Improved Watershed Algorithm for CT Liver Segmentation Using Intraclass Variance Minimization

Accurate liver segmentation is essential for radiation therapy planning of hepatocellular carcinoma and absorbed dose calculation. However, liver segmentation is a challenging task due to the anatomical variability in both shape and size and the low contrast between liver and its surrounding organs. Thus we propose a convolutional neural network (CNN) for automated liver segmentation. In our method, fractional differential enhancement is firstly applied for preprocessing. Subsequently, an initial liver segmentation is obtained by using a CNN. Finally, accurate liver segmentation is achieved by the evolution of an active contour model. Experimental results show that the proposed method outperforms existing methods. One hundred fifty CT scans are evaluated for the experiment. For liver segmentation, Dice of 95.8%, true positive rate of 95.1%, positive predictive value of 93.2%, and volume difference of 7% are calculated. In addition, the values of these evaluation measures show that the proposed method is able to provide a precise and robust segmentation estimate, which can also assist the manual liver segmentation task.

Liver segmentation in CT images based on region-growing and unified level set method

Accurate segmentation of liver and tumor regions in medical imaging is crucial for the diagnosis, treatment, and monitoring of hepatocellular carcinoma (HCC) patients. However, manual segmentation is time-consuming and subject to inter- and intra-rater variability. Therefore, automated methods are necessary but require rigorous validation of high-quality segmentations based on a consensus of raters. To address the need for reliable and comprehensive data in this domain, we present LiverHccSeg, a dataset that provides liver and tumor segmentations on multiphasic contrast-enhanced magnetic resonance imaging from two board-approved abdominal radiologists, along with an analysis of inter-rater agreement.LiverHccSeg provides a curated resource for liver and HCC tumor segmentation tasks. The dataset includes a scientific reading and co-registered contrast-enhanced multiphasic magnetic resonance imaging (MRI) scans with corresponding manual segmentations by two board-approved abdominal radiologists and relevant metadata and offers researchers a comprehensive foundation for external validation, and benchmarking of liver and tumor segmentation algorithms. The dataset also provides an analysis of the agreement between the two sets of liver and tumor segmentations. Through the calculation of appropriate segmentation metrics, we provide insights into the consistency and variability in liver and tumor segmentations among the radiologists. A total of 17 cases were included for liver segmentation and 14 cases for HCC tumor segmentation. Liver segmentations demonstrates high segmentation agreement (mean Dice, 0.95 ± 0.01 [standard deviation]) and HCC tumor segmentations showed higher variation (mean Dice, 0.85 ± 0.16 [standard deviation]).The applications of LiverHccSeg can be manifold, ranging from testing machine learning algorithms on public external data to radiomic feature analyses. Leveraging the inter-rater agreement analysis within the dataset, researchers can investigate the impact of variability on segmentation performance and explore methods to enhance the accuracy and robustness of liver and tumor segmentation algorithms in HCC patients. By making this dataset publicly available, LiverHccSeg aims to foster collaborations, facilitate innovative solutions, and ultimately improve patient outcomes in the diagnosis and treatment of HCC.

