This white paper explores the clinical use of novel tools in fetal 3D ultrasound, focusing on EzVolume™, Fetal Face Auto Detection (FAD), and PortraitVue™ to enhance fetal face visualization and workflow efficiency.
The paper outlines how 3D obstetric ultrasound plays a central role in evaluating fetal anatomy and facial structures, particularly when assessing anomalies. However, conventional 3D imaging may be limited by acoustic shadowing, suboptimal fetal position, and manual segmentation challenges.
EzVolume™ is presented as an AI-based automatic segmentation tool that identifies key fetal structures within a 3D volume dataset. By reducing manual interaction and simplifying volume navigation, it supports faster and more consistent analysis.
Fetal Face Auto Detection (FAD) automatically detects and isolates the fetal face within the acquired 3D volume. This reduces operator dependency and helps ensure accurate facial visualization even in technically challenging cases.
PortraitVue™ enhances 3D rendering by providing realistic surface visualization with improved depth perception and texture detail. This contributes to clearer depiction of facial contours and anatomical relationships.
Together, these tools aim to streamline 3D obstetric ultrasound workflow, reduce manual post-processing, and improve reproducibility in fetal face visualization. The paper emphasizes that integrating AI-assisted segmentation and rendering technologies may support more efficient examinations while maintaining diagnostic quality in fetal 3D ultrasound.
