Learning Invariant Representation of Tasks for Robust Surgical State Estimation
This addresses the challenge of limited and diverse real-world surgical datasets for improving state estimation in robot-assisted surgery, representing an incremental advancement in domain-specific robustness.
The paper tackled the problem of robust surgical state estimation in robot-assisted surgery by proposing StiseNet, a network that learns invariant representations to minimize variations in surgical techniques and operating environments, and it outperformed state-of-the-art methods on three datasets including a new real-world dataset.
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).