Related Experiment Video
Updated: Jan 12, 2026
Application of Laparoscopic Ultrasonography in Primary Choledochal Suture during Combined Two-lens Surgery
Published on: March 28, 2025
Automated surgical instrument recognition in laparoscopic cholecystectomy videos: a novel two-step deep learning
Jae Hyun Kwon1, Jaewoong Kang2,3, Soeui Kim2
1Department of Surgery, Hallym University Sacred Heart Hospital, Hallym University College of Medicine, Anyang-Si, Gyeonggi-Do, Republic of Korea. ponakwon@gmail.com.
Background:
To optimize surgical procedures and prevent retained surgical instruments, precise identification of required instruments during surgical treatment is essential. However, establishing ground truth data can be a labor-intensive barrier for researchers. Therefore, we developed and evaluated a novel system for detecting laparoscopic surgical instruments during laparoscopic cholecystectomy through virtual image creation.
Methods:
Virtual images were created by synthesizing laparoscopic instrument photos with surgical video backgrounds. The 311 instrument images and 1610 background images from 52 patients were augmented through random brightness, contrast, crop, rotation, scaling, flipping, and perspective transformations, resulting in 6023 composite images. These data were split into training, tuning, and internal test sets. Based on synthetic data, we developed a system comprising two-step processes. The first model is a unified instrument localization model that detects surgical instruments, and the second model is an instrument-type classification model that categorizes the detected surgical instruments. External and public datasets were used to evaluate generalizability.
Results:
The unified instrument localization model achieved average precision (AP) values with intersection over union (IoU) of 0.5 of 0.981, 0.882, and 0.689 for internal, external, and public datasets, respectively. The instrument-type classification model demonstrated area under the curve (AUC) values of 0.959 for seven instrument types in the external dataset and 0.749 for four instrument types in the public dataset. The final two-step instrument detection model demonstrated an AUC of 0.848 for the external dataset and 0.688 for the public dataset, which showed significantly superior performance compared to conventional multi-class instrument models.
Conclusions:
This validated deep learning model using synthetically generated data provides a reliable framework for surgical instrument detection. Our approach demonstrates strong performance and generalizability, suggesting its potential for improving operative workflow efficiency and surgical education across various minimally invasive procedures.
