From Slices to Structures: Unsupervised 3D Reconstruction of Female Pelvic Anatomy from Freehand Transvaginal Ultrasound

2025-08-20

AI Summary

This work addresses the challenge of unsupervised 3D ultrasound reconstruction from freehand transvaginal ultrasound (TVUS) sequences, aiming to recover high-fidelity pelvic anatomical volumes without external tracking devices or pre-trained pose estimators. Methodologically, it introduces anisotropic 3D Gaussian lattices—novel to ultrasound imaging—to establish a slice-aware, differentiable rendering framework; further, it jointly optimizes sensor-free probe motion estimation and geometry priors grounded in ultrasound physics, enabling end-to-end, label-free volumetric reconstruction. Experiments demonstrate that the method produces compact, spatially consistent, and anatomically accurate 3D models, achieving significantly improved reconstruction fidelity while maintaining computational efficiency. This work establishes a new paradigm for low-cost, scalable AI-assisted pelvic ultrasound diagnosis.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Learning with Manifolds
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

Volumetric ultrasound has the potential to significantly improve diagnostic accuracy and clinical decision-making, yet its widespread adoption remains limited by dependence on specialized hardware and restrictive acquisition protocols. In this work, we present a novel unsupervised framework for reconstructing 3D anatomical structures from freehand 2D transvaginal ultrasound (TVS) sweeps, without requiring external tracking or learned pose estimators. Our method adapts the principles of Gaussian Splatting to the domain of ultrasound, introducing a slice-aware, differentiable rasterizer tailored to the unique physics and geometry of ultrasound imaging. We model anatomy as a collection of anisotropic 3D Gaussians and optimize their parameters directly from image-level supervision, leveraging sensorless probe motion estimation and domain-specific geometric priors. The result is a compact, flexible, and memory-efficient volumetric representation that captures anatomical detail with high spatial fidelity. This work demonstrates that accurate 3D reconstruction from 2D ultrasound images can be achieved through purely computational means, offering a scalable alternative to conventional 3D systems and enabling new opportunities for AI-assisted analysis and diagnosis.

Problem

• Reconstructing 3D pelvic anatomy from 2D ultrasound sweeps
• Eliminating need for external tracking hardware
• Overcoming limitations of specialized ultrasound acquisition protocols

Innovation

• Unsupervised 3D reconstruction from ultrasound sweeps
• Gaussian Splatting adapted with slice-aware rasterizer
• Sensorless probe motion estimation with geometric priors