Towards Robotic Knee Arthroscopy: Multi-Scale Network for Tissue-Tool Segmentation
This work addresses tissue awareness for improved surgical accuracy in minimally invasive arthroscopy, representing an incremental advance in domain-specific segmentation.
The paper tackles the problem of tissue-tool segmentation in robotic knee arthroscopy, where surgical videos have limited features and high intra-class variations, by proposing a densely connected shape-aware multi-scale segmentation model that achieved a 5.09% accuracy improvement on a polyp dataset.
Tissue awareness has a great demand to improve surgical accuracy in minimally invasive procedures. In arthroscopy, it is one of the challenging tasks due to surgical sites exhibit limited features and textures. Moreover, arthroscopic surgical video shows high intra-class variations. Arthroscopic videos are recorded with endoscope known as arthroscope which records tissue structures at proximity, therefore, frames contain minimal joint structure. As consequences, fully conventional network-based segmentation model suffers from long- and short- term dependency problems. In this study, we present a densely connected shape aware multi-scale segmentation model which captures multi-scale features and integrates shape features to achieve tissue-tool segmentations. The model has been evaluated with three distinct datasets. Moreover, with the publicly available polyp dataset our proposed model achieved 5.09 % accuracy improvement.