Liver cancer is one of the leading causes of cancer death. To assist doctors in hepatocellular carcinoma diagnosis and treatment planning, an accurate and automatic liver and tumor segmentation method is highly demanded in the clinical practice. Recently, fully convolutional neural networks (FCNs), including 2-D and 3-D FCNs, serve as the backbone in many volumetric image segmentation. However, 2-D convolutions cannot fully leverage the spatial information along the third dimension while 3-D convolutions suffer from high computational cost and GPU memory consumption. To address these issues, we propose a novel hybrid densely connected UNet (H-DenseUNet), which consists of a 2-D DenseUNet for efficiently extracting intra-slice features and a 3-D counterpart for hierarchically aggregating volumetric contexts under the spirit of the auto-context algorithm for liver and tumor segmentation. We formulate the learning process of the H-DenseUNet in an end-to-end manner, where the intra-slice representations and inter-slice features can be jointly optimized through a hybrid feature fusion layer. We extensively evaluated our method on the data set of the MICCAI 2017 Liver Tumor Segmentation Challenge and 3DIRCADb data set. Our method outperformed other state-of-the-arts on the segmentation results of tumors and achieved very competitive performance for liver segmentation even with a single model.

H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes

The objective of this study was to develop anatomically correct whole body human models of an adult male (34 years old), an adult female (26 years old) and two children (an 11-year-old girl and a six-year-old boy) for the optimized evaluation of electromagnetic exposure. These four models are referred to as the Virtual Family. They are based on high resolution magnetic resonance (MR) images of healthy volunteers. More than 80 different tissue types were distinguished during the segmentation. To improve the accuracy and the effectiveness of the segmentation, a novel semi-automated tool was used to analyze and segment the data. All tissues and organs were reconstructed as three-dimensional (3D) unstructured triangulated surface objects, yielding high precision images of individual features of the body. This greatly enhances the meshing flexibility and the accuracy with respect to thin tissue layers and small organs in comparison with the traditional voxel-based representation of anatomical models. Conformal computational techniques were also applied. The techniques and tools developed in this study can be used to more effectively develop future models and further improve the accuracy of the models for various applications. For research purposes, the four models are provided for free to the scientific community.

/pdf/the-virtual-family-development-of-surface-based-anatomical-47u5t3e6am.pdf

The Virtual Family—development of surface-based anatomical models of two adults and two children for dosimetric simulations

The use of laparoscopy for liver surgery is increasing rapidly. The Second International Consensus Conference on Laparoscopic Liver Resections (LLR) was held in Morioka, Japan, from October 4 to 6, 2014 to evaluate the current status of laparoscopic liver surgery and to provide recommendations to aid its future development. Seventeen questions were addressed. The first 7 questions focused on outcomes that reflect the benefits and risks of LLR. These questions were addressed using the Zurich-Danish consensus conference model in which the literature and expert opinion were weighed by a 9-member jury, who evaluated LLR outcomes using GRADE and a list of comparators. The jury also graded LLRs by the Balliol Classification of IDEAL. The jury concluded that MINOR LLRs had become standard practice (IDEAL 3) and that MAJOR liver resections were still innovative procedures in the exploration phase (IDEAL 2b). Continued cautious introduction of MAJOR LLRs was recommended. All of the evidence available for scrutiny was of LOW quality by GRADE, which prompted the recommendation for higher quality evaluative studies. The last 10 questions focused on technical questions and the recommendations were based on literature review and expert panel opinion. Recommendations were made regarding preoperative evaluation, bleeding controls, transection methods, anatomic approaches, and equipment. Both experts and jury recognized the need for a formal structure of education for those interested in performing major laparoscopic LLR because of the steep learning curve.

Recommendations for laparoscopic liver resection: a report from the second international consensus conference held in Morioka

Efficient segmentation of globally optimal surfaces representing object boundaries in volumetric data sets is important and challenging in many medical image analysis applications. We have developed an optimal surface detection method capable of simultaneously detecting multiple interacting surfaces, in which the optimality is controlled by the cost functions designed for individual surfaces and by several geometric constraints defining the surface smoothness and interrelations. The method solves the surface segmentation problem by transforming it into computing a minimum s{\hbox{-}} t cut in a derived arc-weighted directed graph. The proposed algorithm has a low-order polynomial time complexity and is computationally efficient. It has been extensively validated on more than 300 computer-synthetic volumetric images, 72 CT-scanned data sets of different-sized plexiglas tubes, and tens of medical images spanning various imaging modalities. In all cases, the approach yielded highly accurate results. Our approach can be readily extended to higher-dimensional image segmentation.

