Accurate real-time catheter segmentation is an important pre-requisite for robot-assisted endovascular intervention. Most of the existing learning-based methods for catheter segmentation and tracking are only trained on smallscale datasets or synthetic data due to the difficulties of ground-truth annotation. Furthermore, the temporal continuity in intraoperative imaging sequences is not fully utilised. In this paper, we present FW-Net, an end-to-end and real-time deep learning framework for endovascular intervention. The proposed FW-Net has three modules: a segmentation network with encoder-decoder architecture, a flow network to extract optical flow information, and a novel flow-guided warping function to learn the frame-to-frame temporal continuity. We show that by effectively learning temporal continuity, the network can successfully segment and track the catheters in real-time sequences using only raw ground-truth for training. Detailed validation results confirm that our FW-Net outperforms stateof-the-art techniques while achieving real-time performance.

Echocardiography is a potential alternative to X-ray fluoroscopy in cardiac catheterization given its richness in soft tissue information and its lack of ionizing radiation. However, its small field of view and acoustic artifacts make direct automatic segmentation of the catheters very challenging. In this study, a fast catheter segmentation framework for echocardiographic imaging guided by the segmentation of corresponding X-ray fluoroscopic imaging is proposed. The complete framework consists of: 1) catheter initialization in the first X-ray frame; 2) catheter tracking in the rest of the X-ray sequence; 3) fast registration of corresponding X-ray and ultrasound frames; and 4) catheter segmentation in ultrasound images guided by the results of both X-ray tracking and fast registration. The main contributions include: 1) a Kalman filter-based growing strategy with more clinical data evalution; 2) a SURF detector applied in a constrained search space for catheter segmentation in ultrasound images; 3) a two layer hierarchical graph model to integrate and smooth catheter fragments into a complete catheter; and 4) the integration of these components into a system for clinical applications. This framework is evaluated on five sequences of porcine data and four sequences of patient data comprising more than 3000 X-ray frames and more than 1000 ultrasound frames. The results show that our algorithm is able to track the catheter in ultrasound images at 1.3 s per frame, with an error of less than 2 mm. However, although this may satisfy the accuracy for visualization purposes and is also fast, the algorithm still needs to be further accelerated for real-time clinical applications.

For many image-guided interventions there exists a need to compute the registration between preprocedure image(s) and the physical space of the intervention. Real-time intraprocedure imaging such as ultrasound (US) can be used to image the region of interest directly and provide valuable anatomical information for computing this registration. Unfortunately, real-time US images often have poor signal-to-noise ratio and suffer from imaging artefacts. Therefore, registration using US images can be challenging and significant preprocessing is often required to make the registrations robust. In this paper we present a novel technique for computing the image-to-physical registration for minimally invasive cardiac interventions using 3-D US. Our technique uses knowledge of the physics of the US imaging process to reduce the amount of preprocessing required on the 3-D US images. To account for the fact that clinical US images normally undergo significant image processing before being exported from the US machine our optimization scheme allows the parameters of the US imaging model to vary. We validated our technique by computing rigid registrations for 12 cardiac US/magnetic resonance imaging (MRI) datasets acquired from six volunteers and two patients. The technique had mean registration errors of 2.1-4.4 mm, and 75% capture ranges of 5-30 mm. We also demonstrate how the same approach can be used for respiratory motion correction: on 15 datasets acquired from five volunteers the registration errors due to respiratory motion were reduced by 45%-92%.

In this paper we describe a novel 3D subdivision strategy to extract the surface of binary image data. This iterative approach generates a series of surface meshes that capture different levels of detail of the underlying structure. At the highest level of detail, the resulting surface mesh generated by our approach uses only about 10% of the triangles in comparison to the marching cube algorithm (MC) even in settings were almost no image noise is present. Our approach also eliminates the so-called "staircase effect" which voxel based algorithms like the MC are likely to show, particularly if non-uniformly sampled images are processed. Finally, we show how the presented algorithm can be parallelized by subdividing 3D image space into rectilinear blocks of subimages. As the algorithm scales very well with an increasing number of processors in a multi-threaded setting, this approach is suited to process large image data sets of several gigabytes. Although the presented work is still computationally more expensive than simple voxel-based algorithms, it produces fewer surface triangles while capturing the same level of detail, is more robust towards image noise and eliminates the above-mentioned "staircase" effect in anisotropic settings. These properties make it particularly useful for biomedical applications, where these conditions are often encountered.