Search papers, labs, and topics across Lattice.
This study introduces a novel approach to tool-tissue contact detection in robot-assisted surgery by utilizing depth images from stereo pairs instead of traditional RGB images. The researchers developed a fully supervised two-state hidden Markov model that leverages a minimum-distance patch around the tool boundary, achieving a macro F1 score of 0.927 and AUPRC of 0.980 across diverse surgical tasks and phantoms. The findings highlight that depth-based signals significantly outperform RGB-based classifiers, particularly in varied surgical contexts, underscoring the importance of depth information for reliable contact detection.
Depth imaging reveals a robust, transferable cue for tool-tissue contact detection, outperforming traditional RGB methods in diverse surgical scenarios.
Reliable tool--tissue contact detection can support interaction-aware control and downstream force estimation in robot-assisted surgery. Most existing methods learn a contact classifier from RGB appearance, which is hard to generalize. In this work, we use the depth image generated from a stereo pair to give more information about tool--tissue contact. For each depth frame, we localize a spatially supported minimum-distance patch around the tool boundary and reduce it to a single scalar, $-\log_{10}|d|$; this signal rises and falls in step with ground-truth contact. We formalize this observation with a fully supervised two-state hidden Markov model. We fit this model as a six-fold leave-one-session-out (LOSO) ensemble on six palpation sessions against a single silicone cup-like phantom, with the decision threshold selected from the pooled out-of-fold predictions. It is evaluated on four held-out sessions of three categories: 1. same task on same phantom; 2. same task on different phantom; 3. different task on different phantom. This model reaches held-out macro F1 $0.927$ and AUPRC $0.980$. We further compare against a reproduction of an RGB-based contact classifier from prior work. This RGB-based model achieves high performance on the first category (F1 $0.965$), but substantially lower performance on the other two, resulting in macro F1 $0.320$ across all four sessions. These results indicate that the tool--tissue distance is a strong, transferable cue for contact detection in robot-assisted surgery.
Amazon Science