Search

The gray contrast between the liver and other soft tissues is low, and the boundary is not obvious. As a result, it is still a challenging task to accurately segment the liver from CT images. In recent years, methods of machine learning have become a research hotspot in the field of medical image segmentation because they can effectively use the "gold standard" personalized features of the liver from different data. However, machine learning usually requires a large number of data samples to train the model and improve the accuracy of medical image segmentation. This paper proposed a method for liver segmentation based on the Gabor dictionary of sparse image blocks with prior boundaries. This method reduced the number of samples by selecting the test sample set within the initial boundary area of the liver. The Gabor feature was extracted and the query dictionary was created, and the sparse coefficient was calculated to obtain the boundary information of the liver. By optimizing the reconstruction error and filling holes, a smooth liver boundary was obtained. The proposed method was tested on the MICCAI 2007 dataset and ISBI2017 dataset, and five measures were used to evaluate the results. The proposed method was compared with methods for liver segmentation proposed in recent years. The experimental results show that this method can improve the accuracy of liver segmentation and effectively repair the discontinuity and local overlap of segmentation results. [ABSTRACT FROM AUTHOR]

• A liver tumor segmentation network based on contextual information and parallel attention. • A novel hybrid dilated convolution and double dilated convolution for enlarging the receptive field of the network. • Contextual multi-scale attention block and dilated convolution block greatly contribute to segmentation performance. • The effectiveness of the proposed network is validated on two public datasets and one clinical dataset. Liver cancer is one of the leading causes of cancer death. Accurate and automatic liver tumor segmentation methods are urgent needs in clinical practice. Currently, Fully Convolutional Network and U-Net framework have achieved good results in medical image segmentation tasks, but there is still room for improvement. The traditional U-Net extracted a large number of low-level features, and the detailed features cannot be transmitted to deeper layers, resulting in poor segmentation ability. Therefore, this paper proposed a novel liver tumor segmentation network with contextual parallel attention and dilated convolution, called CPAD-Net. The proposed network applies a subsampled module, which has the same dimensionality reduction function as max-pooling without losing detailed features. CPAD-Net employs a contextual parallel attention module at skip connection. The module fuses contextual multi-scale features and extracts channel-spatial features in parallel. These features are concatenated with deep features to narrow the semantic gap and increase detailed information. Hybrid dilated convolution and double-dilated convolution are used in the encoding and decoding stages to expand the network receptive field. Dropout is added after each hybrid dilated convolution block to prevent overfitting. The efficacy of the proposed network is proved by widespread experimentation on two public datasets (LiTS2017 and 3Dircadb-01) and a clinical dataset from the Affiliated Hospital of Hebei University. The proposed network achieved Dice scores of 74.2%, 73.7% and 73.26%. The experimental results show that the proposed network outperforms most segmentation networks. [ABSTRACT FROM AUTHOR]

This study proposes a novel adaptive mesh expansion model (AMEM) for liver segmentation from computed tomography images. The virtual deformable simplex model (DSM) is introduced to represent the mesh, in which the motion of each vertex can be easily manipulated. The balloon, edge, and gradient forces are combined with the binary image to construct the external force of the deformable model, which can rapidly drive the DSM to approach the target liver boundaries. Moreover, tangential and normal forces are combined with the gradient image to control the internal force, such that the DSM degree of smoothness can be precisely controlled. The triangular facet of the DSM is adaptively decomposed into smaller triangular components, which can significantly improve the segmentation accuracy of the irregularly sharp corners of the liver. The proposed method is evaluated on the basis of different criteria applied to 10 clinical data sets. Experiments demonstrate that the proposed AMEM algorithm is effective and robust and thus outperforms six other up-to-date algorithms. Moreover, AMEM can achieve a mean overlap error of 6.8% and a mean volume difference of 2.7%, whereas the average symmetric surface distance and the root mean square symmetric surface distance can reach 1.3 mm and 2.7 mm, respectively. [ABSTRACT FROM AUTHOR]

Angiographic image is the perspective projection of the whole body from a 3D space to a 2D imaging plane, in which X-ray is used. As such, topological vasculature information has been lost. In 2D angiograms, foreshortening and overlapping are commonly observed in tubular-like structures. Hence, an optimum viewing angle should be determined to observe an interesting vessel segment (IVS) or an interesting vessel bifurcation (IVB) with minimized foreshortening and overlapping from a limited number of angiographic images. In this study, a novel integrated optimization method is proposed to calculate the optimum viewing angle. In the proposed method, the irregular shape and inter-branch distance of vasculatures are considered. Furthermore, three optimized conditions, including projection foreshortening rate, projection stenosis rate, and projection overlapping rate, are designed and integrated to determine the optimum viewing angle in a single vessel segment. The three conditions, including projection foreshortening, projection stenosis, and projection adjacent spacing rates, are also designed to optimize the viewing angle of bifurcations. To evaluate the performance of the proposed method, we simulated an angiographic image based on X-ray propagating principle by integrating 3D coronary artery tree models and the respective CT volume data. Experimental results demonstrate that the proposed method is very effective and robust; hence, this method can be used to determine the optimum viewing angle of IVS or IVB with irregular stenosis. The proposed method can also help physicians observe the branching structure or stenosis clearly in clinical practice. [ABSTRACT FROM AUTHOR]