Temporal Segmentation of Surgical Sub-tasks through Deep Learning with Multiple Data Sources
This work addresses the need for temporal perception in surgical automation, which is crucial for enhancing robot-assisted surgeries, though it appears incremental as it builds on existing state estimation models with multi-source data fusion.
The paper tackles the problem of real-time surgical state estimation in robot-assisted surgeries by proposing Fusion-KVE, a model that integrates kinematics, vision, and system events data. It achieves up to 89.4% frame-wise accuracy, improving state-of-the-art results on the JIGSAWS suturing dataset and a new RIOUS dataset.
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.