Surgical workflow recognition using two-stream mixed convolution network

Yuan Ding, Jingfan Fan*, Kun Pang, Heng Li, Tianyu Fu, Hong Song, Lingfeng Chen, Jian Yang

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

3 引用 (Scopus)

摘要

Surgical workflow recognition is the prerequisite for automatic indexing of surgical video databases and optimization of real-time operating scheduling, which is an important part of the modern operating room (OR). In this paper, we propose a surgical phase recognition method based on a two-stream mixed convolutional network (TsMCNet) to automatically recognize surgical workflow. TsMCNet optimizes the visual and temporal features learned from surgical videos by integrating 2D and 3D convolutional networks (CNNs) to form a spatio-temporal complementary architecture. Specifically, temporal branch (3D CNN) is responsible for learning the spatio-temporal features among adjacent frames, whereas the parallel visual branch (2D CNN) is focused on capturing the deep visual features of each frame. Extensive experiments on a public surgical video dataset (MICCAI 2016 Workflow Challenge) demonstrated outstanding performance of our proposed method, exceeding that of state-of-the-art methods (e.g., 86.2% accuracy and 83.0% F1 score).

源语言英语
主期刊名Proceedings - 2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2020
出版商Institute of Electrical and Electronics Engineers Inc.
264-269
页数6
ISBN(电子版)9781728181431
DOI
出版状态已出版 - 4月 2020
活动3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2020 - Shenzhen, 中国
期限: 24 4月 202026 4月 2020

出版系列

姓名Proceedings - 2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2020

会议

会议3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2020
国家/地区中国
Shenzhen
时期24/04/2026/04/20

指纹

探究 'Surgical workflow recognition using two-stream mixed convolution network' 的科研主题。它们共同构成独一无二的指纹。

引用此

Ding, Y., Fan, J., Pang, K., Li, H., Fu, T., Song, H., Chen, L., & Yang, J. (2020). Surgical workflow recognition using two-stream mixed convolution network. 在 Proceedings - 2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2020 (页码 264-269). 文章 9131322 (Proceedings - 2020 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AEMCSE50948.2020.00064