scispace - formally typeset
Search or ask a question
Author

Xiaochun Yang

Bio: Xiaochun Yang is an academic researcher from Tongji University. The author has contributed to research in topics: Canopy clustering algorithm & Fuzzy clustering. The author has an hindex of 2, co-authored 3 publications receiving 34 citations.

Papers
More filters
Proceedings ArticleDOI
11 Jun 2009
TL;DR: A liver segmentation method based on region growing approach is proposed, and the superior liver region is extracted by applying the morphologic operation on a variety of CT images.
Abstract: Accurate liver segmentation on computed tomography (CT) images is a challenging task because of inter and intra- patient variations in liver shapes, similar intensity with its nearby organs. We proposed a liver segmentation method based on region growing approach. First of all, basic theory of region growing approach is introduced. Secondly, a pre-processing method using anisotropic filter and Gaussian function is employed to form liver likelihood images for the following segmentation. Thirdly, an improved slice-to-slice region growing method combined with centroid detection and intensity distribution analysis is proposed. Finally, the superior liver region is extracted by applying the morphologic operation. Experiments on a variety of CT images show the effectiveness and efficiency of the proposed method.

30 citations

Proceedings ArticleDOI
16 May 2008
TL;DR: An improved clustering algorithm based on the Ant-Tree algorithm that builds adaptively a tree structure which changes over the run in order to improve the final results.
Abstract: In this paper, we propose an improved clustering algorithm based on the Ant-Tree algorithm. This method represents a more flexible version of its basis. The classes with high density are defined as definite classes, and our algorithm starts with finding the definite classes. Centroid approximation method is utilized to make the clustering model of Ant-Tree more accurately by approaching the real center of the classes gradually. The ants that have fixed themselves on the structure can be disconnected from the tree for a better position, and in this way more accurate results of clustering can be achieved. As a consequence, this algorithm builds adaptively a tree structure which changes over the run in order to improve the final results. Compared against some other ant-based clustering algorithms, our approach acquires better results on some standard databases efficiently as demonstrated in experiments.

4 citations

Proceedings ArticleDOI
01 Jun 2008
TL;DR: An improved clustering algorithm based Ant-Tree is used for recognition of certain kind of architectural symbols with prior knowledge in engineering drawings to get easily with the guidance of some prior knowledge.
Abstract: In this paper, an improved clustering algorithm based Ant-Tree is used for recognition of certain kind of architectural symbols with prior knowledge in engineering drawings. Symbols are segmented from an AutoCAD format drawing and a vector of invariants based on pseudo-Zernike moments is calculated to represent the graphical feature of a symbol. A normalization method is used to make these moments invariant of translation, rotation and scaling. Then the improved Ant-Tree algorithm is applied to cluster the symbols with regard to their features. The class of target symbols can thus be got easily with the guidance of some prior knowledge. For the proposed clustering algorithm, a new initialization method is presented with regard to the distribution of the data, and centroid approximation is also utilized to optimize the clustering process. Experiments show the effectiveness of our recognition approach proposed.

2 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: In order to accurately detect the liver surface, deformable graph cut was proposed, which effectively integrates the properties and inter-relationship of the input images and initialized surface.
Abstract: Liver segmentation is still a challenging task in medical image processing area due to the complexity of the liver’s anatomy, low contrast with adjacent organs, and presence of pathologies. This investigation was used to develop and validate an automated method to segment livers in CT images. The proposed framework consists of three steps: 1) preprocessing; 2) initialization; and 3) segmentation. In the first step, a statistical shape model is constructed based on the principal component analysis and the input image is smoothed using curvature anisotropic diffusion filtering. In the second step, the mean shape model is moved using thresholding and Euclidean distance transformation to obtain a coarse position in a test image, and then the initial mesh is locally and iteratively deformed to the coarse boundary, which is constrained to stay close to a subspace of shapes describing the anatomical variability. Finally, in order to accurately detect the liver surface, deformable graph cut was proposed, which effectively integrates the properties and inter-relationship of the input images and initialized surface. The proposed method was evaluated on 50 CT scan images, which are publicly available in two databases Sliver07 and 3Dircadb. The experimental results showed that the proposed method was effective and accurate for detection of the liver surface.

