Scholarlink

<b>Purpose</b> <p>Artificial intelligence is transforming surgical practices by improving procedural quality and decision-making. Machine learning-based video analysis can reliably identify surgical milestones, enhancing contextual understanding for surgeons. This study proposes a novel framework for detecting critical view of safety (CVS) in robot-assisted laparoscopic cholecystectomy (RLC) to improve procedural safety.</p> <b>Methods</b> <p>We present a meta-auxiliary learning framework that delicately combines milestone recognition and anatomical segmentation to enhance contextual awareness. The framework addresses label imbalance by facilitating knowledge sharing across tasks, ensuring balanced optimization. A curated RLC dataset was utilized to evaluate CVS identification and multi-instance segmentation performance.</p> <b>Results</b> <p>The proposed method achieved an F1 score of 78% for CVS detection and a mean IOU of 83.9% for anatomical segmentation, demonstrating its efficacy in complex surgical environments.</p> <b>Conclusion</b> <p>This framework establishes a new paradigm for surgical video analysis by integrating milestone detection and segmentation. Its ability to enhance decision support and procedural review in RLC highlights its potential for broader adoption in clinical practice.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Dual-task meta-auxiliary learning in laparoscopic cholecystectomy

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年6月26日

查看全文
  • Rui Guo,
  • Conor Perreault,
  • Benjamin Mueller,
  • Xi Liu,
  • Anthony Jarc

摘要

Purpose

Artificial intelligence is transforming surgical practices by improving procedural quality and decision-making. Machine learning-based video analysis can reliably identify surgical milestones, enhancing contextual understanding for surgeons. This study proposes a novel framework for detecting critical view of safety (CVS) in robot-assisted laparoscopic cholecystectomy (RLC) to improve procedural safety.

Methods

We present a meta-auxiliary learning framework that delicately combines milestone recognition and anatomical segmentation to enhance contextual awareness. The framework addresses label imbalance by facilitating knowledge sharing across tasks, ensuring balanced optimization. A curated RLC dataset was utilized to evaluate CVS identification and multi-instance segmentation performance.

Results

The proposed method achieved an F1 score of 78% for CVS detection and a mean IOU of 83.9% for anatomical segmentation, demonstrating its efficacy in complex surgical environments.

Conclusion

This framework establishes a new paradigm for surgical video analysis by integrating milestone detection and segmentation. Its ability to enhance decision support and procedural review in RLC highlights its potential for broader adoption in clinical practice.