Optimal Surface Segmentation in Volumetric Images-A Graph-Theoretic Approach

Learning Deconvolution Network for Semantic Segmentation

The segmentation of hepatic vessel systems is important for many applications treating malignant liver disease such as selective internal radiation therapy. To enhance the different vessel systems, contrast agent is injected intravenously and CT scans are obtained at different time points and phases of contrast agent perfusion in liver vessels and parenchyma. We demonstrate that using the registered arterial phase as additional input for training an aU-Net for portal vein (PV) and hepatic vein (HV) segmentation increases the centerline Dice. However, using the registered venous phase for hepatic artery (HA) segmentation does not improve segmentation performance.

Combining arterial and venous CT scans in a multi-encoder network for improved hepatic vessel segmentation

Objective: During RF ablation of liver tumours it is a risk of incomplete tumor areas along the liver vessels. Up to now, there is no systematically analysis of the influence of vessel diameter and flow velocity on the intensity of heat dissipation during therapy available. The objective of this study was to quantify this cooling effect in an ex vivo model. Methods: In our experimental setup with fresh porcine liver we used a bipolar applicator with 30W output power and 15 kJ energy. For the simulation of different vessel diameters, glass tubes with different diameters (di=1.0–8.0 mm) were inserted. The distance between RF applicator and glass tubes was 5 mm. For the simulation of different flow velocities, for the glass tube with diameter di=3,4 mm we varied the flow velocity from 0–917.35 mms−1. After the ablation, the dimensions of the resulting lesion were digitally measured. Results: 144 lesions were induced in 48 porcine livers with 6 repetitions for each parameter setting. In the results for the different vessel diameters, there is no significant difference between the lesion sizes. But the flow velocities are clearly influencing the lesion size. Already with a flow of 1.84mms−1 we could measure a significant area reduction of 16.2% compared to zero flow, which stepped up to 33.6% area reduction for 917.35 mms−1 flow velocity. Conclusion: In a standardised ex vivo model could be shown, that the main influence is not the vessel diameter but rather the blood flow. Even for low flow rates, the heat reduction is enough to significantly reduce the lesion size. These results could be helpful for clinical therapy planning when the tumor is close to liver vessels with significant blood flow.

Uncontrolled cooling effects of intrahepatic vessels by RF ablation: An ex vivo study about the influence of vessel diameter and flow velocity on heat dissipation during therapy

Robust Liver Segmentation with Deep Learning Across DCE-MRI Contrast Phases

Explainability of decisions made by deep neural networks is of high value as it allows for validation and improvement of models. This work proposes an approach to explain semantic segmentation networks by means of layer-wise relevance propagation. As an exemplary application, we investigate which MRI sequences are most relevant for liver tumor segmentation.

Relevance analysis of MRI sequences for automatic liver tumor segmentation

Medical software for computer-assisted surgery often solely supports one phase of the surgical process, e.g., surgery planning. This paper describes a concept for a system, which can be seamlessly used in the preoperative planning phase, in the intraoperative phase for viewing the planning data, as well as for training and education. A combination of virtual and augmented reality with a multi-user functionality will support the three phases. 3D-printed organ models will be used as interaction devices for more intuitive interaction with the visual data and for educating future surgeons. We present the three application scenarios for this concept in detail and discuss the research opportunities.

Andrea Schenk

Papers

Combining arterial and venous CT scans in a multi-encoder network for improved hepatic vessel segmentation

Uncontrolled cooling effects of intrahepatic vessels by RF ablation: An ex vivo study about the influence of vessel diameter and flow velocity on heat dissipation during therapy

Robust Liver Segmentation with Deep Learning Across DCE-MRI Contrast Phases

Relevance analysis of MRI sequences for automatic liver tumor segmentation

Application Scenarios for 3D-Printed Organ Models for Collaboration in VR & AR