Imitation Learning for Robotic Assisted Ultrasound Examination of Deep Venous Thrombosis using Kernelized Movement Primitives

TL;DR

This paper presents a novel imitation learning approach using Kernelized Movement Primitives to train a robotic ultrasound system for DVT diagnosis, improving consistency and reducing operator skill dependence.

Contribution

It introduces a new ergonomic demonstration device and applies KMPs to capture and generalize sonographer skills for autonomous DVT ultrasound exams.

Findings

KMP-based RUS replicates expert force control and image quality.

The method outperforms manual force profile approaches.

Demonstrates effective generalization beyond training demonstrations.

Abstract

Deep Vein Thrombosis (DVT) is a common yet potentially fatal condition, often leading to critical complications like pulmonary embolism. DVT is commonly diagnosed using Ultrasound (US) imaging, which can be inconsistent due to its high dependence on the operator's skill. Robotic US Systems (RUSs) aim to improve diagnostic test consistency but face challenges with the complex scanning pattern needed for DVT assessment, where precise control over US probe pressure is crucial for indirectly detecting occlusions. This work introduces an imitation learning method, based on Kernelized Movement Primitives (KMP), to standardize DVT US exams by training an autonomous robotic controller using sonographer demonstrations. A new recording device design enhances demonstration ergonomics, integrating with US probes and enabling seamless force and position data recording. KMPs are used to capture scanning skills, linking scan trajectory and force, enabling generalization beyond the demonstrations. Our approach, evaluated on synthetic models and volunteers, shows that the KMP-based RUS can replicate an expert's force control and image quality in DVT US examination. It outperforms previous methods using manually defined force profiles, improving exam standardization and reducing reliance on specialized sonographers.