Department of Gastroenterological and Pediatric Surgery, Faculty of Medicine, Oita University, Oita, Japan.
Department of Information System and Engineering, Faculty of Information Engineering, Fukuoka Institute of Technology, Fukuoka, Japan.
Surg Endosc. 2023 Nov;37(11):8755-8763. doi: 10.1007/s00464-023-10328-y. Epub 2023 Aug 11.
The Critical View of Safety (CVS) was proposed in 1995 to prevent bile duct injury during laparoscopic cholecystectomy (LC). The achievement of CVS was evaluated subjectively. This study aimed to develop an artificial intelligence (AI) system to evaluate CVS scores in LC.
AI software was developed to evaluate the achievement of CVS using an algorithm for image classification based on a deep convolutional neural network. Short clips of hepatocystic triangle dissection were converted from 72 LC videos, and 23,793 images were labeled for training data. The learning models were examined using metrics commonly used in machine learning.
The mean values of precision, recall, F-measure, specificity, and overall accuracy for all the criteria of the best model were 0.971, 0.737, 0.832, 0.966, and 0.834, respectively. It took approximately 6 fps to obtain scores for a single image.
Using the AI system, we successfully evaluated the achievement of the CVS criteria using still images and videos of hepatocystic triangle dissection in LC. This encourages surgeons to be aware of CVS and is expected to improve surgical safety.
为防止腹腔镜胆囊切除术（LC）中胆管损伤，1995 年提出了安全关键视角（CVS）。CVS 的实现是主观评估的。本研究旨在开发一种人工智能（AI）系统，以评估 LC 中的 CVS 评分。
开发了一种 AI 软件，使用基于深度卷积神经网络的图像分类算法来评估 CVS 的实现情况。将 72 个 LC 视频中的肝胆囊三角解剖短片转换为短剪辑，并对 23793 张图像进行标记作为训练数据。使用机器学习中常用的指标来检查学习模型。
最佳模型的所有标准的平均值精度、召回率、F1 分数、特异性和总体准确性分别为 0.971、0.737、0.832、0.966 和 0.834。获取单个图像分数的速度约为 6 fps。
使用 AI 系统，我们成功地使用 LC 中肝胆囊三角解剖的静态图像和视频评估了 CVS 标准的实现情况。这鼓励外科医生意识到 CVS，并有望提高手术安全性。
