Diagnostic Trial of a Vision Transformer-Based Ultrasound AI Model for Placenta Accreta Spectrum

NCT07643090 | Recruiting DMC

• 1 other identifier: Ethics Review NO. 286A01
• Study Type: observational
• Target: 561
• Locations: 1 country
• Sites: 1

Brief Summary

This study develops an end-to-end Vision Transformer (ViT)-based artificial intelligence system for ultrasound-based diagnosis of placenta accreta spectrum (PAS), aiming to improve the accuracy and efficiency of prenatal screening using standardized ultrasound video inputs.

Conditions

Placenta Accreta Spectrum

Keywords

Placenta Accreta Spectrum; Ultrasonography; Artificial Intelligence; Prenatal Diagnosis; Vision Transformer

Outcome Measures

Primary Outcomes (1)

• Diagnostic performance of the end-to-end Vision Transformer (ViT)-based ultrasound AI model for placenta accreta spectrum (PAS)

  Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUC) of the model.

  At delivery (following confirmation of PAS status by surgical and/or pathological findings)

Secondary Outcomes (3)

• Clinical Feasibility of the Standardized Ultrasound Video Recording Method

  At enrollment during the ultrasound examination

• Consistency and Efficiency Between the AI Model and Physician Diagnosis

  At enrollment during the ultrasound examination

• Safety of the AI Model

  At delivery, when PAS status and maternal outcomes are assessed

Interventions

Vision Transformer-Based End-to-End Ultrasound Artificial Intelligence Model DIAGNOSTIC_TEST

An end-to-end ultrasound AI model based on the Vision Transformer (ViT) architecture was developed for the diagnosis of placenta accreta spectrum (PAS) using standardized ultrasound video inputs. Ultrasound Video Acquisition Protocol: With the patient in the supine position, the operator scanned the lower abdomen using a conventional grayscale probe. Video recording was performed in gray-scale mode for approximately 20-30 seconds, ensuring that the entire scanning region from the lower uterine segment to the uterine fundus was comprehensively captured.

Eligibility Criteria

• Age: 18 Years - 45 Years
• Sex: female
• Healthy Volunteers: No
• Age Groups: Adult (18-64)
• Sampling Method: Non-Probability Sample

Study Population

Pregnant women aged 18-45 years; Gestational age between 24 and 34 weeks; Pregnant women with a history of placenta previa or with an anterior placenta.

You may qualify if:

• Pregnant women aged between 18 and 45 years;
• Gestational age between 24 and 34 weeks;
• Pregnant women with a history of placenta previa;
• Pregnant women with an anterior placenta;
• Willingness to participate in the study and provision of written informed consent.

You may not qualify if:

• Failure to provide written informed consent;
• Presence of severe complications that precluded continuation of pregnancy;
• Inability to comply with study procedures for other reasons.

Sponsors & Collaborators

• FANG HE: lead

Study Sites (1)

The Third Affiliated Hospital, Guangzhou Medical University

Guangzhou, Guangdong, 510150, China

RECRUITING

MeSH Terms

Conditions

Placenta Accreta

Condition Hierarchy (Ancestors)

Obstetric Labor Complications; Pregnancy Complications; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Placenta Diseases

Central Study Contacts

Fang He, M.D, PhD

CONTACT

+86 13724831279; Gzhefang@gzhmu.edu.cn

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: PROSPECTIVE
• Target Duration: 12 Months
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Chief Physician/Professor of the Obstetrics Department

Study Record Dates

• First Submitted: June 2, 2026
• First Posted: June 11, 2026
• Study Start: September 1, 2025
• Primary Completion (Estimated): September 1, 2027
• Study Completion (Estimated): December 31, 2027
• Last Updated: June 11, 2026

Record last verified: 2026-06

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)