经视频处理计算机软件分析直肠癌机器人辅助腹腔镜与传统腹腔镜手术中腹腔镜导航的质量。

Quality of laparoscopic camera navigation in robot-assisted versus conventional laparoscopic surgery for rectal cancer: An analysis of surgical videos through a video processing computer software.

机构信息

Division of Colon and Rectal Surgery, Department of Surgery, Korea University Anam Hospital, Korea University College of Medicine, Seoul, Korea.

Kim Jaechul School of Artificial Intelligence, KAIST, Daejeon, Korea.

出版信息

Int J Med Robot. 2022 Aug;18(4):e2393. doi: 10.1002/rcs.2393. Epub 2022 Mar 31.

DOI:10.1002/rcs.2393

PMID:35338680

Abstract

BACKGROUND

To compare laparoscopic camera navigation (LCN) quality between robot-assisted laparoscopic surgery (RALS) and conventional laparoscopic surgery (CLS).

METHODS

20 recordings were selected by propensity score matching and subjected to Python® software to generate single frames at one second intervals. For each frame, the pixel where the camera should be centred, based on instrument position, current action (dissection/haemostasis/traction) in the frame, was detected. LCN quality was reviewed by two independent surgeons to evaluate erroneous LCN.

RESULTS

RALS had higher incidence of centred views (83.1 ± 4.02% vs. 76.0 ± 2.38%, p < 0.05) and a shorter distance between actual and optimal frame centres (123.3 ± 9.8 vs. 144.8 ± 13.9, p < 0.05) compared to CLS. Erroneous camera navigations were more frequent in CLS regarding total time of horizontal alignment failure (2.1 ± 2.2 vs. 6.0 ± 5.4 min, p = 0.063) and number of excessive zoom-in visualization (0.1 ± 0.3 vs. 1.9 ± 1.4, p = 0.003).

CONCLUSIONS

RALS provided higher LCN quality than did CLS, emphasising the benefits of a surgeon-controlled view.

摘要

背景

比较机器人辅助腹腔镜手术（RALS）和传统腹腔镜手术（CLS）的腹腔镜摄像导航（LCN）质量。

方法

通过倾向评分匹配选择 20 个记录，并使用 Python®软件生成以一秒为间隔的单帧。对于每一帧，根据器械位置、当前帧中的操作（解剖/止血/牵引），检测应将相机中心置于哪个像素上。由两名独立的外科医生评估错误的 LCN 来审查 LCN 质量。

结果

RALS 中居中视图的发生率更高（83.1±4.02%比 76.0±2.38%，p<0.05），实际和最佳帧中心之间的距离更短（123.3±9.8 比 144.8±13.9，p<0.05），与 CLS 相比。在总水平对准故障时间（2.1±2.2 比 6.0±5.4 分钟，p=0.063）和过度缩放可视化的次数（0.1±0.3 比 1.9±1.4，p=0.003）方面，CLS 中错误的相机导航更为频繁。