Automated laparoscopic colorectal surgery workflow recognition using artificial intelligence: Experimental research. (July 2020)

• Record Type: Journal Article
• Authors: Kitaguchi, Daichi; Takeshita, Nobuyoshi; Matsuzaki, Hiroki; Oda, Tatsuya; Watanabe, Masahiko; Mori, Kensaku; Kobayashi, Etsuko; Ito, Masaaki
• Is Part Of: International journal of surgery. Volume 79(2020)
• Page Start: 88
• Page End: 94
• Publication Date: 2020-07
• Subjects: Laparoscopic colorectal surgery -- Convolutional neural network -- Artificial intelligence -- Surgical workflow recognition -- Automatic video indexing -- Surgical skill assessment; Surgery -- Periodicals; Surgical Procedures, Operative -- Periodicals; 617.005
• DOI: 10.1016/j.ijsu.2020.05.015
• Languages: English
• ISSNs: 1743-9191

Abstract

Abstract: Background: Identifying laparoscopic surgical videos using artificial intelligence (AI) facilitates the automation of several currently time-consuming manual processes, including video analysis, indexing, and video-based skill assessment. This study aimed to construct a large annotated dataset comprising laparoscopic colorectal surgery (LCRS) videos from multiple institutions and evaluate the accuracy of automatic recognition for surgical phase, action, and tool by combining this dataset with AI. Materials and methods: A total of 300 intraoperative videos were collected from 19 high-volume centers. A series of surgical workflows were classified into 9 phases and 3 actions, and the area of 5 tools were assigned by painting. More than 82 million frames were annotated for a phase and action classification task, and 4000 frames were annotated for a tool segmentation task. Of these frames, 80% were used for the training dataset and 20% for the test dataset. A convolutional neural network (CNN) was used to analyze the videos. Intersection over union (IoU) was used as the evaluation metric for tool recognition. Results: The overall accuracies for the automatic surgical phase and action classification task were 81.0% and 83.2%, respectively. The mean IoU for the automatic tool segmentation task for 5 tools was 51.2%. Conclusions: A large annotated dataset of LCRS videos was constructed, and the phase, action, and tool were recognized with high accuracy using AI. Our dataset has potential uses in medical applications such as automatic video indexing and surgical skill assessments. Open research will assist in improving CNN models by making our dataset available in the field of computer vision. Graphical abstract: Image 1 Highlights: A large annotated dataset of laparoscopic colorectal surgery was constructed. Surgical phase, action, and tool were recognized with high accuracy using AI. The dataset has numerous potential to utilize for medical applications.