Patient positioning by visualising surgical robot rotational workspace in augmented reality

Improved distinct bone segmentation in upper-body CT through multi-resolution networks

PURPOSE

Automated distinct bone segmentation from CT scans is widely used in planning and navigation workflows. U-Net variants are known to provide excellent results in supervised semantic segmentation. However, in distinct bone segmentation from upper-body CTs a large field of view and a computationally taxing 3D architecture are required. This leads to low-resolution results lacking detail or localisation errors due to missing spatial context when using high-resolution inputs.

METHODS

We propose to solve this problem by using end-to-end trainable segmentation networks that combine several 3D U-Nets working at different resolutions. Our approach, which extends and generalizes HookNet and MRN, captures spatial information at a lower resolution and skips the encoded information to the target network, which operates on smaller high-resolution inputs. We evaluated our proposed architecture against single-resolution networks and performed an ablation study on information concatenation and the number of context networks.

RESULTS

Our proposed best network achieves a median DSC of 0.86 taken over all 125 segmented bone classes and reduces the confusion among similar-looking bones in different locations. These results outperform our previously published 3D U-Net baseline results on the task and distinct bone segmentation results reported by other groups.

CONCLUSION

The presented multi-resolution 3D U-Nets address current shortcomings in bone segmentation from upper-body CT scans by allowing for capturing a larger field of view while avoiding the cubic growth of the input pixels and intermediate computations that quickly outgrow the computational capacities in 3D. The approach thus improves the accuracy and efficiency of distinct bone segmentation from upper-body CT.

Automatic patient positioning based on robot rotational workspace for extended reality

PURPOSE

Understanding the properties and aspects of the robotic system is essential to a successful medical intervention, as different capabilities and limits characterize each. Robot positioning is a crucial step in the surgical setup that ensures proper reachability to the desired port locations and facilitates docking procedures. This very demanding task requires much experience to master, especially with multiple trocars, increasing the barrier of entry for surgeons in training.

METHODS

Previously, we demonstrated an Augmented Reality-based system to visualize the rotational workspace of the robotic system and proved it helps the surgical staff to optimize patient positioning for single-port interventions. In this work, we implemented a new algorithm to allow for an automatic, real-time robotic arm positioning for multiple ports.

RESULTS

Our system, based on the rotational workspace data of the robotic arm and the set of trocar locations, can calculate the optimal position of the robotic arm in milliseconds for the positional and in seconds for the rotational workspace in virtual and augmented reality setups.

CONCLUSIONS

Following the previous work, we extended our system to support multiple ports to cover a broader range of surgical procedures and introduced the automatic positioning component. Our solution can decrease the surgical setup time and eliminate the need to repositioning the robot mid-procedure and is suitable both for the preoperative planning step using VR and in the operating room-running on an AR headset.

Improved distinct bone segmentation from upper-body CT using binary-prediction-enhanced multi-class inference

PURPOSE

Automated distinct bone segmentation has many applications in planning and navigation tasks. 3D U-Nets have previously been used to segment distinct bones in the upper body, but their performance is not yet optimal. Their most substantial source of error lies not in confusing one bone for another, but in confusing background with bone-tissue.

METHODS

In this work, we propose binary-prediction-enhanced multi-class (BEM) inference, which takes into account an additional binary background/bone-tissue prediction, to improve the multi-class distinct bone segmentation. We evaluate the method using different ways of obtaining the binary prediction, contrasting a two-stage approach to four networks with two segmentation heads. We perform our experiments on two datasets: An in-house dataset comprising 16 upper-body CT scans with voxelwise labelling into 126 distinct classes, and a public dataset containing 50 synthetic CT scans, with 41 different classes.

RESULTS

The most successful network with two segmentation heads achieves a class-median Dice coefficient of 0.85 on cross-validation with the upper-body CT dataset. These results outperform both our previously published 3D U-Net baseline with standard inference, and previously reported results from other groups. On the synthetic dataset, we also obtain improved results when using BEM-inference.

CONCLUSION

Using a binary bone-tissue/background prediction as guidance during inference improves distinct bone segmentation from upper-body CT scans and from the synthetic dataset. The results are robust to multiple ways of obtaining the bone-tissue segmentation and hold for the two-stage approach as well as for networks with two segmentation heads.