Rethinking Anticipation Tasks: Uncertainty-aware Anticipation of Sparse Surgical Instrument Usage for Context-aware Assistance
This addresses the need for context-aware assistance in surgery, such as instrument preparation, but is incremental as it builds on existing anticipation tasks with a focus on sparsity and uncertainty.
The paper tackles the problem of anticipating surgical instrument usage in laparoscopic videos, which is challenging due to sparse occurrences, and proposes a probabilistic model that outperforms baselines and is competitive with methods using richer annotations.
Intra-operative anticipation of instrument usage is a necessary component for context-aware assistance in surgery, e.g. for instrument preparation or semi-automation of robotic tasks. However, the sparsity of instrument occurrences in long videos poses a challenge. Current approaches are limited as they assume knowledge on the timing of future actions or require dense temporal segmentations during training and inference. We propose a novel learning task for anticipation of instrument usage in laparoscopic videos that overcomes these limitations. During training, only sparse instrument annotations are required and inference is done solely on image data. We train a probabilistic model to address the uncertainty associated with future events. Our approach outperforms several baselines and is competitive to a variant using richer annotations. We demonstrate the model's ability to quantify task-relevant uncertainties. To the best of our knowledge, we are the first to propose a method for anticipating instruments in surgery.