Search

With the development of deep learning network models, the automatic segmentation of medical images is becoming increasingly popular. Left ventricular cavity segmentation is an important step in the diagnosis of cardiac disease, but post-processing segmentation is a time-consuming and challenging task. That is why a fully automated segmentation method can assist specialists in increasing their efficiency. Inspired by the power of deep neural networks, a multi-scale multi-skip connection network (MMNet) model is proposed to fully automate the left ventricular segmentation of cardiac magnetic resonance imaging (MRI) images; this model is simple and efficient and has high segmentation accuracy without pre-detecting left ventricular localization. MMNet redesigns the classic encoder and decoder to take advantage of multi-scale feature information, effectively solving the problem of difficult segmentation due to blurred left ventricular edge information and the low accuracy of end-systolic segmentation of the cardiac area. In the model encoding stage, a multi-scale feature fusion module applying dilated convolution is proposed to obtain richer semantic information from different perceptual fields. The decoding stage reconstructs the full-size skip connection structure to make full use of the feature information obtained from different layers for contextual semantic information fusion. At the same time, a pre-activation module is used before each weighting layer to prevent overfitting phenomena from arising. The experimental results demonstrate that the proposed model has better segmentation performance than advanced benchmark models. Ablation experiments show that the proposed modules are effective at improving segmentation results. Therefore, MMNet is a promising approach for the left ventricular fully automated segmentation.

Ensemble learning is an effective approach for improving the generalization ability of base classifiers. To generate a set of accurate and diverse base classifiers, different data perturbation schemes have been proposed. For instance, Bagging perturbs the training data via bootstrap sampling. However, when a stable learning algorithm (e.g., KNN, Naive Bayes) is used to train base classifiers, the sole perturbation on the training data may not produce diverse base classifiers. In this paper, by using the attribute reduction technology in rough sets, a multi-modal perturbation-based algorithm (called ‘E _ EARBS’) is proposed for the ensemble of base classifiers. E _ EARBS simultaneously perturbs the feature space, training data and learning parameters, where the relative decision entropy(RDE)-based approximate reducts are used to perturb the feature space, and bootstrap sampling is used to perturb the training data. Experimental results show that E _ EARBS can provide competitive solutions for ensemble learning.

Glaucoma is a leading cause of blindness. Accurate and efficient segmentation of the optic disc and cup from fundus images is important for glaucoma screening. However, using off-the-shelf networks against new datasets may lead to degraded performances due to domain shift. To address this issue, in this paper, we propose a coarse-to-fine adaptive Faster R-CNN framework for cross-domain joint optic disc and cup segmentation. The proposed CAFR-CNN consists of the Faster R-CNN detector, a spatial attention-based region alignment module, a pyramid ROI alignment module and a prototype-based semantic alignment module. The Faster R-CNN detector extracts features from fundus images using a VGG16 network as a backbone. The spatial attention-based region alignment module extracts the region of interest through a spatial mechanism and aligns the feature distribution from different domains via multilayer adversarial learning to achieve a coarse-grained adaptation. The pyramid ROI alignment module learns multilevel contextual features to prevent misclassifications due to the similar appearances of the optic disc and cup. The prototype-based semantic alignment module minimizes the distance of global prototypes with the same category between the target domain and source domain to achieve a fine-grained adaptation. We evaluated the proposed CAFR-CNN framework under different scenarios constructed from four public retinal fundus image datasets (REFUGE2, DRISHTI-GS, DRIONS-DB and RIM-ONE-r3). The experimental results show that the proposed method outperforms the current state-of-the-art methods and has good accuracy and robustness: it not only avoids the adverse effects of low contrast and noise interference but also preserves the shape priors and generates more accurate contours.