Segmentation of livers and liver tumors is one of the most important steps in radiation therapy of hepatocellular carcinoma. The segmentation task is often done manually, making it tedious, labor intensive, and subject to intra-/inter- operator variations. While various algorithms for delineating organ-at-risks (OARs) and tumor targets have been proposed, automatic segmentation of livers and liver tumors remains intractable due to their low tissue contrast with respect to the surrounding organs and their deformable shape in CT images. The U-Net has gained increasing popularity recently for image analysis tasks and has shown promising results. Conventional U-Net architectures, however, suffer from three major drawbacks. First, skip connections allow for the duplicated transfer of low resolution information in feature maps to improve efficiency in learning, but this often leads to blurring of extracted image features. Secondly, high level features extracted by the network often do not contain enough high resolution edge information of the input, leading to greater uncertainty where high resolution edge dominantly affects the network's decisions such as liver and liver-tumor segmentation. Thirdly, it is generally difficult to optimize the number of pooling operations in order to extract high level global features, since the number of pooling operations used depends on the object size. To cope with these problems, we added a residual path with deconvolution and activation operations to the skip connection of the U-Net to avoid duplication of low resolution information of features. In the case of small object inputs, features in the skip connection are not incorporated with features in the residual path. Furthermore, the proposed architecture has additional convolution layers in the skip connection in order to extract high level global features of small object inputs as well as high level features of high resolution edge information of large object inputs. Efficacy of the modified U-Net (mU-Net) was demonstrated using the public dataset of Liver tumor segmentation (LiTS) challenge 2017. For liver-tumor segmentation, Dice similarity coefficient (DSC) of 89.72 %, volume of error (VOE) of 21.93 %, and relative volume difference (RVD) of - 0.49 % were obtained. For liver segmentation, DSC of 98.51 %, VOE of 3.07 %, and RVD of 0.26 % were calculated. For the public 3D Image Reconstruction for Comparison of Algorithm Database (3Dircadb), DSCs were 96.01 % for the liver and 68.14 % for liver-tumor segmentations, respectively. The proposed mU-Net outperformed existing state-of-art networks.

Liver and tumor segmentation from CT images is a complex and crucial step in achieving full-course adaptive radiotherapy and also plays an essential role in computer-aided clinical diagnosis systems. Deep learning-based methods play an important role in achieving automatic segmentation. This research aims to improve liver tumor detection performance by proposing a dual path feature extracting strategy and employing Swin-Transformer. The hierarchical Swin-Transformer is embedded into the encoder and decoder and combined with CNN to form a dual coding path structure incorporating long-range dependencies and multi-scale contextual connections to capture coarse-tuned features at different semantic scales. The features of the two encoding paths and the upsampling path are fused, tested and validated with LITS and in-house datasets. The proposed method has a DG of 97.95% and a DC of 96.2% for liver segmentation; a DG of 80.6% and a DC of 68.1% for tumor segmentation; and a classification study of the tumor dataset shows a DG of 91.1% and a DC of 87.2% for large and continuous tumors and a DG of 71.7% and a DC of 66.4% for small and scattered tumors. Swin-Transformer can be used as a robust encoder for medical image segmentation networks and, combined with CNN networks, can better recover local spatial information and enhance feature representation. Accurate localization before segmentation can achieve better results for small and scattered tumors.

The analysis of CT images of the abdomen has become increasingly important as lesions occurring in the liver are not easily detectable. The development of medical imaging technology has led to an explosive growth in the number of pathological sections of CT images. In the field of medical imaging, the use of computer-aided techniques for liver segmentation of abdominal CT images is particularly important. To further improve the accuracy of liver segmentation in abdominal CT images, this paper proposes the U2-OANet liver segmentation network on the basis of U2Net. This paper combines the new octave convolution module to design the OCRSU module, which produces better results for segmentation of liver boundaries while reducing the video memory usage. At the same time, this paper adds a dual attention module including the bottom attention module and the mixed attention module, to ensure the liver edge details while alleviating the noise problem and the false-positive problem, and further optimizes the liver segmentation network. Compared with the U2Net network, the U2-OANet network proposed in this paper has effectively improved the liver segmentation accuracy on CHAOS and 3DIRCADB datasets.

