Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

An Anatomy-Aware Shared Control Approach for Assisted Teleoperation of Lung Ultrasound Examinations

Davide Nardi, Edoardo Lamon, Daniele Fontanelli, Matteo Saveriano, Luigi Palopoli

TL;DR

Anatomy variability limits autonomous ultrasound, so this work proposes an anatomy-aware shared-control framework for teleoperated lung ultrasound based on a SKEL biomechanical model to generate patient-specific virtual fixtures that constrain probe position and orientation. The method combines 3D SKEL-based patient modelling, rib-aware VF constraints (both position and orientation), visual overlays, vibrotactile feedback, and Cartesian impedance control to assist probe placement and imaging alignment. Two experiments (naive operators on a single patient and an expert on six patients) show improved usability and a substantial reduction in exam duration (~23% for the expert) while maintaining anatomical targeting accuracy within a few centimeters. This approach demonstrates a practical path toward faster, more objective, and repeatable remote LUS exams, with future plans for online model updates and force-sensing to capture viscoelastic properties.

Abstract

Although fully autonomous systems still face challenges due to patients' anatomical variability, teleoperated systems appear to be more practical in current healthcare settings. This paper presents an anatomy-aware control framework for teleoperated lung ultrasound. Leveraging biomechanically accurate 3D modelling, the system applies virtual constraints on the ultrasound probe pose and provides real-time visual feedback to assist in precise probe placement tasks. A twofold evaluation, one with 5 naive operators on a single volunteer and the second with a single experienced operator on 6 volunteers, compared our method with a standard teleoperation baseline. The results of the first one characterised the accuracy of the anatomical model and the improved perceived performance by the naive operators, while the second one focused on the efficiency of the system in improving probe placement and reducing procedure time compared to traditional teleoperation. The results demonstrate that the proposed framework enhances the physician's capabilities in executing remote lung ultrasound, reducing more than 20% of execution time on 4-point acquisitions, towards faster, more objective and repeatable exams.

An Anatomy-Aware Shared Control Approach for Assisted Teleoperation of Lung Ultrasound Examinations

TL;DR

Anatomy variability limits autonomous ultrasound, so this work proposes an anatomy-aware shared-control framework for teleoperated lung ultrasound based on a SKEL biomechanical model to generate patient-specific virtual fixtures that constrain probe position and orientation. The method combines 3D SKEL-based patient modelling, rib-aware VF constraints (both position and orientation), visual overlays, vibrotactile feedback, and Cartesian impedance control to assist probe placement and imaging alignment. Two experiments (naive operators on a single patient and an expert on six patients) show improved usability and a substantial reduction in exam duration (~23% for the expert) while maintaining anatomical targeting accuracy within a few centimeters. This approach demonstrates a practical path toward faster, more objective, and repeatable remote LUS exams, with future plans for online model updates and force-sensing to capture viscoelastic properties.

Abstract

Although fully autonomous systems still face challenges due to patients' anatomical variability, teleoperated systems appear to be more practical in current healthcare settings. This paper presents an anatomy-aware control framework for teleoperated lung ultrasound. Leveraging biomechanically accurate 3D modelling, the system applies virtual constraints on the ultrasound probe pose and provides real-time visual feedback to assist in precise probe placement tasks. A twofold evaluation, one with 5 naive operators on a single volunteer and the second with a single experienced operator on 6 volunteers, compared our method with a standard teleoperation baseline. The results of the first one characterised the accuracy of the anatomical model and the improved perceived performance by the naive operators, while the second one focused on the efficiency of the system in improving probe placement and reducing procedure time compared to traditional teleoperation. The results demonstrate that the proposed framework enhances the physician's capabilities in executing remote lung ultrasound, reducing more than 20% of execution time on 4-point acquisitions, towards faster, more objective and repeatable exams.
Paper Structure (19 sections, 6 equations, 8 figures)

This paper contains 19 sections, 6 equations, 8 figures.

Table of Contents

  1. INTRODUCTION
  2. METHODOLOGY
  3. Patient Body Modelling
  4. Anatomical Model using SKEL
  5. Rib Cage Definition
  6. Anatomical Virtual Fixtures
  7. Forbidden Region VF -- for Position
  8. Conic Constraints VF -- for Orientation
  9. Visual and Vibrotactile Feedback -- for Position and Orientation
  10. Robot Interaction Control
  11. EXPERIMENTS
  12. Experimental Protocols
  13. Naïve Operators on one Patient
  14. Expert Operator on 6 Patients
  15. Results and Discussion
  16. ...and 4 more sections

Figures (8)

  • Figure 1: High-level overview of the proposed framework.
  • Figure 2: Anatomical perception data and models. From left: the RGB-D image of one of the two fixed cameras, the merged point cloud filtered with the YOLO mask, and the reconstructed volumetric and skeletal model.
  • Figure 3: Visual feedback generated by ribs-shaped position VF (salmon), and conic orientation VF. The latter restricts the motion of the axis of the rotation matrix (red for $x$-axis, green for $y$-axis, and blue for $z$-axis).
  • Figure 4: Experimental setup. (left) remote follower side and subject, (right) leader side with haptic interface used by the operator. A video of the experiment is available in the multimedia attachment.
  • Figure 5: Examples of lung ultrasound images sampled from the US probe at the end-effector of the robot: (left) full pleural line, (right) partial pleural line due to rib shadowing.
  • ...and 3 more figures