🤖 AI Summary
To address limited ultrasound accessibility in remote regions, this study proposes a novel long-distance mixed reality (MR)–enabled tele-ultrasound paradigm integrating haptic feedback for real-world clinical settings. The system combines HoloLens 2, a force-feedback haptic interface, low-latency audiovisual streaming, and a standardized procedural guidance protocol, enabling novice operators to perform ultrasound scans under real-time expert supervision across provinces (754 km). Without requiring prior training, operators achieved accurate anatomical localization and image acquisition. In 11 clinical trials, all participants successfully obtained five standard diagnostic views and associated biometric measurements. Double-blind evaluation confirmed a 96.4% rate of diagnostically usable images. These results demonstrate the high reliability and clinical feasibility of this human–machine collaborative tele-ultrasound framework for expanding equitable access to point-of-care ultrasound in underserved areas.
📝 Abstract
Ultrasound is a hand-held, low-cost, non-invasive medical imaging modality which plays a vital role in diagnosing various diseases. Despite this, many rural and remote communities do not have access to ultrasound scans due to the lack of local experts trained to perform them. To address this challenge, we built a mixed reality and haptics-based tele-ultrasound system to enable an expert to precisely guide a novice remotely in carrying out an ultrasound exam. The precision and flexibility of our solution makes it more practical than existing tele-ultrasound solutions. We tested the system in Skidegate on the islands of Haida Gwaii, BC, Canada, with the experts positioned 754 km away at the University of British Columbia, Vancouver, Canada. We performed 11 scans with 10 novices and 2 experts. The experts were tasked with acquiring 5 target images and measurements in the epigastric region. The novices of various backgrounds and ages were all inexperienced in mixed reality and were not required to have prior ultrasound experience. The captured images were evaluated by two radiologists who were not present for the tests. These results are discussed along with new insights into the human computer interaction in such a system. We show that human teleoperation is feasible and can achieve high performance for completing remote ultrasound procedures, even at a large distance and with completely novice followers.