EP01.25: Advantages of 5D CNS<sup>Deep</sup> versus 5D CNS<sup>+</sup> for generating a fetal neurosonogram in clinical routine

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 CNSDeep 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 CNSDeep 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/m2 (16.90 to 44.05 kg/m2). 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 CNSDeep. 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 CNSDeep 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 CNSDeep 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’.

Authors

Institutions

Publication Details

Journal
Ultrasound in Obstetrics and Gynecology
Published
2024-09-01
DOI
https://doi.org/10.1002/uog.28040
Primary Topic
Neonatal and fetal brain pathology
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

EP01.25: Advantages of 5D CNSDeep versus 5D CNS+ for generating a fetal neurosonogram in clinical routine

Amrei Welp, Christoph Dracopoulos, M Gembicki, Jann Lennard Scharf et al.
Ultrasound in Obstetrics and Gynecology
Neonatal and fetal brain pathology
article

EP01.25: Advantages of 5D CNSDeep versus 5D CNS+ for generating a fetal neurosonogram in clinical routine

Amrei Welp, Christoph Dracopoulos, M Gembicki, Jann Lennard Scharf, J. Weichert
article en

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 CNSDeep 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 CNSDeep 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/m2 (16.90 to 44.05 kg/m2). 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 CNSDeep. 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 CNSDeep 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 CNSDeep 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’.

Ultrasound in Obstetrics and GynecologyVol. 64(S1)
University Hospital Schleswig-Holstein (DE), University of Lübeck (DE)
Zero hunger
Openalex Percentile: Top 76%
Neonatal and fetal brain pathology
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.