Skip to content

The clinical efficacy of deep learning artificial intelligence in detecting fetal intracranial malformations in ultrasonography

The clinical efficacy of deep learning artificial intelligence in detecting fetal intracranial malformations in ultrasonography

Status
Active, not recruiting
Phases
Early Phase 1
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2100048233
Enrollment
Unknown
Registered
2021-07-05
Start date
2021-07-05
Completion date
Unknown
Last updated
2022-03-14

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

fetal central nervous system malformation

Interventions

Gold Standard:Confirmed either by prenatal or postnatal MRI, follow-up examination, or autopsy
and the expert consensus, especially for normal cases.
Index test:Macro AUC value

Sponsors

the First Affiliated Hospital of Sun Yat-sen University
Lead Sponsor

Eligibility

Sex/Gender
All

Inclusion criteria

Inclusion criteria: 1. Inclusion criteria for images: (1) Cranial ultrasound two-dimensional screening standard slice images; (2) Moderate image magnification; (3) The skull ring is complete; (4) No overlapping of measurement marks; (5) No obvious sound attenuation. 2. Selection criteria of who read the film: (1) Qualified as a medical practitioner in imaging medicine; (2) Engaged in obstetrics and gynecology ultrasound for more than 2 years, and scanned about 1,000 fetuses.

Exclusion criteria

Exclusion criteria: 1. Image exclusion criteria: (1) Two-dimensional ultrasound color Doppler image of fetal brain; (2) The image quality is not clear.

Design outcomes

Primary

MeasureTime frame
Reader's overall diagnostic performance of pictures and videos;

Countries

China

Contacts

Public ContactXie Hongning

the First Affiliated Hospital of Sun Yat-sen University

xiehn@mail.sysu.edu.cn+86 13527870288

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 8, 2026