Learn More
Liver surgery planning system plays an important role in achieving the optimized surgery plan in Living Donor Liver Transplantation (LDLT). Segmentation of liver is a very challenging component in liver surgery planning systems. Patient-specific shape prior is of great significance in improving the robustness of liver segmentation. However, complex liver(More)
PURPOSE To improve the accuracy and the robustness of the segmentation in living donor liver transplantation (LDLT) surgery planning system, the authors present a new segmentation framework that addresses challenges induced by the complex shape variations of patients' livers with cancer. It is designed to achieve the accurate and robust segmentation of(More)
Shape prior plays an important role in accurate and robust liver segmentation. However, liver shapes have complex variations and accurate modeling of liver shapes is challenging. Using large-scale training data can improve the accuracy but it limits the computational efficiency. In order to obtain accurate liver shape priors without sacrificing the(More)
Segmentation of the placenta from fetal MRI is challenging due to sparse acquisition, inter-slice motion, and the widely varying position and shape of the placenta between pregnant women. We propose a minimally interactive framework that combines multiple volumes acquired in different views to obtain accurate segmentation of the placenta. In the first(More)
Deep convolutional neural networks are powerful tools for learning visual representations from images. However, designing efficient deep architectures to analyse volumetric medical images remains challenging. This work investigates efficient and flexible elements of modern convolutional networks such as dilated convolution and residual connection. With(More)
(a) number of vertices:500 (b) number of vertices:1000 (c) number of vertices:2000 Figure 1. Runtime of SSC with the increase of repository's capacity and number of vertices. FISTA, Homotopy and LP converge to the same accuracy. Please note that the running time of LP is in minute, as shown in the green axis on right.  With the increase of the repository's(More)
Accurate medical image segmentation is essential for diagnosis, surgical planning and many other applications. Convolutional Neural Networks (CNNs) have shown to be state-of-the-art automatic segmentation methods while the result still needs to be refined to become accurate and robust enough for clinical use. We propose a deep learning-based interactive(More)
This research proposes an augmented magnetic navigation system for Transcatheter Aortic Valve Implantation (TAVI) employing a magnetic tracking system (MTS) combined with a dynamic aortic model and intra-operative ultrasound (US) images. The dynamic 3D aortic model is constructed based on the preoperative 4D computed tomography (CT), which is animated(More)