Evaluating Usability of a Touchless Image Viewer in the Operating Room

Area of Science:

• Medical imaging
• Surgical technology
• Human-computer interaction

Background:

• Intraoperative access to patient-specific imaging (CT, MRI) is crucial for surgical success and safety.
• Hand gesture recognition offers an alternative input method for medical image viewers during surgery.
• Previous research highlighted the need for usability evaluations of such systems.

Purpose of the Study:

• To assess the accuracy and usability of a new software system integrating machine learning-based gesture recognition into an existing image viewer.
• To evaluate the system's performance in a simulated operating room environment.

Main Methods:

• A prospective, observational pilot study involving eight surgeons.
• Surgeons performed standardized tasks using the gesture recognition software in a sterile, simulated operating room.
• Usability was assessed using the System Usability Scale (SUS); neural network accuracy was also evaluated.

Main Results:

• The neural network demonstrated 98.94% accuracy in gesture prediction.
• The system achieved an average usability score of 80.25 points on the SUS.
• Surgeons reported good overall usability, with identified areas for improvement.

Conclusions:

• The novel gesture recognition software exhibits good usability and high technical accuracy.
• Standard PC hardware facilitates easy integration into operating room workflows.
• Further usability studies are recommended to refine the system.