An entropy‐based approach to detect and localize intraoperative bleeding during minimally invasive surgery

Abstract

Background: During minimally invasive surgery (either robotic or traditional laparoscopic), vascular injuries may occur because of inadvertent surgical tool movements or actions. These vascular injuries can lead to arterial or venous bleeding with varying degrees of severity that may be life-threatening. Materials and Methods: Given that a bloody spot is characterized by homogenous and uniform texture, our algorithm automatically scans the entire surgical video frame-by-frame using a local entropy filter to segment each image into different regions sequence. By comparing changes in entropy in the frames sequences, the algorithm detects the moment of bleeding occurrence and its pixel location. We preliminarily tested the algorithm using ten minimally invasive-surgery videos., each of which contains one surgical-tool-induced bleeding. Results: Our results show that the algorithm can detect bleeding within 0.635 s, on average, after their occurrences and locate the bleeding sources within, on average, 2.5% of discrepancy in pixels from their origins. Conclusion: In this study, we present a novel and promising local-entropy-based image processing algorithm that detects spurts of blood and locate their source in real-time.

A Natural Language Interface for an Autonomous Camera Control System on the da Vinci Surgical Robot

“…In the future, Natural Language Processing can be extended beyond camera control. For instance, using our previous work on bleeding detection and prediction [30,31], an overwatch system can be created to verbally warn the surgeon about unsafe tool movements or even attenuate robot movements. In addition, using recording capability [32], the surgeon could easily ask to record videos or even movements for later use.…”

ChatGPT-Enabled daVinci Surgical Robot Prototype: Advancements and Limitations

“…This may be a steppingstone to a natural language robotic platform that partners with the surgeon for a more intuitive and efficient system that enhances patient outcomes. Future iterations of this GPT-robot merging of technology could allow collaboration with surgeons in more profound ways, including in surgical education [1], preplanning surgeries [2], executing specific steps of the surgery [3], and keeping the surgeon informed about any anomalies in the scene or the patient's data [4,5].…”