Multi-pass Volume Reconstruction for Freehand Ultrasound: Demonstration in Simulation, Phantom, and In Vivo Kidney.

Abstract

This work describes the development and validation of an algorithm to improve ultrasound volume reconstruction from noisy initial scans taken using a tracked freehand ultrasound device. The algorithm was first tested and refined in simulation using an approximate kidney shape model re-sliced to represent various real life scan conditions. Next, an Intel RealSense D435i camera was used to track the pose of a commercial ultrasound probe. This device was used to scan a phantom with a known volume and shape. Finally, repeated scans were taken in vivo to test the repeatability of volume measurements. The simulation experiments were used to refine algorithm hyperparameters. The volume of the phantom was measured to within 2.5-17% (1-11.5% with automatic pass finding) of ground truth for four different scan styles, compared to traditional methods that underestimate the volume by 17.5%. In 11 human subjects, right kidney volume was measured within between 3.6-14.6% (7.7-23.3% with automatic pass finding) variation between scans. The proposed algorithm was demonstrated to produce repeatable volume measurement results in both phantom and in vivo scans. The proposed algorithm improves the clinical translatability and repeatability of freehand volume ultrasound systems.