3DFETUS: Standardizing Fetal Facial Planes in 3D Ultrasound

2025-11-13

AI Summary

In fetal ultrasound, fetal motion, pose variability, and operator dependency hinder consistent acquisition of standardized facial planes, compromising diagnostic reproducibility and efficiency. To address this, we propose GT++—a novel algorithm—and 3DFETUS, a dedicated deep learning model, enabling the first end-to-end, anatomy-guided automated localization of standardized 3D fetal facial planes. Our method jointly leverages 3D volumetric data, expert-annotated anatomical landmark points, rigid-body transformation estimation, and deep network optimization. Validation involved both qualitative expert review and quantitative error assessment. Experiments demonstrate mean translational and rotational localization errors of 4.13 mm and 7.93°, respectively—significantly outperforming state-of-the-art methods (p < 0.01). The framework substantially improves clinical localization accuracy and inter-scan reproducibility, establishing a robust, efficient paradigm for standardized fetal facial assessment.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Local Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Acquiring standard facial planes during routine fetal ultrasound (US) examinations is often challenging due to fetal movement, variability in orientation, and operator-dependent expertise. These factors contribute to inconsistencies, increased examination time, and potential diagnostic bias. To address these challenges in the context of facial assessment, we present: 1) GT++, a robust algorithm that estimates standard facial planes from 3D US volumes using annotated anatomical landmarks; and 2) 3DFETUS, a deep learning model that automates and standardizes their localization in 3D fetal US volumes. We evaluated our methods both qualitatively, through expert clinical review, and quantitatively. The proposed approach achieved a mean translation error of 4.13 mm and a mean rotation error of 7.93 degrees per plane, outperforming other state-of-the-art methods on 3D US volumes. Clinical assessments further confirmed the effectiveness of both GT++ and 3DFETUS, demonstrating statistically significant improvements in plane estimation accuracy.

Problem

• Standardizing fetal facial planes in 3D ultrasound imaging
• Addressing inconsistencies from fetal movement and operator variability
• Automating localization of standard facial planes using deep learning

Innovation

• GT++ algorithm estimates fetal planes from 3D ultrasound
• 3DFETUS deep learning model automates fetal plane localization
• Combined approach reduces translation and rotation errors