Real-Time Expanded Field-of-View for Minimally Invasive Surgery Using Multi-Camera Visual Simultaneous Localization...

Area of Science:

• Medical Technology
• Computer Vision
• Surgical Robotics

Background:

• Minimally invasive surgery offers patient benefits but is challenged by a narrow field of view.
• Enhancing surgical visualization is crucial for improving surgeon performance and patient outcomes.

Purpose of the Study:

• To develop a real-time dynamic field-of-view expansion system for minimally invasive surgery.
• To improve the surgeon's experience by providing a broader and more comprehensive view.

Main Methods:

• Adapted the monocular ORB-SLAM (Oriented FAST and Rotated BRIEF-Simultaneous Localization and Mapping) for multi-camera setups.
• Introduced new threads for relative camera pose calculation and expanded view construction.
• Developed a novel algorithm for estimating the optimal inter-camera correspondence matrix from 3D map points.

Main Results:

• The proposed correspondence matrix estimation algorithm demonstrated reduced error and accurate transformation.
• The system successfully produced an expanded view even when other methods failed.
• The real-time dynamic field-of-view expansion achieved a processing speed of 21 frames per second.

Conclusions:

• The developed approach provides a robust real-time dynamic field-of-view expansion for minimally invasive surgery.
• This system outperforms previous methods and functions effectively regardless of image overlap.
• The technology enhances surgical visualization, potentially improving surgical procedures.