PEg TRAnsfer Workflow recognition challenge report: Do multimodal data improve recognition?

Arnaud Huaulmé¹, Kanako Harada², Quang-Minh Nguyen³, Bogyu Park⁴, Seungbum Hong⁴, Min-Kook Choi⁴, Michael Peven⁵, Yunshuang Li⁶, Yonghao Long⁷, Qi Dou⁷, Satyadwyoom Kumar⁸, Seenivasan Lalithkumar⁹, Ren Hongliang¹⁰, Hiroki Matsuzaki¹¹, Yuto Ishikawa¹¹, Yuriko Harai¹¹, Satoshi Kondo¹², Manoru Mitsuishi², Pierre Jannin¹³

¹Univ Rennes, INSERM, LTSI - UMR 1099, Rennes, F35000, France. Electronic address: arnaud.huaulme@univ-rennes.fr.

²Department of Mechanical Engineering, the University of Tokyo, Tokyo 113-8656, Japan.

³Univ Rennes, INSERM, LTSI - UMR 1099, Rennes, F35000, France.

⁴VisionAI hutom, Seoul, Republic of Korea.

⁵Johns Hopkins University, Baltimore, USA.

⁶Zhejiang University, Hangzhou, China.

⁷Department of Computer Science & Engineering, The Chinese University of Hong Kong, Hong Kong.

⁸Netaji Subhas University of Technology, Delhi, India.

⁹National University of Singapore, Singapore, Singapore.

¹⁰National University of Singapore, Singapore, Singapore; The Chinese University of Hong Kong, Hong Kong, Hong Kong.

¹¹National Cancer Center Japan East Hospital, Tokyo 104-0045, Japan.

¹²Muroran Institute of Technology, Hokkaido, Japan.

¹³Univ Rennes, INSERM, LTSI - UMR 1099, Rennes, F35000, France. Electronic address: pierre.jannin@univ-rennes.fr.

PubMed DOI

Abstract

BACKGROUND AND OBJECTIVE: In order to be context-aware, computer-assisted surgical systems require accurate, real-time automatic surgical workflow recognition. In the past several years, surgical video has been the most commonly-used modality for surgical workflow recognition. But with the democratization of robot-assisted surgery, new modalities, such as kinematics, are now accessible. Some previ…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.