Related Experiment Video
Updated: Jan 17, 2026
State of the Art Cranial Ultrasound Imaging in Neonates
Published on: February 2, 2015
Advantages of fully automated AI-enhanced algorithm (5D CNS+™) for generating a fetal neurosonogram in clinical
Jann Lennard Scharf1, Michael Gembicki1, Achim Rody1
1Department of Gynecology and Obstetrics, Division of Prenatal Medicine, University Hospital of Schleswig-Holstein, Lübeck, Germany.
Objectives:
The objective was to demonstrate superiority of a fully vs. semi-automated approach (5D CNS+™) and to verify operators could handle and benefit from a fully automated rendering volumetric datasets to generate a complete fetal neurosonogram.
Methods:
A total of 136 stored three-dimensional (3D) volumes of the brain of unselected, structurally normal fetuses were examined. Two operators applied both software versions for detailed assessment of the fetal central nervous system (CNS). The procession time was measured for each operator and for both program versions. The number of correctly calibrated planes were evaluated and necessity for manual adjustment of the planes was registered.
Results:
The intraclass correlation coefficient was 0.507 (0.307-0.648) for semi-automated and 0.782 (0.693-0.846) for fully automated 5D CNS+™. The acquisition time of application for semi-automated 5D CNS+™ was 27.70 s ± 6.28 s for operator 1 and 33.20 s ± 9.67 s for operator 2, for fully automated 5D CNS+™ 10.89 s ± 0.85 s for operator 1 and 10.79 s ± 0.60 s for operator 2 (p<0.0001). The statistical analysis for manually corrected planes by both operators between both software algorithms showed a Bland-Altman-Bias of 1.44/9 planes for operator 1 and 1.45/9 planes for operator 2.
Conclusions:
The fully automated 5D CNS+™ algorithm applied on 3D volume datasets provides examiners regardless their expertise not only enormous time efficiency, but also diagnostic confidence in evaluating details of the fetal CNS. This tremendously simplifies application in clinical routine.
