UltraGelBot: Autonomous Gel Dispenser for Robotic Ultrasound
Deepak Raina, Ziming Zhao, Richard Voyles, Juan Wachs, Subir K. Saha, S. H. Chandrashekhara
TL;DR
The paper addresses operator-dependence in gel application during robotic ultrasound (RUS) examinations, which can cause poor acoustic coupling and longer procedure times. It introduces UltraGelBot, an autonomous end-effector that detects gel with an onboard camera using a Faster R-CNN detector and dispenses gel via a piston-driven syringe; a modular gripper also supports various probe geometries. Quantitative results on forearm artery ultrasound show the gel-dispensing system yields an image-quality increase of $18.6\%$ and a scanning-time reduction of $37.2\%$, with user workload improvements per NASA TLX. The approach demonstrates autonomous gel application within a robotic platform, reducing operator involvement and potentially improving safety and efficiency; limitations include single-camera constraint, with plans for multiple cameras and in-vivo testing.
Abstract
Telerobotic and Autonomous Robotic Ultrasound Systems (RUS) help alleviate the need for operator-dependability in free-hand ultrasound examinations. However, the state-of-the-art RUSs still rely on a human operator to apply the ultrasound gel. The lack of standardization in this process often leads to poor imaging of the scanned region. The reason for this has to do with air-gaps between the probe and the human body. In this paper, we developed a end-of-arm tool for RUS, referred to as UltraGelBot. This bot can autonomously detect and dispense the gel. It uses a deep learning model to detect the gel from images acquired using an on-board camera. A motorized mechanism is also developed, which will use this feedback and dispense the gel. Experiments on phantom revealed that UltraGelBot increases the acquired image quality by $18.6\%$ and reduces the procedure time by $37.2\%$.