RapidVol: Rapid Reconstruction of 3D Ultrasound Volumes from Sensorless 2D Scans

TL;DR

RapidVol is a neural framework that significantly accelerates and improves the accuracy of reconstructing 3D ultrasound volumes from 2D scans, making it more robust and efficient than previous methods.

Contribution

It introduces a tensor-rank decomposition-based neural representation for fast, accurate, and robust 3D ultrasound reconstruction from 2D scans, reducing computational time.

Findings

Over 3x faster than prior methods

46% more accurate in reconstructions

More robust to pose inaccuracies

Abstract

Two-dimensional (2D) freehand ultrasonography is one of the most commonly used medical imaging modalities, particularly in obstetrics and gynaecology. However, it only captures 2D cross-sectional views of inherently 3D anatomies, losing valuable contextual information. As an alternative to requiring costly and complex 3D ultrasound scanners, 3D volumes can be constructed from 2D scans using machine learning. However this usually requires long computational time. Here, we propose RapidVol: a neural representation framework to speed up slice-to-volume ultrasound reconstruction. We use tensor-rank decomposition, to decompose the typical 3D volume into sets of tri-planes, and store those instead, as well as a small neural network. A set of 2D ultrasound scans, with their ground truth (or estimated) 3D position and orientation (pose) is all that is required to form a complete 3D reconstruction. Reconstructions are formed from real fetal brain scans, and then evaluated by requesting novel cross-sectional views. When compared to prior approaches based on fully implicit representation (e.g. neural radiance fields), our method is over 3x quicker, 46% more accurate, and if given inaccurate poses is more robust. Further speed-up is also possible by reconstructing from a structural prior rather than from scratch.