Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer in adults, and the most common cause of death of people suffering from cirrhosis. The segmentation of liver lesions in CT images allows assessment of tumor load, treatment planning, prognosis and monitoring of treatment response. Manual segmentation is a very time-consuming task and in many cases, prone to inaccuracies and automatic tools for tumor detection and segmentation are desirable. In this paper, we use a network architecture that consists of two consecutive fully convolutional neural networks. The first network segments the liver whereas the second network segments the actual tumor inside the liver. Our network is trained on a subset of the LiTS (Liver Tumor Segmentation) challenge and evaluated on data provided from the radiological center in Innsbruck.

In this paper, we propose a variational image segmentation framework for multichannel multiphase image segmentation based on the Chan-Vese active contour model. The core of our method lies in finding a variable u encoding the segmentation, by minimizing a multichannel energy functional that combines the information of multiple images. We create a decomposition of the input, either by multichannel filtering, or simply by using plain natural RGB, or medical images, which already consist of several channels. Subsequently we minimize the proposed functional for each of the channels simultaneously. Our model meets the necessary assumptions such that it can be solved efficiently by optimization techniques like the Chambolle-Pock method. We prove that the proposed energy functional has global minimizers, and show its stability and convergence with respect to noisy inputs. Experimental results show that the proposed method performs well in single-and multichannel segmentation tasks, and can be employed to the segmentation of various types of images, such as natural and texture images as well as medical images.

No abstract

Whole-body motor imagery is conceptualised as a mental symbolisation directly and indirectly associated with neural oscillations similar to whole-body motor execution. Motor and somatosensory activity, including vestibular activity, is a typical corticocortical substrate of body motion. Yet, it is not clear how this neural substrate is organised when participants are instructed to imagine moving their body forward or backward along the sagittal-anteroposterior axis. It is the aim of the current study to identify the fingerprint of the neural substrate by recording the cortical activity of 39 participants via a 32 electroencephalography (EEG) device. The participants were instructed to imagine moving their body forward or backward from a first-person perspective. Principal Component Analysis (i.e. PCA) applied to the neural activity of whole-body motor imagery revealed neural interconnections mirroring between forward and backward conditions: beta pre-motor and motor oscillations in the left and right hemisphere overshadowed beta parietal oscillations in forward condition, and beta parietal oscillations in the left and right hemisphere overshadowed beta pre-motor and motor oscillations in backward condition. Although functional significance needs to be discerned, beta pre-motor, motor and somatosensory oscillations might represent specific settings within the corticocortical network and provide meaningful information regarding the neural dynamics of continuous whole-body motion. It was concluded that the evoked multimodal fronto-parietal neural activity would correspond to the neural activity that could be expected if the participants were physically enacting movement of the whole-body in sagittal-anteroposterior plane as they would in their everyday environment.