LC-YOLOmatch: A Novel Scene Segmentation Approach Based on YOLO for Laparoscopic Cholecystectomy

Hong Long^1,2Yuancheng Shao²Mini Han Wang^3*Fengshi JING^2,4Yuqiao Chen²Shuai Xiao¹Jia Gu^2,5*

• ¹Department of Gastrointestinal Surgery, The First Affiliated Hospital, University of South China, Hengyang, China
• ²Faculty of Data Science, City University of Macau, Taipa, Macao, SAR China
• ³Zhuhai City People's Hospital, Zhuhai, China
• ⁴School of Medicine, The University of North Carolina at Chapel Hill, Chapel Hill, United States
• ⁵Suzhou Ultimage Health Technology Co.,Ltd.,, Suzhou, China

Laparoscopy is a visual biosensor that can obtain real-time images of the body cavity, assisting in minimally invasive surgery. Laparoscopic cholecystectomy is one of the most frequently performed endoscopic surgeries and the most fundamental modular surgery. However, many iatrogenic complications still occur each year, mainly due to the anatomical recognition errors of the surgeons. Therefore, the development of artificial intelligence-assisted recognition is of great significance. This paper proposes a method based on the lightweight YOLOv11n model. By introducing the efficient multi-scale feature extraction module DWR, the real-time performance of the model is enhanced. Additionally, the bidirectional feature pyramid network (BiFPN) is incorporated to strengthen the capability of multi-scale feature fusion. Finally, we developed the LC-YOLOmatch semi-supervised learning framework, which effectively addresses the issue of scarce labeled data in the medical field. The experimental results on the publicly available Cholec80 dataset show that this method achieves 70% mAP50 and 40.8% mAP50-95, reaching a new technical level and reducing the reliance on manual annotations. These improvements not only highlight its potential in automated surgeries but also significantly enhance the assistance in laparoscopic procedures while effectively reducing the incidence of complications.