Orimoto Hiroki, Hirashita Teijiro, Ikeda Subaru, Amano Shota, Kawamura Masahiro, Kawano Yoko, Takayama Hiroomi, Masuda Takashi, Endo Yuichi, Matsunobu Yusuke, Shinozuka Ken'ichi, Tokuyasu Tatsushi, Inomata Masafumi
Department of Gastroenterological and Pediatric Surgery, Faculty of Medicine, Oita University, 1-1 Hasama-Machi, Yufu, Oita, 879-5593, Japan.
Department of Information System and Engineering, Faculty of Information Engineering, Fukuoka Institute of Technology, Fukuoka, Japan.
Surg Endosc. 2025 Feb;39(2):1379-1387. doi: 10.1007/s00464-024-11514-2. Epub 2025 Jan 21.
The surgical difficulty of laparoscopic cholecystectomy (LC) for acute cholecystitis (AC) and the risk of bile duct injury (BDI) depend on the degree of fibrosis and scarring caused by inflammation; therefore, understanding these intraoperative findings is crucial to preventing BDI. Scarring makes it particularly difficult to perform safely and increases the BDI risk. This study aimed to develop an artificial intelligence (AI) system to indicate intraoperative findings of scarring in LC for AC.
An AI system was developed to detect scarred areas using an algorithm for semantic segmentation based on deep learning. The training dataset consisted of 2025 images extracted from LC videos of 21 cases with AC. External evaluation committees (EEC) evaluated the AI system on 20 cases of untrained data from other centers. EECs evaluated the accuracy in identifying the scarred area and the usefulness of the AI system, which were assessed based on annotation and a 5-point Likert-scale questionnaire.
The average DICE coefficient for scarred areas between AI detection and EEC annotation was 0.612. The EEC's average detection accuracy on the Likert scale was 3.98 ± 0.76. AI systems were rated as relatively useful for both clinical and educational applications.
We developed an AI system to detect scarred areas in LC for AC. Since scarring increases the surgical difficulty, this AI system has the potential to reduce BDI.
急性胆囊炎（AC）行腹腔镜胆囊切除术（LC）的手术难度及胆管损伤（BDI）风险取决于炎症所致的纤维化和瘢痕形成程度；因此，了解这些术中发现对于预防BDI至关重要。瘢痕形成使得安全操作尤为困难，并增加了BDI风险。本研究旨在开发一种人工智能（AI）系统，以指示AC行LC时的术中瘢痕形成情况。
开发了一种AI系统，使用基于深度学习的语义分割算法来检测瘢痕区域。训练数据集由从21例AC患者的LC视频中提取的2025张图像组成。外部评估委员会（EEC）对来自其他中心的20例未训练数据的AI系统进行评估。EEC评估识别瘢痕区域的准确性以及AI系统的实用性，这基于注释和5级李克特量表问卷进行评估。
AI检测与EEC注释之间瘢痕区域的平均DICE系数为0.612。EEC在李克特量表上的平均检测准确性为3.98±0.76。AI系统在临床和教育应用方面均被评为相对有用。
我们开发了一种AI系统来检测AC行LC时的瘢痕区域。由于瘢痕形成增加了手术难度，该AI系统有可能降低BDI。