Segmentation of multimodal brain tissues from 3D medical images is of great significance for brain diagnosis. It is required to create an automated and accurate segmentation based on deep-learning network due to the manual segmentation is time-consuming. However, how to segment medical images accurately and how to build neural network effectively with very limited computing resource, is still challenging task. To address these problems, we propose a novel model based on 3D fully convolutional network. More specifically, we apply multi-pathway architecture to feature extraction so as to effectively extract features from multi-modal MRI images. Different receptive field of feature have been extracted by adopting 3D dilated convolution in each pathway. By evaluating one-pathway model and key components of our model with a set of effective training schemes, we analyzed how these alternative methods affect the performance of experiments. Our proposed model was evaluated in the Brain Tumor Segmentation 2019 dataset (BraTS 2019), making an effective segmentation for the complete, core and enhancing tumor regions in Dice Similarity Coefficient metric (0.89, 0.78, 0.76) for the dataset. Also, we made a practice on BraTS 2018 using the same method with the Dice Similarity Coefficient metric of 0.90, 0.79, and 0.77 for the complete, core and enhancing tumor regions. Our method is inherently general and is a powerful tool to studies of medical images of brain tumors. Our code is available at https://github.com/JalexDooo/BrainstormTS .

The presence of proper wrinkles is important while modeling realistic virtual garments. Unlike previously used full 3D information methods, our approach achieves detailed garment generation from a single image. First, we retrieve a garment image similar to the initial virtual garment based on content-based image retrieval (CBIR) method. Then, we preprocess the image with a combination of human body reshaping, image segmentation and shape recovery, to obtain the 3D wrinkle details. Finally, the garment height are synthesized into the virtual garment. For better suit the posture of the human body, excess garment energy are released to remove the unmatched wrinkles. We apply our method to various styles of virtual garments, and it enable virtual characters in general pose to be dressed in these garments and complete wrinkle generation. Compared with existing garment modeling methods, the experimental results show that the proposed method could quickly capture the realistic wrinkles of virtual garments with less manual operation and achieve more realistic wrinkles for virtual garments.

With the recent advancement in Industrial Internet of Things (IIoT), general programmable logic controllers (PLCs) have been playing more and more critical roles in industrial control systems (ICSs), such as providing local data processing, decentralized control and fault diagnosis. These so called edge-PLCs, directly receive the raw data from sensors embedded in factory equipments, put them into predefined memory space and perform analysis using programs such as the ladder logic. The challenge is how to allocate blocks in the fixed-size memory to different sensors so as to match irregular data flows. In this paper, we try to conduct performance analysis of different partition instances of the memory in the edge-PLC by modeling this problem as a multiple single-server queueing systems. We assume every sensing flow is independent of each other and has its dedicated processer. Changes can be made to partition instances to adapt to the external environment, such as the rising of order numbers or product category switching. Each state of the environment is defined by the finite state Markov chain and arrival of sensing data flows follow the stationary Poisson process. The data in the queue will expire after staying in the memory for a while. The duration of availability and service is modeled as the exponential distribution. The performance measured under different system states are analyzed in the simulation.

In the domain of geotechnical engineering analysis, fast Lagrangian analysis based on the finite difference method is the most commonly used numerical analysis method. It is a classical numerical algorithm applied to calculate the in situ stress. In this paper, we propose a deep learning (DL) architecture called the enhance-and-split feature capsule network embedded in fully convolutional neural networks (ES-Caps-FCN) to predict the in situ stress for a strain-softening model when using the finite difference method for the numerical computation. Experiments indicate that this novel approach is stable and convergent. Compared with some classical prediction methods including linear regression analysis and a deep neural network, the mean squared error of our proposed algorithm is as low as 0.059866%, which is lower than the 0.616676% of the deep neural network prediction algorithm and the 0.978495% of the conventional machine learning algorithm. Additionally, the calculation efficiency of fully trained deep learning models is superior to that of the conventional finite difference method. Therefore, DL is a feasible and promising fast and accurate surrogate for the finite difference method for solving the in situ stress.

