[Show abstract][Hide abstract] ABSTRACT: The segmentation and detection of various types of nodules in a Computer-aided detection (CAD) system present various challenges, especially when (1) the nodule is connected to a vessel and they have very similar intensities; (2) the nodule with ground-glass opacity (GGO) characteristic possesses typical weak edges and intensity inhomogeneity, and hence it is difficult to define the boundaries. Traditional segmentation methods may cause problems of boundary leakage and "weak" local minima. This paper deals with the above mentioned problems. An improved detection method which combines a fuzzy integrated active contour model (FIACM)-based segmentation method, a segmentation refinement method based on Parametric Mixture Model (PMM) of juxta-vascular nodules, and a knowledge-based C-SVM (Cost-sensitive Support Vector Machines) classifier, is proposed for detecting various types of pulmonary nodules in computerized tomography (CT) images. Our approach has several novel aspects: (1) In the proposed FIACM model, edge and local region information is incorporated. The fuzzy energy is used as the motivation power for the evolution of the active contour. (2) A hybrid PMM Model of juxta-vascular nodules combining appearance and geometric information is constructed for segmentation refinement of juxta-vascular nodules. Experimental results of detection for pulmonary nodules show desirable performances of the proposed method.
Computational and Mathematical Methods in Medicine 04/2013; 2013(1):515386. DOI:10.1155/2013/515386 · 0.77 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: Computer-aided detection(CAD) system for lung nodules plays the important role in the diagnosis of lung cancer. In this paper, an improved intelligent recognition method of lung nodule in HRCT combing rule-based and cost-sensitive support vector machine(C-SVM) classifiers is proposed for detecting both solid nodules and ground-glass opacity(GGO) nodules(part solid and nonsolid). This method consists of several steps. Firstly, segmentation of regions of interest(ROIs), including pulmonary parenchyma and lung nodule candidates, is a difficult task. On one side, the presence of noise lowers the visibility of low-contrast objects. On the other side, different types of nodules, including small nodules, nodules connecting to vasculature or other structures, part-solid or nonsolid nodules, are complex, noisy, weak edge or difficult to define the boundary. In order to overcome the difficulties of obvious boundary-leak and slow evolvement speed problem in segmentatioin of weak edge, an overall segmentation method is proposed, they are: the lung parenchyma is extracted based on threshold and morphologic segmentation method; the image denoising and enhancing is realized by nonlinear anisotropic diffusion filtering(NADF) method; candidate pulmonary nodules are segmented by the improved C-V level set method, in which the segmentation result of EM-based fuzzy threshold method is used as the initial contour of active contour model and a constrained energy term is added into the PDE of level set function. Then, lung nodules are classified by using the intelligent classifiers combining rules and C-SVM. Rule-based classification is first used to remove easily dismissible nonnodule objects, then C-SVM classification are used to further classify nodule candidates and reduce the number of false positive(FP) objects. In order to increase the efficiency of SVM, an improved training method is used to train SVM, which uses the grid search method to search the optimal parameters of C-SVM and uses second order information to achieve fast convergence to select the Sequential Minimal Optimization(SMO) working set. Experimental results of recognition for lung nodules show desirable performances of the proposed method.
International Journal of Computational Intelligence Systems 04/2012; 5(1):76-92. DOI:10.1080/18756891.2012.670523 · 0.45 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: Benefiting from the kernel skill and the sparse property, the relevance vector machine (RVM) could acquire a sparse solution, with an equivalent generalization ability compared with the support vector machine. The sparse property requires much less time in the prediction, making RVM potential in classifying the large-scale hyperspectral image. However, RVM is not widespread influenced by its slow training procedure. To solve the problem, the classification of the hyperspectral image using RVM is accelerated by the parallel computing technique in this paper. The parallelization is revealed from the aspects of the multiclass strategy, the ensemble of multiple weak classifiers, and the matrix operations. The parallel RVMs are implemented using the C language plus the parallel functions of the linear algebra packages and the message passing interface library. The proposed methods are evaluated by the AVIRIS Indian Pines data set on the Beowulf cluster and the multicore platforms. It shows that the parallel RVMs accelerate the training procedure obviously.
