Temporal matching in endoscopic images for remote-controlled robotic surgery

Area of Science:

• Medical Robotics
• Computer Vision
• Surgical Technology

Background:

• Accurate tumor boundary tracking is crucial in robotic surgery.
• Segmentation errors can hinder precise tumor localization and tracking.

Purpose of the Study:

• To develop a temporal matching technique for tracking tumor boundaries over time.
• To improve tumor segmentation and localization in image sequences.
• To enhance the formation of high-level entities in remote-controlled robotic surgery.

Main Methods:

• Utilizing attributed string matching to establish correspondences between tumor boundaries in sequential images.
• Exploiting identified relationships to reconstruct tumor boundaries.
• Implementing methods to mitigate inconsistencies arising from detection errors.

Main Results:

• Successfully tracked tumor boundaries across image sequences.
• Improved accuracy in tumor segmentation and localization.
• Reduced inconsistencies caused by detection errors.

Conclusions:

• Temporal matching is an effective approach for enhancing tumor tracking in robotic surgery.
• The proposed method improves the reliability of tumor boundary detection and localization.
• This technique contributes to more precise and effective remote-controlled surgical procedures.