161 citations

Journal ArticleDOI
TL;DR: Experimental results show that the proposed method can detect the liver accurately with significant reduction of processing time, especially when dealing with diseased liver cases.
Abstract: Accurate segmentation of liver from abdominal CT scans is critical for computer-assisted diagnosis and therapy. Despite many years of research, automatic liver segmentation remains a challenging task. In this paper, a novel method was proposed for automatic delineation of liver on CT volume images using supervoxel-based graph cuts. To extract the liver volume of interest (VOI), the region of abdomen was firstly determined based on maximum intensity projection (MIP) and thresholding methods. Then, the patient-specific liver VOI was extracted from the region of abdomen by using a histogram-based adaptive thresholding method and morphological operations. The supervoxels of the liver VOI were generated using the simple linear iterative clustering (SLIC) method. The foreground/background seeds for graph cuts were generated on the largest liver slice, and the graph cuts algorithm was applied to the VOI supervoxels. Thirty abdominal CT images were used to evaluate the accuracy and efficiency of the proposed algorithm. Experimental results show that the proposed method can detect the liver accurately with significant reduction of processing time, especially when dealing with diseased liver cases.

90 citations

Journal ArticleDOI
TL;DR: The proposed computer-aided diagnosis system for detecting cirrhosis and hepatocellular carcinoma (HCC) showed promising results and can be used as effective screening tool in medical image analysis.
Abstract: High mortality rate due to liver cirrhosis has been reported over the globe in the previous years. Early detection of cirrhosis may help in controlling the disease progression toward hepatocellular carcinoma (HCC). The lack of trained CT radiologists and increased patient population delays the diagnosis and further management. This study proposes a computer-aided diagnosis system for detecting cirrhosis and HCC in a very efficient and less time-consuming approach. Contrast-enhanced CT dataset of 40 patients (n = 40; M:F = 5:3; age = 25–55 years) with three groups of subjects: healthy (n = 14), cirrhosis (n = 12) and cirrhosis with HCC (n = 14), were retrospectively analyzed in this study. A novel method for the automatic 3D segmentation of liver using modified region-growing segmentation technique was developed and compared with the state-of-the-art deep learning-based technique. Further, histogram parameters were calculated from segmented CT liver volume for classification between healthy and diseased (cirrhosis and HCC) liver using logistic regression. Multi-phase analysis of CT images was performed to extract 24 temporal features for detecting cirrhosis and HCC liver using support vector machine (SVM). The proposed method produced improved 3D segmentation with Dice coefficient 90% for healthy liver, 86% for cirrhosis and 81% for HCC subjects compared to the deep learning algorithm (healthy: 82%; cirrhosis: 78%; HCC: 70%). Standard deviation and kurtosis were found to be statistically different (p < 0.05) among healthy and diseased liver, and using logistic regression, classification accuracy obtained was 92.5%. For detecting cirrhosis and HCC liver, SVM with RBF kernel obtained highest slice-wise and patient-wise prediction accuracy of 86.9% (precision = 0.93, recall = 0.7) and 80% (precision = 0.86, recall = 0.75), respectively, than that of linear kernel (slice-wise: accuracy = 85.4%, precision = 0.92, recall = 0.67; patient-wise: accuracy = 73.33%, precision = 0.75, recall = 0.75). The proposed computer-aided diagnosis system for detecting cirrhosis and hepatocellular carcinoma (HCC) showed promising results and can be used as effective screening tool in medical image analysis.

45 citations

Proceedings ArticleDOI
04 Oct 2018
TL;DR: Li et al. as mentioned in this paper proposed a 3D to 2D fully convolution network (3D-2D-FCN) to segment the target liver in less than a minute with Dice score of 93.52%.
Abstract: The need for CT scan analysis is growing for diagnosis and therapy of abdominal organs. Automatic organ segmentation of abdominal CT scan can help radiologists analyze the scans faster, and diagnose disease and injury more accurately. However, existing methods are not efficient enough to perform the segmentation process for victims of accidents and emergency situations. In this paper, we propose an efficient liver segmentation with our 3D to 2D fully convolution network (3D-2D-FCN). The segmented mask is enhanced using the conditional random field on the organ's border. Consequently, we segment a target liver in less than a minute with Dice score of 93.52%.

35 citations

01 Jan 2013
TL;DR: Various approaches of MRI brain image segmentation algorithms are reviewed and their advantages, disadvantages are discussed.
Abstract: Brain tumour is one of the most dangerous disease occurring commonly among human beings. The chances of survival can be increased if the tumour is detected correctly at its early stage. MRI brain imaging technique is widely used to visualize the anatomy and structure of the brain. The images produced by MRI are high in tissue contrast and have fewer artifacts. It has several advantages over other imaging techniques, providing high contrast between soft tissues. However, the amount of data is far too much for manual analysis, which has been one of the biggest obstacles in the effective use of MRI. The detection of tumour requires several processes on MRI images which includes image preprocessing, feature extraction, image enhancement and classification. The final classification process concludes that a person is diseased or not. Although numerous efforts and promising results are obtained in medical imaging area, reproducible segmentation and classification of abnormalities are still a challenging task because of the different shapes, locations and image intensities of different types of tumours. In this paper, various approaches of MRI brain image segmentation algorithms are reviewed and their advantages, disadvantages are discussed.

33 citations