Blood vessel (BV) information can be used to guide body organ segmentation on computed tomography (CT) imaging. The proposed method uses abdominal BVs (ABVs) to segment the liver through the portal phase of an abdominal CT dataset. This method aims to address the wide variability in liver shape and size, separate liver from other organs of similar intensity, and segment hepatic low-intensity tumors (LITs). Thin ABVs are enhanced using three-dimensional (3D) opening. ABVs are extracted and classified into hepatic BVs (HBVs) and nonhepatic BVs (non-HBVs) with a small number of interactions, and HBVs and non-HBVs are used for constraining automatic liver segmentation. HBVs are used to individually segment the core region of the liver. To separate the liver from other organs, this core region and non-HBVs are used to construct an initial 3D boundary surface. To segment LITs, the core region is classified into non-LIT- and LIT-parts by fitting the histogram of the core region using a variational Bayesian Gaussian mixture model. Each part of the core region is extended based on its corresponding component of the mixture, and extension is completed when it reaches a variation in intensity or the constructed boundary surface, which is reconfirmed to fit robustly between the liver and neighboring organs of similar intensity. A solid-angle technique is used to refine main BVs at the entrances to the inferior vena cava and the portal vein. The proposed method was applied to 80 datasets: 30 Medical Image Computing and Computer Assisted Intervention (MICCAI) and 50 non-MICCAI; 30 datasets of non-MICCAI data include tumors. Our results for MICCAI-test data were evaluated by sliver07 (http://www.sliver07.org/) organizers with an overall score of 85.7, which ranks best on the site as of July 2013. These results (average ± standard deviation) include the five error measures of the 2007 MICCAI workshop for liver segmentation as follows. Results for volume overlap error, relative volume difference, average symmetric surface distance, root mean square symmetric surface distance, and maximum symmetric surface distance were 4.33 ± 0.73, 0.28 ± 0.87, 0.63 ± 0.16, 1.19 ± 0.28, and 14.01 ± 2.88, respectively; and when applying our method to non-MICCAI data, results were 3.21 ± 0.75, 0.06 ± 1.29, 0.45 ± 0.17, 0.98 ± 0.26, and 12.69 ± 3.89, respectively. These results demonstrate high performance of the method when applied to different CT datasets. BVs can be used to address the wide variability in liver shape and size, as BVs provide unique details for the structure of each studied liver. Constructing a boundary surface using HBVs and non-HBVs can separate liver from its neighboring organs of similar intensity. By fitting the histogram of the core region using a variational Bayesian Gaussian mixture model, LITs are segmented and measuring the volumetry of non-LIT- and LIT-parts becomes possible. Further examination of the proposed method on a large number of datasets is required for clinical applications, and development of the method for full automation may be possible and useful in the clinic.

Liver segmentation is important for the computer-assisted diagnosis of liver disease and liver volume measurement. Because of the complexity of liver computed tomography (CT) images, multiple image segmentation techniques are required to robustly segment the liver. Many liver segmentation approaches have been proposed in the past few decades, however the liver segmentation problem remains. More robust approaches are needed and new possibilities should be investigated. In this paper, we propose a novel 3D liver segmentation approach that contains four major parts: (1) image pre-processing, (2) edge-constrained liver segmentation by 3D region growing, (3) separation of 3D liver and other organs, and (4) post-processing. In the first step, an anisotropic diffusion filter removes noise effectively while keeping the image edges almost unchanged. In the second step, both 3D and 2D canny edges are combined to constrain the region growing process. The seeds of region growing are generated by slope difference distribution threshold selection of the 3D CT image and morphological erosion. In the third step, 3D random walk and slope difference distribution threshold selection are combined to separate the adhered organs. In the fourth step, a novel 2D vascular region correction method is proposed for post-processing. Two open accessible CT liver datasets are used to evaluate the proposed approach and the achieved average DICE measure accuracy is 96.83%.

Automatic 3D liver segmentation is a fundamental step in the liver disease diagnosis and surgery planning. This paper presents a novel fully automatic algorithm for 3D liver segmentation in clinical 3D computed tomography (CT) images. Based on image features, we propose a new Mahalanobis distance cost function using an active shape model (ASM). We call our method MD-ASM. Unlike the standard active shape model (ST-ASM), the proposed method introduces a new feature-constrained Mahalanobis distance cost function to measure the distance between the generated shape during the iterative step and the mean shape model. The proposed Mahalanobis distance function is learned from a public database of liver segmentation challenge (MICCAI-SLiver07). As a refinement step, we propose the use of a 3D graph-cut segmentation. Foreground and background labels are automatically selected using texture features of the learned Mahalanobis distance. Quantitatively, the proposed method is evaluated using two clinical 3D CT scan databases (MICCAI-SLiver07 and MIDAS). The evaluation of the MICCAI-SLiver07 database is obtained by the challenge organizers using five different metric scores. The experimental results demonstrate the availability of the proposed method by achieving an accurate liver segmentation compared to the state-of-the-art methods.