Unstructured point clouds are a representative shape representation of real-world scenes in 3D vision and graphics. Incompletion inevitably arises, due to the way the set of unorganized points is captured, e.g., as fusion of depth images, merged laser scans, or structure-from-x. In this paper, an end-to-end sparse-to-dense multi-encoder neural network (termed an SDME-Net) is proposed for uniformly completing an unstructured point cloud with its shape details preserved. Unlike most existing learning-based shape completion methods that are enforced on the representations of 2D images and 3D voxelization of point clouds, and require priors of the underlying shape's structures, topologies and annotations, the SDME-Net is implemented on the incomplete and even noisy point cloud without any transformation, and makes no specific assumptions about the incompletion distribution and geometry features in the input. Specifically, the defective point cloud is completed and optimized in a sparse-to-dense manner of two-stages. In the first stage, we generate a sparse but complete point cloud based on a bistratal PointNet, and in the second stage, we yield a dense and high-fidelity point cloud by encoding and decoding the sparse result in the first stage using PointNet++. Meanwhile, we combine the distance loss and repulsion loss to generate more uniformly distributed output point clouds closer to the ground-truth counterparts. Qualitative and quantitative experiments on the public ShapeNet dataset illustrate that our approach outperforms the state-of-art learning-based point cloud shape completion methods in terms of real structure recovery, uniformity, and noise/partiality robustness.

Face symmetrization has extensive applications in both medical and academic fields, such as facial disorder diagnosis. Human face possesses an important characteristic, which is as known as symmetry. However, in many scenarios, the perfect symmetry doesn't exist in human faces, which yields a large number of studies around this topic. For example, facial palsy evaluation, facial beauty evaluation based on facial symmetry analysis, and many among others. Currently, there are still very limited researches dedicated for automatic facial symmetrization. Most of the existing studies only utilized their own implantations for facial symmetrization to assist their interdisciplinary academic researches. Limitations thus can be noticed in their methods, such as the requirements for manual interventions. Furthermore, most existing methods utilize facial landmark detection algorithms for automatic facial symmetrization. Though accuracies of the landmark detection algorithms are promising, the uncontrolled conditions in the facial images can still negatively impact the performance of the symmetrical face production. To this end, this paper presents a joint-loss enhanced deep generative network model for automatic facial symmetrization, which is achieved by a full facial image analysis. The joint-loss consists of a pair of adversarial losses and an identity loss. The adversarial losses try to make the generated symmetrical face as realistic as possible, while the identity loss helps to constrain the output to have the same identity of the person in the original input as much as possible. Rather than an end-to-end learning strategy, the proposed model is constructed by a multi-stage training process, which avoids the demand for a large size of the symmetrical face as training data. Experiments are conducted with comparisons with several existing methods based on some of the most popular facial landmark detection algorithms. Competitive results of the proposed method are demonstrated.

We present a dual adaptive garment slice adjustment technique for automatic resizing of apparel products with variant body shapes, and this technique can quickly generate clothed characters. Our first contribution is to propose a novel fit evaluation method. When a 2D garment pattern and a 3D draped garment have the same triangle topology connection, we calculate the shape variable of each triangle and output heat map simultaneously. For sewing a pattern to a newly targeted human body, we propose a fully automatic adjustment method that conforms to the body structure and is composed of two stages. In the coarse auto adjustment (CAA) stage, we propose a method of controlling the size of a garment by the length of a bounding box in five parts of the human body. Then, the garment pattern is automatically adjusted using the measured dimension, by stretching or shrinking. In the fine auto adjustment (FAA) stage, boundary vertices control the shape in the adjustment process. For better matching with the body, the vertices of the garment pattern boundary are relocated with the calculated moving distance and moving direction. As demonstrated in the results, our method enables fully automatic adjustment, preserving the original pattern style of garments between characters with vastly body shapes. Compared with the state-of-art 2D editing method, our proposed approach leads to time saving, and it achieves realistic garment effect compared to auto fitting methods.

