OperA: Attention-Regularized Transformers for Surgical Phase Recognition
This work addresses the problem of automating surgical workflow analysis for medical professionals, representing an incremental improvement with a specific method enhancement.
The paper tackles surgical phase recognition from long laparoscopic videos by introducing OperA, a transformer-based model with a novel attention regularization loss that focuses on high-quality frames, achieving state-of-the-art performance on two cholecystectomy datasets.
In this paper we introduce OperA, a transformer-based model that accurately predicts surgical phases from long video sequences. A novel attention regularization loss encourages the model to focus on high-quality frames during training. Moreover, the attention weights are utilized to identify characteristic high attention frames for each surgical phase, which could further be used for surgery summarization. OperA is thoroughly evaluated on two datasets of laparoscopic cholecystectomy videos, outperforming various state-of-the-art temporal refinement approaches.