HDTN: hybrid duo-transformer network for liver and hepatic tumor segmentation in CT images

In this paper, we propose an approach to detection and segmentation of liver tumors in noisy computed topography (CT) images. Image segmentation plays crucial role in medical image processing applications. Noise is quite common in medical images. It occurs while acquisition and transmission of images. The essential goal of this framework is to identify liver cancer by segmenting liver tumors from noisy CT scan images. Liver segmentation is difficult task in medical applications because inter-patient variability in size, shape and disease. In general CT scanning is used to inspect liver cancer. In this research work, the liver tumors are detected by the medical images in three stages, pre-processing stage, processing stage and detection stage. First in pre-processing stage, median filter is used to remove the noise from CT image, and then the denoised image is segmented by fuzzy c-means clustering (FCM) algorithm. Finally in the detection stage distance regularized level set evolution (DRLSE) is used to extract tumor boundaries. This algorithm is very much useful for identifying hepatocellular carcinoma (liver cancer). Experimental results on various noisy CT scan images show that the proposed method is efficient for extracting hepatic tumors from liver.

In this paper, we present an indexing structure of data-driven cuboid patterns to speed up the process of liver detection and segmentation from computed tomography (CT) scans using the cube-based generalized Hough transform (CGHT). Most existing approaches to automatic liver segmentation from CT scans use a statistical shape model (SSM) integrated with a searching algorithm to recover the deformation. However, establishing the correspondences among landmark points of training shapes for the construction of the average shape of SSM remains as a challenge due to the high variation of liver shapes in CT scans. The proposed method is a fully automatic segmentation method that combines four steps. Firstly, a test CT volume is partitioned into multiple non-overlapped sub-volumes with each of them consisting of variable numbers of consecutive slices. Secondly, we locate the cube-based liver shapes in all sub-volumes via Hough voting and dynamic programming. Thirdly, we construct the basic 3D model through a level-set framework for liver shape segmentation. Finally, to introduce neighbors statistical analysis into the above model, we deform the 3D liver shape to overcome disturbances caused by noise and inhomogeneity. The MICCAI 2007 liver segmentation challenge datasets are used to verify the effectiveness of the proposed method. Experimental results demonstrate the good performance of the proposed method in terms of segmentation accuracy and execution speed.

In this paper, the problem of liver segmentation in liver CT images is studied, and the MSN-Net model is proposed. The single-hop connection in the traditional U-Net model is replaced by an embedded structure in the MSN-Net model. The embedded structure is a novel skip-connection architecture between the encoding path and the decoding path. The convolution operation is added to the structure to alleviate the semantic gap caused by the traditional skip connection; in addition, the high-dimensional-low-dimensional feature fusion strategy is used in the embedded structure, which combines the feature maps from high-dimensional and low-dimensional features. The feature maps are combined to enhance the feature expression ability of CT images and extract richer semantic information. The MSN-Net model is subjected to ablation experiments and compared with other current state-of-the-art methods. The experimental results show that the MSN-Net model proposed in this paper has superior segmentation performance.

Deep Learning for Automated Liver Segmentation to Aid in the Study of Infectious Diseases in Nonhuman Primates

Renal cancer is one of ten most common cancers in human beings. The laparoscopic partial nephrectomy (LPN) becomes the main therapeutic approach in treating renal cancer. Accurate kidney and tumor segmentation in CT images is a prerequisite step in the surgery planning. However, automatic and accurate kidney and renal tumor segmentation in CT images remains a challenge. In this paper, we propose a new method to perform a precise segmentation of kidney and renal tumor in CT angiography images. This method relies on a three-dimensional (3D) fully convolutional network (FCN) which combines a pyramid pooling module (PPM). The proposed network is implemented as an end-to-end learning system directly on 3D volumetric images. It can make use of the 3D spatial contextual information to improve the segmentation of the kidney as well as the tumor lesion. The experiments conducted on 140 patients show that these target structures can be segmented with a high accuracy. The resulting average dice coefficients obtained for kidney and renal tumor are equal to 0.931 and 0.802 respectively. These values are higher than those obtained from the other two neural networks.