EP01.25: Advantages of 5D CNSDeep versus 5D CNS+ for generating a fetal neurosonogram in clinical routine
Year: 2024
Type: conference-abstract
Abstract: A comprehensive prenatal workup of the entire central nervous system (CNS) anatomy in its complexity remains challenging. The objective was to demonstrate the superiority of 5D CNS versus 5D CNS and to verify that even less experienced operators could handle and benefit from a fully automated rendering of a fetal neurosonogram in clinical routine. A total of 116 stored 3D volumes of the brain of unselected, structurally normal second and third trimester fetuses were examined. Two operators independently applied both programs 5D CNS and 5D CNS separately for detailed assessment of the fetal CNS. The procession time was measured for each operator and for both program versions. The number of correctly calibrated planes were evaluated and the requirement for manual adjustment of the planes was registered. Descriptive statistics, paired t-test and Wilcoxon test were performed. The intraclass correlation coefficient (ICC) was calculated for interoperator reproducibility. Bland-Altman plot was used to test agreement between both software algorithms. The mean maternal age was 32 years (ranging from 23 to 43 years), and the mean maternal body mass index prior to pregnancy was 23.44 kg/m (16.90 to 44.05 kg/m). The gestational age ranged from 17.7 to 27.7 (average 22.5 weeks). The ICC was 0.614 (0.321 – 0.780) for 5D CNS and 0.818 (0.677 – 0.897) for 5D CNS. The acquisition time of application for 5D CNS was 27.41 s ± 4.86 s for operator 1 and 35.45 s ± 10.50 s for operator 2 (p < 0.0001), for 5D CNS 11.09 s ± 0.65 s for operator 1 and 11.13 s ± 0.47 s for operator 2 (p 0.744). The statistical analysis for manually corrected planes by both operators between both software algorithms showed a Bland-Altman-Bias of 1.45/9 planes for operator 1 and 1.35/9 planes for operator 2. 5D CNS provides fetal sonologists, regardless of practical skills, not only enormous time efficiency, but also diagnostic confidence. This simplifies application in clinical routine ‘on the fly’.
DOI: 10.1002/uog.28040
Institution: University Hospital Schleswig-Holstein
Language: English
Field: Medicine
Domain: Health Sciences
Open Access status: bronze
OpenAlex ID: W4402358470