[Show abstract][Hide abstract] ABSTRACT: Aimming at the problem of weeding robot has a bigger radius when changing lines in paddy fields. A novel system of weeding robot based on visual navigation was proposed. Firstly, a special and compact mechanical structure of weeding robot is designed. Secondly, to control the weeding robot automatic navigation, motion control and motors driver board and realtime video capture board respectively were designed. The visual navigation algorithm implemented in TI SOC DM6446 on the video capture module. When video capture is completed, the attitude parameters of seedling centerlines were calculated and detected based on the color model and the nearest neighbor algorithm of clustering combined with Hough transform. Finally, according to the parameters, weeding robot was driven to walk along line corps and cut off weeds with the crawler mobile mechanism in stamping mode. When arriving at the end of raw crops, the weeding robot adjusts the supporting device and striding device to fulfill automatic change lines. Nonholonomic equation with parameter uncertainty was applied to the problem of robot motion control system during the navigation process. The effectiveness of the proposed approach was validated by paddy field tests according to the proposed system. And the results show that weeding robot can correctly achieve line-changed action and meets fast, accurate weeding job requirements.
Robotics and Biomimetics (ROBIO), 2012 IEEE International Conference on; 01/2012
[Show abstract][Hide abstract] ABSTRACT: This paper studied the path following case of a PZT-driven electromagnetic miniature robot which was used as a locomotion platform in a "Desktop Micro Robots Factory". To avoid the wire wound-up problem of the former method which happened because of an in-situ rotation of the robot, an improved method was proposed based on temporary path planning. The nonlinearity of the locomotive characteristics according to the difference equation describing the position and orientation changes of the robot was introduced, which was then used in the simulation. The proposed generating path was composed of two arcs and a line with directional information, which aimed at a smoothly joining the desired path at some specified point. Together with a conventional fuzzy logic controller, tracking performance was preferred.
[Show abstract][Hide abstract] ABSTRACT: Piezo was used widely in precise machinery, micro electromechanical system assembly, bio-engineering, optics engineering and so on. Based on the stick-and-slip moving manner, a detailed modeling was studied for a piezo actuators parallel-setup robot, which was able to move on a ferromagnetic working surface. A global vision sensor was used for positioning and locomotive control. A trajectory tracking controller was designed in the image space via Lyapunov function, whose results were verified by simulation.
[Show abstract][Hide abstract] ABSTRACT: How to accurately identify mini-nodules in a large amount of high resolution computed tomography (HRCT) images is always a significant and difficult issue in lung nodule computer-aided detection (CAD). This paper describes a new mini-nodules detection method which is based on a multi-feature tracking algorithm. Our detection method began after running the Da-Jing algorithm and morphological operation to extract the lung region of every HRCT image in a sequence. Once the lung had been extracted, a hybrid algorithm, combining gray threshold and improved template matching, was used to obtain the regions of interest (ROD). Next, several characteristics of each ROI were calculated to identify the final results by using multi-feature tracking throughout the whole HRCT image sequence. The results showed that the proposed method would be of high accuracy with a low occurrence of false positives.
Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi 06/2011; 28(3):437-41.
[Show abstract][Hide abstract] ABSTRACT: In order to realize effectively and efficiently the automatic registration and fusion of multimodal medical images data in 3D conformal radiotherapy treatment planning (3D CRTP), a rapid image registration and fusion method is proposed in this paper. This proposed registration method is based on hierarchical adaptive free-form deformation(FFD) algorithm, which can be described as follows: First the ROI(region of interest) is extracted by using C-V level sets algorithm, and feature points are matched automatically which is based on parallel computing method. Then, the global rough registration is carried out by employing principal axes algorithm. Next, the automatic fine registration of the multimodal medical images is realized by a FFD method based on hierarchical B-splines. Moreover, in order to speed up the calculation of the FFD coefficients, stochastic gradient descent method-Simultaneous Perturbation(SP) and the criteria of maximum mutual information entropy are adopted. After the registration of multimodal images, their sequence images are fused by applying an image fusion method based on parallel computing and wavelet transform with the fusion rule of combining the local standard deviation and energy. This study demonstrates the superiority of the proposed method.
