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

Diagnostic Trial of Vision Transformer-Based End-to-End Ultrasound Artificial Intelligence Model for Assisting in the Diagnosis of Placenta Accreta Spectrum Disorders: An Investigator-Initiated Prospective Clinical Study

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.

Study Overview

• Status: Recruiting
• Conditions: Placenta Accreta Spectrum
• Intervention / Treatment: Diagnostic test: Vision Transformer-Based End-to-End Ultrasound Artificial Intelligence Model

Detailed Description

Placenta accreta spectrum (PAS) is a life-threatening obstetric disorder involving abnormal placental invasion into the uterine wall, which is associated with severe maternal and neonatal complications. Despite advances in imaging, prenatal diagnosis remains challenging due to variability in ultrasound interpretation and reliance on operator expertise.

This study will establish a standardized ultrasound video acquisition protocol and develop a deep learning-based model using Vision Transformer (ViT) architecture to process dynamic ultrasound sequences. The model will be trained using clinically confirmed postpartum outcomes as reference labels.

The diagnostic performance of the system will be systematically evaluated, with the goal of improving consistency in interpretation and supporting more efficient clinical decision-making in prenatal PAS screening.

• Study Type: Observational
• Enrollment (Estimated): 561

Contacts and Locations

• Study Contact: Name: Fang He, M.D, PhD; Phone Number: +86 13724831279; Email: Gzhefang@gzhmu.edu.cn

Study Locations

• China
  • Guangdong
    • Guangzhou, Guangdong, China, 510150
      • Recruiting
      • The Third Affiliated Hospital, Guangzhou Medical University
      • Contact: Fang He, MD, PhD; Phone Number: +86 13724831279; Email: Gzhefang@gzhmu.edu.cn

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult
• Accepts Healthy Volunteers: No

• 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.

Description

Inclusion criteria:

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

Exclusion criteria:

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

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
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 Outcome Measures

Outcome Measure	Measure Description	Time Frame
Clinical Feasibility of the Standardized Ultrasound Video Recording Method	Completion Rate (Proportion of patients who successfully complete the standardized recording) and time consumption (Mean recording time)	At enrollment during the ultrasound examination
Consistency and Efficiency Between the AI Model and Physician Diagnosis	Diagnostic Consistency: Kappa coefficient used to evaluate the consistency between the AI model's diagnoses and those of experienced ultrasound physicians (Kappa > 0.75 indicates good agreement).	At enrollment during the ultrasound examination
Safety of the AI Model	False Negative Rate: Proportion of missed PAS-positive patients and the impact on patient outcomes .	At delivery, when PAS status and maternal outcomes are assessed

Collaborators and Investigators

• Sponsor: FANG HE

Study record dates

Study Major Dates

• Study Start (Actual): September 1, 2025
• Primary Completion (Estimated): September 1, 2027
• Study Completion (Estimated): December 31, 2027

Study Registration Dates

• First Submitted: June 2, 2026
• First Submitted That Met QC Criteria: June 8, 2026
• First Posted (Actual): June 11, 2026

Study Record Updates

• Last Update Posted (Actual): June 11, 2026
• Last Update Submitted That Met QC Criteria: June 8, 2026
• Last Verified: June 1, 2026

More Information

Terms related to this study

• Keywords: Artificial Intelligence; Ultrasonography; Prenatal Diagnosis; Placenta Accreta Spectrum; Vision Transformer
• Additional Relevant MeSH Terms: Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Obstetric Labor Complications; Pregnancy Complications; Placenta Diseases; Placenta Accreta
• Other Study ID Numbers: Ethics Review NO. 286A01

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No