English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Robot-assisted minimally invasive surgery is improving surgeon performanceand patient outcomes. This innovation is also turning what has been asubjective practice into motion sequences that can be precisely measured. Agrowing number of studies have used machine learning to analyze video andkinematic data captured from surgical robots. In these studies, models aretypically trained on benchmark datasets for representative surgical tasks toassess surgeon skill levels. While they have shown that novices and experts canbe accurately classified, it is not clear whether machine learning can separatehighly proficient surgeons from one another, especially without video data. Inthis study, we explore the possibility of using only kinematic data to predictsurgeons of similar skill levels. We focus on a new dataset created fromsurgical exercises on a simulation device for skill training. A simple,efficient encoding scheme was devised to encode kinematic sequences so thatthey were amenable to edge learning. We report that it is possible to identifysurgical fellows receiving near perfect scores in the simulation exercisesbased on their motion characteristics alone. Further, our model could beconverted to a spiking neural network to train and infer on the Nengosimulation framework with no loss in accuracy. Overall, this study suggeststhat building neuromorphic models from sparse motion features may be apotentially useful strategy for identifying surgeons and gestures with chipsdeployed on robotic systems to offer adaptive assistance during surgery andtraining with additional latency and privacy benefits.

Recurrent and Spiking Modeling of Sparse Surgical Kinematics