4 Applications of Machine Learning in Surgical Robotics

4 applications of machine learning (ML) in surgical robotics :

• Automation of Suturing

• Evaluation of Surgical Skills

• Improving Surgical Robotic Materials

• Surgical Workflow Modeling

Automation of suturing

In 2013, a team of researchers at the University of California at Berkeley published research on the application of an algorithm for automated suturing performed by robots.

The algorithm was tested and simulated on two robot models: the Raven II robot and the PR2 robot.

The Raven robot is designed for laparoscopic surgery, while the PR2 platform appears to be adaptable across various robotic applications.

The Berkeley research team reported an overall success rate of 87 percent of successful suturing. However, the increased complexity of the suturing scenarios tended to correspond with decreased robot accuracy.

These results are encouraging because suturing has been identified as a key factor limiting the use of laparoscopy among surgeons.

Using a pig model, the robot’s performance was compared to the work of five human surgeons in three different procedures: “open surgery, laparoscopic, and robot-assisted surgery.” Overall, the researchers reported comparable or better results to standard surgical performance.

Evaluation of surgical skills

A study presented at the 2016 World Congress on Engineering and Computer Science discussed using machine learning to evaluate surgeon performance in robot-assisted minimally invasive surgery.

The research team evaluated data collected from suturing performance and classified surgeons into two categories: novice and expert.

The machine learning algorithm was developed to measure the following six features:

• Completion time

• Path length

• Depth perception

• Speed

• Smoothness

• Curvature

This is a promising result, offering the possibility of more standardized evaluation methods.

Improving surgical robotic materials

In the case of neurosurgery, where particularly sensitive maneuvering is required, robots often lack the necessary dexterity to operate effectively and prevent injury.

Researchers at the University of California, San Diego (UCSD) Advanced Robotics and Controls Lab are exploring machine learning applications to improve surgical robotics, especially “continuum robots”.

Surgical workflow modeling

To improve how clinical reports are processed, a team of researchers developed a clinical information extraction system called IDEAL-X.

The manual process is frequently time-consuming and does not provide automatic user feedback on how to improve the process.

The IDEAL-X adaptive learning platform uses machine learning to understand how a user generates reports and to predict patterns to improve the speed and efficiency of the process.