Scholarlink

Background <p>Accurate intraoperative identification of scar tissue is essential for preventing bile duct injury during laparoscopic cholecystectomy (LC), especially under visually impaired conditions caused by bleeding. This study aimed to develop an artificial intelligence (AI)-based framework to enhance scar region prediction in such challenging surgical environments.</p> Methods <p>A hybrid approach was proposed, combining Cycle-Consistent Generative Adversarial Network-based image translation with uncertainty-aware fusion. Bleeding-contaminated laparoscopic images were translated into pseudo non-bleeding representations using unpaired domain adaptation. Segmentation results obtained from the original and translated images were then fused based on pixel-wise entropy to improve robustness.</p> Results <p>The system was evaluated using 99 representative images from 20 surgical patients. Compared with conventional segmentation methods, the proposed framework significantly improved Dice coefficients across all three board-certified endoscopic surgeons who served as expert annotators, with all improvements demonstrating significance (<i>P</i> &lt; 0.001). Subjective evaluations by the same surgeons confirmed high clinical utility, particularly in scar visibility and boundary delineation. The framework achieved near real-time inference speed (0.06&#xa0;s per frame on an RTX A5000 GPU).</p> Conclusion <p>This AI-assisted framework improved the accuracy and robustness of scar tissue detection during LC, even in bleeding-compromised fields. Its real-time capability and strong clinical validation indicate substantial potential for intraoperative application and enhancement of surgical safety.</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

Artificial intelligence-assisted scar visualization under intraoperative bleeding using CycleGAN and uncertainty fusion in laparoscopic cholecystectomy

  • 期刊论文

  • 发表日期：

    2025年9月15日

查看全文
  • Tatsushi Tokuyasu,
  • Subal Ikeda,
  • Hiroki Orimoto,
  • Teijiro Hirashita,
  • Yuichi Endo,
  • Masafumi Inomata

摘要

Background

Accurate intraoperative identification of scar tissue is essential for preventing bile duct injury during laparoscopic cholecystectomy (LC), especially under visually impaired conditions caused by bleeding. This study aimed to develop an artificial intelligence (AI)-based framework to enhance scar region prediction in such challenging surgical environments.

Methods

A hybrid approach was proposed, combining Cycle-Consistent Generative Adversarial Network-based image translation with uncertainty-aware fusion. Bleeding-contaminated laparoscopic images were translated into pseudo non-bleeding representations using unpaired domain adaptation. Segmentation results obtained from the original and translated images were then fused based on pixel-wise entropy to improve robustness.

Results

The system was evaluated using 99 representative images from 20 surgical patients. Compared with conventional segmentation methods, the proposed framework significantly improved Dice coefficients across all three board-certified endoscopic surgeons who served as expert annotators, with all improvements demonstrating significance (P < 0.001). Subjective evaluations by the same surgeons confirmed high clinical utility, particularly in scar visibility and boundary delineation. The framework achieved near real-time inference speed (0.06 s per frame on an RTX A5000 GPU).

Conclusion

This AI-assisted framework improved the accuracy and robustness of scar tissue detection during LC, even in bleeding-compromised fields. Its real-time capability and strong clinical validation indicate substantial potential for intraoperative application and enhancement of surgical safety.