Current developments in information and electronic technologies have pushed a tremendous amount of applications to meet the demands of personal computing services. Various kinds of smart devices have been launched and applied in our daily lives to provide services for individuals; however, the existing computing frameworks including local silo-based and cloud-based architectures, are not quite fit for personal computing services. Meanwhile, personal computing applications exhibit special features, they are latency-sensitive, energy efficient, highly reliable, mobile, etc, which further indicates that a new computing architecture is urgently needed to support such services. Thanks to the emerging edge computing paradigm, we were inspired to apply the distributed cooperative computing idea at the data source, which perfectly solves issues occurring among existing computing paradigms while meeting the requirements of personal computing services. Therefore, we explore personal computing services utilizing the edge computing paradigm, discuss the overall edge-based system architecture for personal computing services, and design the conceptual framework for an edge-based personal computing system. We analyze the functionalities in detail. To validate the feasibility of the proposed architecture, a fall detection application is simulated in our preliminary evaluation as an example service in which three Support Vector Machine based fall detection algorithms with different kernel functions are implemented. Experimental results show edge computing architecture can improve the performance of the system in terms of total latency, with about 22.75% reduction on average in the case of applying 4G at the second hop even when the data and computing stream of the application is small.

Falls are abnormal activity events that occur infrequently; however, they are serious health problems among elderly individuals. With the advancements of technologies, falls have been widely studied by scientific researchers to minimize serious consequences and negative impacts. Fall detection and fall prevention are two strategies to tackle fall issues with a variety of sensing techniques and classifier models. Currently, many reviews on fall-related technologies have been presented and analyzed; however, most of them give surveys on the subfield of fall-related systems, while others are not extensive and comprehensive reviews. In fact, the latest researches have a new trend of fusion-based methods to improve the performance of the fall-related systems based on a combination of different sensors or classifier models. Adaptive threshold and radio frequency-based systems are also researched and proposed recently, which are seldom mentioned in other reviews. Therefore, a global taxonomy for current fall-related studies from four aspects, including current literature reviews, fall detection, and prevention systems based on different sensor apparatus and analytic algorithm, low power techniques, and sensor placements for fall-related systems are conducted in this paper. Several research challenges and issues in the fall-related field are also discussed and analyzed. The objective of this review paper is to conclude and provide a good position of current fall-related studies to inspire researchers in this field.

Recently, proximity-based outlier detection methods receive much attention. For any given object x, a proximity-based method usually measures the degree of outlierness of x through examining the nearest neighbor structure of x, where the size of nearest neighborhood should be predetermined by the users. However, it is difficult for users to determine the size of nearest neighborhood. To solve the above problem, in this paper, we present an approximation accuracy entropy-based outlier detection algorithm, called ODAAE, within the framework of rough sets. Approximation accuracy entropy is an extension of Shannon information entropy in rough sets. To quantify the degree of outlierness of any given object, we develop a measure called the AAE(approximation accuracy entropy)-based outlier factor. Experimental results on real-world data sets show that the proposed algorithm is effective for outlier detection.

The theory of compressed sensing brings a revolutionary breakthrough to signal acquisition technology, it can sample the signal far below the Nyquist frequency, and accurately reconstruct the original signal through numerical optimization method. In order to improve the precision of microseismic signal after reconstruction and improve the sampling efficiency, an adaptive microseismic data compressed sensing method based on dictionary learning is proposed in this paper. Firstly, the adaptive redundancy dictionary is constructed according to the characteristics of the microseismic signal. Then the energy and the sparsity under redundant dictionary of signal are calculated. Finally, according to the comprehensive index of energy and sparseness, an adaptive sampling strategy of compressed sensing is developed. Simulation experiment show that, the algorithm reduces the number of samples by 10% compared with traditional compressed sensing, and improves the reconstruction accuracy.