Bioinformatics and Biomedical Engineering (iCBBE), 2010 4th International Conference on; 07/2010
[Show abstract][Hide abstract] ABSTRACT: In order to efficiently and effectively reconstruct 3D medical images and clearly display the detailed information of inner structures and the inner hidden interfaces between different media, an Improved Volume Rendering Optical Model (IVROM) for medical translucent volume rendering and its implementation using the preintegrated Shear-Warp Volume Rendering algorithm are proposed in this paper, which can be readily applied on a commodity PC. Based on the classical absorption and emission model, effects of volumetric shadows and direct and indirect scattering are also considered in the proposed model IVROM. Moreover, the implementation of the Improved Translucent Volume Rendering Method (ITVRM) integrating the IVROM model, Shear-Warp and preintegrated volume rendering algorithm is described, in which the aliasing and staircase effects resulting from under-sampling in Shear-Warp, are avoided by the preintegrated volume rendering technique. This study demonstrates the superiority of the proposed method.
International Journal of Biomedical Imaging 05/2010; 2010:429051. DOI:10.1155/2010/429051
[Show abstract][Hide abstract] ABSTRACT: This is a report on how we use the hybrid force-displacement control method to load the human knee and analyze the effect and value of our robot experimental system through the biomechanical experiments of total meniscal resection of human knee. The whole robot control system can load continuously on the specimens, thus overcoming the shortcomings of the traditional loading methods which can only load discretely. In the meantime, by using the robot-based testing system, the force (torque) of the specimens and the spatial position under the force can be measured in real-time, which overcomes the shortcomings caused by the separation of force (torque) measurement from displacement measurement and so greatly improves the measurement accuracy.
Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi 02/2010; 27(1):62-6.
[Show abstract][Hide abstract] ABSTRACT: In order to classify lung nodules, an approach combining rule-based and SVM is proposed in the paper. Firstly, the candidate ROIs shape features are calculated, and some blood vessels are get rid of using rule-based according to shape features; secondly, the remainder candidates gray and texture features are calculated; finally, the shape, gray and texture features are taken as the inputs of the SVM (Support Vector Machine) classifier to classify the candidates. Experimental results show that the rule-based approach has no omission, but the misclassification probability is too large; the approach combining rule-based and SVM has higher omission than SVM, but lower misclassification. The causes of nodules omission and misclassification are summarized and the solution is discussed in the paper at last.
Fifth International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2010, University of Hunan, Liverpool Hope University, Liverpool, United Kingdom / Changsha, China, September 8-10 and September 23-26, 2010; 01/2010
[Show abstract][Hide abstract] ABSTRACT: This paper studied the path following case of a PZT-driven electromagnetic miniature robot which is used as a locomotion platform in a “Desktop Micro Robots Factory”. Considering the nonlinearity of the locomotive characteristics according to the difference equation describing the position and orientation changes of the robot, a fuzzy logic controller was designed to calculate the driven voltage amplitude applied to the two piezoelectric elements to fulfill the task. To overcome the overshoot when the robot joined the path from a far starting position, an improved method, which introduced a simple coarse initial pose error adjustment before the fuzzy controller took action, was proposed, resulting in a tracking error reduction preferably.
[Show abstract][Hide abstract] ABSTRACT: Perspective Volume Rendering has well known advantages, so it is applied widely in medical visualization. In the visualization of 3D medical images, it is common to frequently adjust the opacity transfer function and viewing angle so that volume rendering is difficult to be realized in real-time. And in traditional perspective Shear-Warp there are the aliasing and staircase effects resulting from under-sampling. In order to efficiently and effectively reconstruct 3D medical images, a novel Rapid Pre-Integrated Perspective Volume Rendering(RPPVR) method based on Pre-Integrated Volume Rendering and Shear-Warp algorithm is proposed in this paper. In the proposed method, classification coding for volume data is implemented by making use of the correlation of opacity transfer function and min-max Octree data structure so that fast reconstruction can be done when opacity transfer function and view angle change. Moreover, the aliasing artifacts resulted from under-sampling can be eliminated by Pre-Integrated Volume Rendering technique incorporated the shading calculation of lighting model, thus improving the reconstruction effect. This study demonstrates the superiority of the proposed method.
