRAGE and followed a two-step workflow: measurement plane selection and circumference measurement within that plane. Plane selection was performed using visual-based, rule-based, atlas-based [(infant) FreeSurfer], or neural network (nn)-based methods. Circumference measurement was performed using manual ellipsoid, manual contour, automated ellipsoid, or automated contour methods. The relative technical error of measurement (r-TEM; acceptable < 1.5%) and intraclass correlation coefficient (ICC; two-way mixed ANOVA model) were used to assess accuracy and consistency with the tape measure.

Visual-based with manual ellipsoid/contour and rule-based with manual ellipsoid/contour showed acceptable accuracy (r-TEM 0.73%-1.12%). Visual-based with automated ellipsoid and rule-based with automated ellipsoid also demonstrated acceptable accuracy (r-TEM 0.77% and 0.68%). Atlas-based with automated ellipsoid achieved the lowest r-TEM (0.55%), followed by nn-based with automated ellipsoid (r-TEM 0.75%). In contrast, automated contour approaches showed unacceptable accuracy (r-TEM 3.42%-4.21%). Seven nn-based measurements with automated ellipsoid/contour were spurious. ICCs were high across all methods (0.993-0.997); however, manual contour and automated ellipsoid were associated with overfitting issues.

The developed, fully automated algorithm based on (infant) FreeSurfer provides precise and reliable head circumference measurements from pediatric MRI scans with acceptable overall accuracy and excellent consistency with manual measurements using a tape (gold standard). Our algorithm simplifies the head circumference measurement process and provides a reproducible, reader-independent value that enhances the interpretation of neuroradiological findings. Further studies should be conducted to validate with larger sample sizes and to develop deep neural network algorithms for segmentation.