Gliomas are the most common brain tumors, which have a high mortality. Magnetic resonance imaging (MRI) is useful to assess gliomas, in which segmentation of multimodal brain tissues in 3D medical images is of great significance for brain diagnosis. Due to manual job for segmentation is time-consuming, an automated and accurate segmentation method is required. How to segment multimodal brain accurately is still a challenging task. To address this problem, we employ residual neural blocks and a U-Net architecture to build a novel network. We have evaluated the performances of different primary residual neural blocks in building U-Net. Our proposed method was evaluated on the validation set of BraTS 2020, in which our model makes an effective segmentation for the complete, core and enhancing tumor regions in Dice Similarity Coefficient (DSC) metric (0.89, 0.78, 0.72). And in testing set, our model got the DSC results of 0.87, 0.82, 0.80. Residual convolutional block is especially useful to improve performance in building model. Our proposed method is inherently general and is a powerful tool to studies of medical images of brain tumors.

Multi-robot services are widely used to improve the efficiency of industry Internet applications, especially in smart factories. Under the situation that the tasks are becoming more and more intensive, how can smart factories use limited robot resources to complete tasks more efficiently? In order to solve this problem, we transform it into a resource-constrained multiproject scheduling problem, and consider using a combinatorial auction method to get the solution. In order to ensure the security of the system and solve the transaction cost of the robot system, we adopt Blockchain technology and smart contracts to organize the work of the robots. We finally conducted performance analysis of our proposed method, and the results show that smart contracts and combined auction algorithms are safe and effective.

Skin lesion image segmentation task has many difficulties due to the hair occlusion or low contrast. Traditional methods based image quality are powerless when processing these kinds of skin images. In this paper, a segmentation architecture based adversarial networks is proposed. The architecture is consist of a segmentation network based U-net and a discrimination network linked by certain convolutional layers. Both two networks are trained alternately and at last segmentation network gets a high segmentation accuracy. We test our architecture on dataset PH2 and dataset obtained from “Skin Lesion Analysis Toward Melanoma Detection” challenge which was hosted by ISBI 2016 conference and we achieved segmentation average accuracy of 0.97, dice coefficient of 0.94 which outperform other existed segmentation network, including winner of ISBI 2016 challenge for skin melanoma segmentation.

Mitochondrion is important organelle of most eukaryotes and play an important role in participating in various life activities of cells. However, some functions of mitochondria can only be achieved in specific submitochondrial location, the study of submitochondrial locations will help to further understand the biological function of protein, which is a hotspot in proteomics research. In this paper, we propose a new method for protein submitochondrial locations prediction. Firstly, the features of protein sequence are extracted by combining Chou's pseudo-amino acid composition (PseAAC) and pseudo-position specific scoring matrix (PsePSSM). Then the extracted feature information is denoised by two-dimensional (2-D) wavelet denoising. Finally, the optimal feature vectors are input to the SVM classifier to predict the protein submitochondrial locations. We obtained the ideal prediction results by jackknife test and compared with other prediction methods. The results indicate that the proposed method is significantly better than the existing research results, which can provide a new method to predict protein locations in other organelles. The source code and all datasets are available at https://github.com/QUST-BSBRC/PseAAC-PsePSSM-WD/ for academic use.

This paper proposed an improved point based method to simulate the deformation and cutting of cornea, realized the real-time interaction between the force feedback device and the model in virtual surgery. We construct a hybrid deformable model, the model consists of two parts: the interior of the cornea consists of some particles, and the boundary consists of some meshes which are formed by surfaces nodes, calculate the stress tensor of particle can simulate corneal deformation. In this process, in order to ensure the stability of the deformation, a volume constraint is added to our model. By sampling on the surface of the model to form some meshes, the model could support the changes of topology. Using a node replication method for surface cutting and subdivide the cutting triangles in the cutting process, so that it can generate relatively smooth incision. Experiments show that the model provides a real and efficient deformation simulation, with good stability and scalability.

