A Caltech Library Service

Learning Invariant Representation of Tasks for Robust Surgical State Estimation

Qin, Yidan and Allan, Max and Yue, Yisong and Burdick, Joel W. and Azizian, Mahdi (2021) Learning Invariant Representation of Tasks for Robust Surgical State Estimation. IEEE Robotics and Automation Letters, 6 (2). pp. 3208-3215. ISSN 2377-3766.

[img] PDF - Accepted Version
See Usage Policy.

[img] PDF (arXiv) - Accepted Version
Creative Commons Attribution.


Use this Persistent URL to link to this item:


Surgical state estimators in robot-assisted surgery (RAS)-especially those trained via learning techniques-rely heavily on datasets that capture surgeon actions in laboratory or real-world surgical tasks. Real-world RAS datasets are costly to acquire, are obtained from multiple surgeons who may use different surgical strategies, and are recorded under uncontrolled conditions in highly complex environments. The combination of high diversity and limited data calls for new learning methods that are robust and invariant to operating conditions and surgical techniques. We propose StiseNet , a Surgical Task Invariance State Estimation Network with an invariance induction framework that minimizes the effects of variations in surgical technique and operating environments inherent to RAS datasets. StiseNet's adversarial architecture learns to separate nuisance factors from information needed for surgical state estimation. StiseNet is shown to outperform state-of-the-art state estimation methods on three datasets (including a new real-world RAS dataset: HERNIA-20).

Item Type:Article
Related URLs:
URLURL TypeDescription Paper
Qin, Yidan0000-0002-7766-1021
Allan, Max0000-0002-6495-065X
Yue, Yisong0000-0001-9127-1989
Burdick, Joel W.0000-0002-3091-540X
Additional Information:© 2021 IEEE. Manuscript received October 15, 2020; accepted February 16, 2021. Date of publication March 2, 2021; date of current version March 22, 2021. This letter was recommended for publication by Associate Editor P. Valdastri and Editor Z. Li upon evaluation of the reviewers’ comments. This work was supported by Intuitive Surgical Inc. We would like to thank Dr. Seyedshams Feyzabadi, Dr. Azad Shademan, Dr. Sandra Park, Dr. Humphrey Chow, and Dr. Wenqing Sun for their support.
Funding AgencyGrant Number
Intuitive Surgical, Inc.UNSPECIFIED
Subject Keywords:AI-Based Methods, deep learning methods, laparoscopy, medical robots and systems, surgical robotics
Issue or Number:2
Record Number:CaltechAUTHORS:20210225-132708240
Persistent URL:
Official Citation:Y. Qin, M. Allan, Y. Yue, J. W. Burdick and M. Azizian, "Learning Invariant Representation of Tasks for Robust Surgical State Estimation," in IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 3208-3215, April 2021, doi: 10.1109/LRA.2021.3063014
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:108201
Deposited By: George Porter
Deposited On:26 Feb 2021 15:36
Last Modified:24 Mar 2021 19:11

Repository Staff Only: item control page