The aim of this study is to automatically detect the boundary of vessel walls in optical coherence tomography (OCT) sequences. We developed a new method to eliminate guide-wire shadow artifacts and accurately estimate the vessel wall. The estimation of the position of the guide-wire is the key concept for the elimination of guide-wire shadow artifacts. After identification of the artifacts we propose a geometrically-based method which can be applied to OCT cross-section images to remove the artifacts. The segmentation approach is based on a novel combination of expectation maximization (EM) based segmentation and graph cut (GC) based segmentation. Validation is performed using simulated data and 4 typical in vivo OCT sequences. The comparison against manual expert segmentation demonstrates that the proposed vessel wall identification is robust and accurate.

Robotic partial nephrectomy is presently the fastest-growing robotic surgical procedure, and in comparison to traditional techniques it offers reduced tissue trauma and likelihood of post-operative infection, while hastening recovery time and improving cosmesis. It is also an ideal candidate for image guidance technology since soft tissue deformation, while still present, is localised and less problematic compared to other surgical procedures. This work describes the implementation and ongoing development of an effective image guidance system that aims to address some of the remaining challenges in this area. Specific innovations include the introduction of an intuitive, partially automated registration interface, and the use of a hardware platform that makes sophisticated augmented reality overlays practical in real time. Results and examples of image augmentation are presented from both retrospective and live cases. Quantitative analysis of registration error verifies that the proposed registration technique is appropriate for the chosen image guidance targets.

Motivation: For primary and metastatic liver cancer patients undergoing liver resection, a laparoscopic approach can reduce recovery times and morbidity while offering equivalent curative results; however, only about 10% of tumours reside in anatomical locations that are currently accessible for laparoscopic resection. Augmenting laparoscopic video with registered vascular anatomical models from pre-procedure imaging could support using laparoscopy in a wider population. Segmentation of liver tissue on laparoscopic video supports the robust registration of anatomical liver models by filtering out false anatomical correspondences between pre-procedure and intra-procedure images. In this paper, we present a convolutional neural network (CNN) approach to liver segmentation in laparoscopic liver procedure videos. Method: We defined a CNN architecture comprising fully-convolutional deep residual networks with multi-resolution loss functions. The CNN was trained in a leave-one-patient-out cross-validation on 2050 video frames from 6 liver resections and 7 laparoscopic staging procedures, and evaluated using the Dice score. Results: The CNN yielded segmentations with Dice scores ≥0.95 for the majority of images; however, the inter-patient variability in median Dice score was substantial. Four failure modes were identified from low scoring segmentations: minimal visible liver tissue, inter-patient variability in liver appearance, automatic exposure correction, and pathological liver tissue that mimics non-liver tissue appearance. Conclusion: CNNs offer a feasible approach for accurately segmenting liver from other anatomy on laparoscopic video, but additional data or computational advances are necessary to address challenges due to the high inter-patient variability in liver appearance.

Automatically recognising surgical gestures from surgical data is an important building block of automated activity recognition and analytics, technical skill assessment, intra-operative assistance and eventually robotic automation. The complexity of articulated instrument trajectories and the inherent variability due to surgical style and patient anatomy make analysis and fine-grained segmentation of surgical motion patterns from robot kinematics alone very difficult. Surgical video provides crucial information from the surgical site with context for the kinematic data and the interaction between the instruments and tissue. Yet sensor fusion between the robot data and surgical video stream is non-trivial because the data have different frequency, dimensions and discriminative capability. In this paper, we integrate multimodal attention mechanisms in a two-stream temporal convolutional network to compute relevance scores and weight kinematic and visual feature representations dynamically in time, aiming to aid multimodal network training and achieve effective sensor fusion. We report the results of our system on the JIG-SAWS benchmark dataset and on a new in vivo dataset of suturing segments from robotic prostatectomy procedures. Our results are promising and obtain multimodal prediction sequences with higher accuracy and better temporal structure than corresponding unimodal solutions. Visualization of attention scores also gives physically interpretable insights on network understanding of strengths and weaknesses of each sensor.