Many medical and real images are suffered from intensity inhomogeneity and weak edges. For higher image segmentation quality, lots of level set-based methods have been proposed. Some of them however cannot take advantage of image gradient information. And severe intensity inhomogeneity and weak edges are not disposed properly. To address these problems, a new level set method integrated with local direction gradient information is presented in this paper. Firstly, according to the two assumptions on image intensity inhomogeneity adopted by many existing methods, a new pixel classification model based on image gradient is introduced. Secondly, we employ variational level set method combined with image spatial information, which improves the anti-noise capability of the proposed method. Finally, considering the gray gradients in homogeneous regions are close to constants, an improved diffusion process is incorporated into the level set function to make the evolving curves stay around true image edges. To verify our method, different testing images including synthetic images, magnetic resonance imaging (MRI) and real-world images are introduced. The image segmentation results demonstrate that our method can deal with the relatively severe intensity inhomogeneity and obtain the comparatively ideal segmentation results efficiently.

Bone sawing is widely used for mandibular angle reduction. In this paper, we develop a surgical simulator for mandibular angle reduction with real-time collision detection, bone reconstruction and force haptic. A volume-based model was organized following the CT or MRI image sequence arrangement. The surgical instrument was simplified into two triangles in geometric model. Then, a new volume-based collision detection method was used to meet the real-time requirements of the simulator. Currently, most of the bone sawing operations regarded the swept surface as the real cut surface of bone. Due to the high-speed reciprocating of the bone saw operation, we innovatively used Marching Cubes Method for the real-time reconstruction of the bone internal sawing part and provided the users with a fine cutting surface. In addition, to obtain a well virtual effect, a simplified bone removal and reconstruction method is carried out to implement the real-time topological changing of the mandibular surface. This paper presents a mechanistic model for prediction of the force during bone sawing, and the simulated force is similar to the measured force in real surgery. Eventually, we realized the high quality visual rendering and tactile rendering, the refresh rate of the force reaches 1000 Hz, and visual refresh frequency up to 30 Hz. To validate the effectiveness of the system, some experiments of simulator evaluation based on the patient-specific data was constructed. Results shown that the virtual orthopedic surgical simulation system can provide inexperienced interns and students with a low-cost, repeatable surgical training platform.

In this paper, an interactive dynamic simulation method is proposed to solve computational models of soft tissue undergoing large deformation, collision detection, and volume conservation in medical surgical simulation visualization. During the process of implementation of the interactive dynamic simulation method, the point-based method is used to simulate the elastic solids undergoing large deformations and the position-based method is used to simulate the objects collision, friction and volume conservation. Numerical results demonstrate that the proposed method improves the efficiency and stability of the response of heterogeneous soft tissue undergoing contact or even the multi-organs interactions, and it can be extended to interactive biopsy and cutting simulation.

We present a novel virtual try-on solution for fitting evaluation and pattern modification to design various types of garment and speed up the garment design process. In the phase of fit evaluation, we propose a method for producing two-dimensional (2D) color maps by comparing a 2D triangle mesh panel garment and a 3D triangle mesh garment, which can display the fit evaluation outcome in real time. In the phase of pattern modification, a novel prior condition based on maximum entropy coordinates and a more comprehensive mean value coordinates interpolation algorithm are proposed. By a combination of the two deformation methods, the positions of the internal vertices are updated smoothly. Applying the proposed method to the repetition of the garment design procedure, the experimental results show that it can easily pinpoint the location where it needs to be modified and can achieve arbitrary pattern modification with a smooth mesh update.

