ML is an expanding field. It is popular as it allows efficient processing of vast amounts of data for interpreting and real-time decision making. Already widely used in imaging and diagnosis, it is believed that ML will also play an important role in surgery and interventional treatments. In particular, ML could become a game changer into the conception of cognitive surgical robots. Such robots endowed with cognitive skills would assist the surgical team also on a cognitive level, such as possibly lowering the mental load of the team. For example, ML could help extracting surgical skill, learned through demonstration by human experts, and could transfer this to robotic skills. Such intelligent surgical assistance would significantly surpass the state of the art in surgical robotics. Current devices possess no intelligence whatsoever and are merely advanced and expensive instruments.

Abstract-Real-time tool segmentation from endoscopic videos is an essential part of many computer-assisted robotic surgical systems and of critical importance in robotic surgical data science. We propose two novel deep learning architectures for automatic segmentation of non-rigid surgical instruments. Both methods take advantage of automated deep-learningbased multi-scale feature extraction while trying to maintain an accurate segmentation quality at all resolutions. The two proposed methods encode the multi-scale constraint inside the network architecture. The first proposed architecture enforces it by cascaded aggregation of predictions and the second proposed network does it by means of a holistically-nested architecture where the loss at each scale is taken into account for the optimization process. As the proposed methods are for realtime semantic labeling, both present a reduced number of parameters. We propose the use of parametric rectified linear units for semantic labeling in these small architectures to increase the regularization of the network while maintaining the segmentation accuracy. We compare the proposed architectures against state-of-the-art fully convolutional networks. We validate our methods using existing benchmark datasets, including ex vivo cases with phantom tissue and different robotic surgical instruments present in the scene. Our results show a statistically significant improved Dice Similarity Coefficient over previous instrument segmentation methods. We analyze our design choices and discuss the key drivers for improving accuracy.

No abstract

Abstract. Real-time tool segmentation is an essential component in computer-assisted surgical systems. We propose a novel real-time automatic method based on Fully Convolutional Networks (FCN) and optical flow tracking. Our method exploits the ability of deep neural networks to produce accurate segmentations of highly deformable parts along with the high speed of optical flow. Furthermore, the pre-trained FCN can be fine-tuned on a small amount of medical images without the need to hand-craft features. We validated our method using existing and new benchmark datasets, covering both ex vivo and in vivo real clinical cases where different surgical instruments are employed. Two versions of the method are presented, non-real-time and real-time. The former, using only deep learning, achieves a balanced accuracy of 89.6% on a real clinical dataset, outperforming the (non-real-time) state of the art by 3.8 percentage points. The latter, a combination of deep learning with optical flow tracking, yields an average balanced accuracy of 78.2% across all the validated datasets.

Bounded Environment Passivity, presented in this paper, allows one to design teleoperation systems that behave passive provided that the environment with which interaction takes place, belongs to an a-priori defined range of environments. The use of such a-priori knowledge on the environment reduces conservativeness with respect to classical design approaches. An additional advantage lies in its capability to get a clearer insight on which type of environments are problematic for the specific controller under investigation. On the basis of a case study, i.e. the well-known Position-Force controller, this paper describes and compares different passivity-based methods. First, the traditional methods of two-port passivity and absolute stability are applied. The restrictions of these methods to come up with useful design rules are explicitly demonstrated. Then, the Bounded Environment Passivity conditions of the Position-Force controller are derived. These conditions describe the relation between the specific controller implementation, the teleoperator dynamics and the environment characteristics. Additionally, the effects of structural resonance frequencies and low-pass filters, often present in realistic teleoperator setups, are described. This analysis reveals fundamental mechatronic rules of thumb for the design of a teleoperator system with a Position-Force control architecture. The theoretical results are verified experimentally on a 1-d.o.f.-teleoperation system.