RSV: Robotic Sonography for Thyroid Volumetry

TL;DR

This paper introduces a robotic ultrasound system that combines neural network segmentation and robotic scanning to improve the accuracy and reproducibility of thyroid volume measurements, outperforming conventional methods especially for non-experts.

Contribution

The novel integration of neural network-based segmentation with robotic ultrasound scanning significantly enhances thyroid volumetry accuracy and consistency over traditional 2D ultrasound.

Findings

Robotic system reduces measurement error from 20.85% to 8.23% in experts.

Non-expert users' errors decreased by up to 85%.

Motion-guided robot movement outperforms naive linear motion.

Abstract

In nuclear medicine, radioiodine therapy is prescribed to treat diseases like hyperthyroidism. The calculation of the prescribed dose depends, amongst other factors, on the thyroid volume. This is currently estimated using conventional 2D ultrasound imaging. However, this modality is inherently user-dependant, resulting in high variability in volume estimations. To increase reproducibility and consistency, we uniquely combine a neural network-based segmentation with an automatic robotic ultrasound scanning for thyroid volumetry. The robotic acquisition is achieved by using a 6 DOF robotic arm with an attached ultrasound probe. Its movement is based on an online segmentation of each thyroid lobe and the appearance of the US image. During post-processing, the US images are segmented to obtain a volume estimation. In an ablation study, we demonstrated the superiority of the motion guidance algorithms for the robot arm movement compared to a naive linear motion, executed by the robot in terms of volumetric accuracy. In a user study on a phantom, we compared conventional 2D ultrasound measurements with our robotic system. The mean volume measurement error of ultrasound expert users could be significantly decreased from 20.85+/-16.10% to only 8.23+/-3.10% compared to the ground truth. This tendency was observed even more in non-expert users where the mean error improvement with the robotic system was measured to be as high as $85\%$ which clearly shows the advantages of the robotic support.