RASNet: Segmentation for Tracking Surgical Instruments in Surgical Videos Using Refined Attention Segmentation Network
This work addresses the problem of accurate instrument tracking for surgical robotics, but it is incremental as it builds on existing U-shape networks with added attention modules.
The paper tackles segmentation of surgical instruments in robot-assisted surgery videos by proposing RASNet, a refined attention segmentation network, achieving state-of-the-art performance with 94.65% mean Dice and 90.33% mean IOU on the MICCAI EndoVis Challenge 2017 dataset.
Segmentation for tracking surgical instruments plays an important role in robot-assisted surgery. Segmentation of surgical instruments contributes to capturing accurate spatial information for tracking. In this paper, a novel network, Refined Attention Segmentation Network, is proposed to simultaneously segment surgical instruments and identify their categories. The U-shape network which is popular in segmentation is used. Different from previous work, an attention module is adopted to help the network focus on key regions, which can improve the segmentation accuracy. To solve the class imbalance problem, the weighted sum of the cross entropy loss and the logarithm of the Jaccard index is used as loss function. Furthermore, transfer learning is adopted in our network. The encoder is pre-trained on ImageNet. The dataset from the MICCAI EndoVis Challenge 2017 is used to evaluate our network. Based on this dataset, our network achieves state-of-the-art performance 94.65% mean Dice and 90.33% mean IOU.