Displaying a variety of fabrics on a customized character could help customers choose which fabric is more suitable for themselves and help customers choose clothing. However, it is not an easy task to show realistic garment on customized virtual character. As a result, we propose a stable finite element method (FEM) model which is stable to approximate stretching behaviors. At first, we measure four kinds of cloth materials with measurement techniques to research elastic deformations in real cloth samples. Then, we use the parameter optimization method by fitting the model with measurement data. For promoting the display of realistic fabrics, we recover 3D human in shape and pose from a single image automatically. Human body datasets are constructed at first. Then, CNN-based image retrieval in shape and skeleton-based template matching method in pose are combined for 3D human model recovery. To enrich human body details, we synthesize the human body and 3D face with spatial transformation. We compared our proposed method of recovering 3D human from a single image with the state-of-the-art methods, and the experimental results show that the proposed method allows the recovered virtual human to put on garment with different fabrics and significantly improves the fidelity of virtual garment.

The concentric torque-split face gear transmission is mainly developed for the rotorcraft which demands high power density and large speed reduction ratio. This paper aims at predicting the load sharing behaviours among paths. An original quasistatic load sharing analysis model, which is a hybrid finite element/lumped parameter quasistatic gear model, is presented. The connection between spur gear and face gear is also established. A number of numerical simulations of load sharing behaviour analysis are conducted. The mechanism of uneven load sharing is revealed. It is observed that the support stiffness of pinion and backlash have significant influences on the load sharing behaviours of the concentric torque-split face gear transmission.

Applications such as garment industry require a two-dimensional (2D) model to assume a three-dimensional (3D) shape. A new surface flattening method based on energy fabric deformation is proposed in this paper. First, the 3D triangular mesh is flattened to a 2D plane to approximate the original surface through initial flattening. Then, the initial flattening result for further optimization by relaxing strain energy. A simplified energy-based fabric deformation model is proposed as our physical model for determining the optimum 2D pattern. Some key procedures for initial flattening are included such as new standard selection of seed triangle and new constrained triangle flattening method. An innovation unify axes system process is presented to get deformation energy. Energy relaxation is also presented can be used as local correction. Compared with other energy-based method, experiment results show that proposed method could achieve better flattening results.

Interactive dynamic simulation method is proposed to solve computational models of soft tissue undergoing large deformation, collision detection, volume conservation in medical surgical simulation visualization. During the process of implementation of the interactive dynamic simulation method, the point based method is used to simulate the elastic solids undergoing large deformations and the position based method is used to simulate the objects collision, friction and volume conservation. It improves the efficiency and stability of the response of heterogeneous soft tissue undergoing contact or even the multi-organs interactions, and can be extended to interactive biopsy and cutting simulation.

Mesh generation is a key step for many areas. Here, an adaptive mesh generation algorithm for piecewise linear domains based on constrained Delaunay is proposed. We focus on improving the quality of the meshes generated and make them conforming to an isotropic size function which is specified by the user. The preliminary mesh with boundaries conforming is generated first. We try to add points to split the mesh either bad shape or not conforming to the size function. The new point can be added to the domain only if it is not close to the existing point in the domain. Finally, local meshes are reconstructed to make all meshes comply with the constrained Delaunay. Experimental comparisons show that the new algorithm is advantageous in generating adaptive mesh. The presented method can be used in a wide range of areas such as computer vision, finite element method and many other areas.

A fast segmentation algorithm of single medical image and sequence images based on active contour model are proposed in this paper. We give out the initial contour forecast segmentation model of 3D medical image first, and then, numerical solution of the image segmentation model algorithm is presented, send data blocks to different processors to do numerical calculations, finally combine the segmentation results. At the same time, parallel designing methods of node allocation, task allocation and load balancing methods are researched. The experiment results show that the parallel method can significantly improve the segmentation speed of 3D medical image.

A segmentation algorithm in 3d medical data is proposed based on boundary model and local character structure in this paper. We found out inner voexls and outer voexls by pre-appointed voxel based on boundary model. And then, boundary voexls are correctly classified into different tissues by their eigenvalues of Hessian matrix based on the local character structure. Only eigenvalues of the boundary voxels are computed, so little time is used compared with other algorithms based on local character structure. It can quickly and effectively realize the segmentation of single tissue.