Accurate instance segmentation of surgical instruments in robotic surgery: model refinement and cross-dataset evaluation

Purpose Automatic segmentation of surgical instruments in robot-assisted minimally invasive surgery plays a fundamental role in improving context awareness. In this work, we present an instance segmentation model based on refined Mask R-CNN for accurately segmenting the instruments as well as identifying their types. Methods We re-formulate the instrument segmentation task as an instance segmentation task. Then we optimize the Mask R-CNN with anchor optimization and improved Region Proposal Network for instrument segmentation. Moreover, we perform cross-dataset evaluation with different sampling strategies. Results We evaluate our model on a public dataset of the MICCAI 2017 Endoscopic Vision Challenge with two segmentation tasks, and both achieve new state-of-the-art performance. Besides, cross-dataset training improved the performance on both segmentation tasks compared with those tested on the public dataset. Conclusion Results demonstrate the effectiveness of the proposed instance segmentation network for surgical instruments segmentation. Cross-dataset evaluation shows our instance segmentation model presents certain cross-dataset generalization capability, and cross-dataset training can significantly improve the segmentation performance. Our empirical study also provides guidance on how to allocate the annotation cost for surgeons while labelling a new dataset in practice.

Automated summary

This study introduces an instance segmentation model based on refined Mask R-CNN for accurately segmenting surgical instruments and identifying their types. Through cross-dataset training, the model's performance on different segmentation tasks was successfully improved. The results demonstrate the effectiveness of the proposed instance segmentation network for surgical instruments segmentation and provide guidance on allocating annotation costs for surgeons in practice.