[Show abstract][Hide abstract] ABSTRACT: This paper introduces the hardware and software of a biomechanical robot-based testing device. The bottom control orders, posture and torque data transmission, and the control algorithms are integrated in a unified visual control platform by Visual C+ +, with easy control and management. By using hybrid force-displacement control method to load the human spine, we can test the organizational structure and the force state of the FSU (Functional spinal unit) well, which overcomes the shortcomings due to the separation of the force and displacement measurement, thus greatly improves the measurement accuracy. Also it is esay to identify the spinal degeneration and the load-bearing impact on the organizational structure of the FSU after various types of surgery.
Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi 12/2009; 26(6):1246-9.
[Show abstract][Hide abstract] ABSTRACT: It is of paramount importance for the diagnosis and therapy of lung cancer, even for the increasing of 5-year survival rate in that the early dignosis of malignant pulmonary nodules are made by intelligent identification successfully. As it stands, in intelligent identification of pulmonary nodules, computer-aided detection/diagnosis (CAD) plays the most important role. The key points of intelligent identification of pulmonary nodules are (1) Detecting pulmonary nodules based on the characterization of nodule appearance; (2) Measuring accurately the nodule size; (3) Computing accurately the growth rate. This article presents a review on the basic technologies and methods of CAD for identifying malignant pulmonary nodules in the course of making early diagnosis, including lung segmentation, registration of volume data, identification of benign/malignant pulmonary nodule, and so on.
Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi 10/2009; 26(5):1141-5, 1157.
[Show abstract][Hide abstract] ABSTRACT: Multi-modal medical image fusion has important value in clinical diagnosis and treatment. In this paper, the multi-resolution analysis of Daubechies 9/7 Biorthogonal Wavelet Transform is introduced for anatomical and functional image fusion, then a new fusion algorithm with the combination of local standard deviation and energy as texture measurement is presented. At last, a set of quantitative evaluation criteria is given. Experiments show that both anatomical and metabolism information can be obtained effectively, and both the edge and texture features can be reserved successfully. The presented algorithm is more effective than the traditional algorithms.
Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi 05/2009; 26(2):244-7, 252.
[Show abstract][Hide abstract] ABSTRACT: Achmoric power, one of the most important quality indices in a Lithopone calcination process, cannot be measured online economically, which is a similar problem many rotary kiln processes encounter. This paper talks about its predictive model by applying data modeling technique and focuses on the model variable selection. According to the Lithopone calcination mechanism, several schemes of model variable selection are discussed, and the one based on energy variation which mixes the information of calcinating temperature and calcinating duration together is chosen at last. To calculate the energy absorbed by the material, ldquounit energyrdquo is introduced, which offers a convenient expression in the form of relative value. Using this novel model variable selection method, the model structure is simplified, which has an advantage in model efficiency. A predictive model for achmoric power is obtained in the next step by least square support vector machines method, and the simulation result shows its promising performance.
[Show abstract][Hide abstract] ABSTRACT: A Fast Multi-resolution Volume Rendering Method (FMVRM) based on wavelet and Shear-Warp is herein proposed. In this method, the medical volume data is compressed using wavelet transformation first. Then based on the set resolution, the medical volume data is decompressed guided by Opacity transfer function (OTF). Finally, the 3D medical image is reconstructed on the basis of Shear-Warp using Block-based run length encoded (BRLE) data structure, in which, the aliasing artifacts resulting from under-sampling in Shear-Warp is avoided by the pre-integrated volume rendering technology. Experiments demonstrate the good performance of the proposed method.
Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi 11/2008; 25(5):1178-83.
[Show abstract][Hide abstract] ABSTRACT: In order to improve the effect and efficiency of the reconstructed image after hybrid volume rendering of different kinds of volume data from medical sequential slices or polygonal models, we propose a hybrid volume rendering method based on Shear-Warp with economical hardware. First, the hybrid volume data are pre-processed by Z-Buffer method and RLE (Run-Length Encoded) data structure. Then, during the process of compositing intermediate image, a resampling method based on the dual-interpolation and the intermediate slice interpolation methods is used to improve the efficiency and the effect. Finally, the reconstructed image is rendered by the texture-mapping technology of OpenGL. Experiments demonstrate the good performance of the proposed method.
Sheng wu yi xue gong cheng xue za zhi = Journal of biomedical engineering = Shengwu yixue gongchengxue zazhi 07/2008; 25(3):524-30.