The Fusion-KVE model, incorporating kinematics, vision, and system events, achieved a frame-wise state estimation accuracy of 89.4% on the RIOUS dataset, improving upon single-input models.
Does the Fusion-KVE model improve frame-wise state estimation accuracy in robot-assisted surgical tasks compared to existing models?
The proposed Fusion-KVE deep learning model improves the accuracy of temporal segmentation of surgical sub-tasks in robot-assisted surgeries by integrating multiple data sources.
Absolute Event Rate: 89.4% vs 78.4%
Many tasks in robot-assisted surgeries (RAS) can be represented by finite-state machines (FSMs), where each state represents either an action (such as picking up a needle) or an observation (such as bleeding). A crucial step towards the automation of such surgical tasks is the temporal perception of the current surgical scene, which requires a real-time estimation of the states in the FSMs. The objective of this work is to estimate the current state of the surgical task based on the actions performed or events occurred as the task progresses. We propose Fusion-KVE, a unified surgical state estimation model that incorporates multiple data sources including the Kinematics, Vision, and system Events. Additionally, we examine the strengths and weaknesses of different state estimation models in segmenting states with different representative features or levels of granularity. We evaluate our model on the JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS), as well as a more complex dataset involving robotic intra-operative ultrasound (RIOUS) imaging, created using the da Vinci Xi surgical system. Our model achieves a superior frame-wise state estimation accuracy up to 89.4%, which improves the state-of-the-art surgical state estimation models in both JIGSAWS suturing dataset and our RIOUS dataset.
Qin et al. (Fri,) conducted a other in Robot-assisted surgery. Fusion-KVE model vs. Single-input state estimation models was evaluated on Frame-wise state estimation accuracy on RIOUS dataset. The Fusion-KVE model, incorporating kinematics, vision, and system events, achieved a frame-wise state estimation accuracy of 89.4% on the RIOUS dataset, improving upon single-input models.