Preliminary Evaluation of an Ultrasound-Guided Robotic System for Autonomous Percutaneous Intervention

TL;DR

The paper tackles the problem of variability and inefficiency in ultrasound-guided biopsies by introducing a fully autonomous end-to-end robotic system for US-guided percutaneous interventions. It integrates ATIR atlas-based registration for multi-organ localization, autonomous 3D US reconstruction, CIR-DBSCAN-based lesion detection, and INGS for needle guidance, all executed without human intervention. Phantom experiments show a targeting error of $5.74 \pm 2.70$ mm under impedance control and demonstrate 100% lesion targeting with robust surface contact, supporting the potential for autonomous biopsies of targets larger than $5$ mm. This work establishes a practical, automated workflow that could standardize US-guided diagnostic procedures and reduce operator dependency, with future work focusing on ex vivo and motion-compensation studies.

Abstract

Cancer cases have been rising globally, resulting in nearly 10 million deaths in 2023. Biopsy, crucial for diagnosis, is often performed under ultrasound (US) guidance, demanding precise hand coordination and cognitive decision-making. Robot-assisted interventions have shown improved accuracy in lesion targeting by addressing challenges such as noisy 2D images and maintaining consistent probe-to-surface contact. Recent research has focused on fully autonomous robotic US systems to enable standardized diagnostic procedures and reproducible US-guided therapy. This study presents a fully autonomous system for US-guided needle placement capable of performing end-to-end clinical workflow. The system autonomously: 1) identifies the liver region on the patient's abdomen surface, 2) plans and executes the US scanning path using impedance control, 3) localizes lesions from the US images in real-time, and 4) targets the identified lesions, all without human intervention. This study evaluates both position and impedance-controlled systems. Validation on agar phantoms demonstrated a targeting error of 5.74 +- 2.70 mm, highlighting its potential for accurately targeting tumors larger than 5 mm. Achieved results show its potential for a fully autonomous system for US-guided biopsies.

Figures (6)

• Figure 1: Ultrasound-guided robotic system for autonomous percutaneous interventions showing: (a) a KUKA iiwa7 with Intelligent Needle Guidance system, an ultrasound probe and mannequin setup for the experiments, and (b) top view of the mannequin showing key points for organ localization and the desired safe scan region for the liver interventions.
• Figure 2: System architecture for US-guided autonomous percutaneous intervention showing its modules for: (1) organ localization, (2) trajectory panning and lesion detection, and (3) needle manipulation.
• Figure 3: Showing coordinate system transformations between various components of the system.
• Figure 4: ATIR: Atlas-based Transformation and Iterative Registration: (a) Initial point clouds with keypoints (b) Point clouds aligned with the initial transform generated by keypoint matching (c) Point clouds aligned after refining the initial transform using ICP and corresponding 3D organs (d) Corresponding ROI for Ultrasound scanning on the surface of the subject's point cloud *Only the liver is visualized, as scanning was limited to this organ for experiments
• Figure 5: Needle driver assembly and insertion angle calculation for autonomous needle insertion.