This paper presents an automatic segmentation of brain lesions from diffusion-weighted magnetic resonance imaging (DW-MRI or DWI) using region growing approach. The lesions are acute infarction, haemorrhage, tumour an...
详细信息
ISBN:
(纸本)9789881925114
This paper presents an automatic segmentation of brain lesions from diffusion-weighted magnetic resonance imaging (DW-MRI or DWI) using region growing approach. The lesions are acute infarction, haemorrhage, tumour and abscess. Region splitting and merging is used to detect the lesion region. Then, histogram thresholding technique is applied to automate the seeds selection. The region is iteratively grown by comparing all unallocated neighbour pixels to the seeds. The difference between pixel's intensity value and the region's mean is used as the similarity measure. Evaluation is made for performance comparison between automatic and manual seeds selection. Overall, automated region growing algorithm provides comparable results with the semi-automatic segmentation.
This paper presents a novel data-adaptive anisotropic filtering technique built on top of an iterative scheme. This new technique can preserve the original significant structures while suppressing noises to the larges...
详细信息
This paper presents a fully automatic segmentation of brain lesions from diffusion-weighted magnetic resonance imaging (DW-MRI or DWI). The lesions are infarction, hemorrhage, tumor and abscess. Pre-processing stage i...
详细信息
This paper presents a fully automatic segmentation of brain lesions from diffusion-weighted magnetic resonance imaging (DW-MRI or DWI). The lesions are infarction, hemorrhage, tumor and abscess. Pre-processing stage is performed for intensity normalization, background removal and intensity enhancement. Then, split and merge algorithm is designed. Several statistical features are discussed and evaluated to select the best feature as homogeneity criteria. Lesions are segmented by merging the homogenous regions according to the selected criteria. This process produces blocky lesion region. Then, histogram thresholding is acquired to automate the seeds selection for region growing process. The region is iteratively grown by comparing all unallocated neighboring pixels to the seeds. The difference between pixel's intensity value and the region's mean is used as the similarity measure. The proposed segmentation technique has been validated by using misclassified area (MA), false positive rate (FPR), false negative rate (FNR), mean absolute percentage error (MAPE) and pixel absolute error ratio (rerr), and compared with previous methods. The result shows that automatic region growing method can successfully segment the lesions and is suitable for analysis and classification of DWI.
Here we present a modeling for electrical stimulation of retinal ganglion cell. This modeling can be used in epiretinal prosthesis to come up with proper electrical stimulation parameters. The model that we present is...
Here we present a modeling for electrical stimulation of retinal ganglion cell. This modeling can be used in epiretinal prosthesis to come up with proper electrical stimulation parameters. The model that we present is a novel one based on the anatomy of the cell. The excitation process of the electrically stimulated retinal cells is simulated in a two step procedure. In the first step the ganglion target cell is represented considering all of its compartments and in a second step the extracellular potential along the neural structure is calculated and finally the membrane voltage response to the applied stimulations is analyzed. A monopolar point electrode was positioned above the cell in an infinite and homogenous environment and the monophasic and biphasic pulses were used as stimulating current. The results show that the responses are in accordance with the values and diagrams of experimental results more than the previous models.
Automatic car plate extraction is one of the interesting research areas in surveillance applications such as traffic control, parking lot and detection of stolen vehicles. This topic is divided in two main parts, firs...
详细信息
ISBN:
(纸本)9781629934563
Automatic car plate extraction is one of the interesting research areas in surveillance applications such as traffic control, parking lot and detection of stolen vehicles. This topic is divided in two main parts, firstly license plate localization, and secondly, license plate characters recognition. In this paper merely the first part is taken into consideration by means of morphological operations and labeling algorithm. Moreover, performance of proposed method is investigated to unveil the ability in extracting of the license plate. Space between characters and also height and width of the license plate are fundamental issues in morphological operations along with dimension of characters in labeling algorithm. Results for this method are promising even in tough conditions.
Shape registration is one of the most challenging problems in computervision and medical imaging. The process is affected by the way the shape is represented and the form of transformation used to move the source sha...
详细信息
Shape registration is one of the most challenging problems in computervision and medical imaging. The process is affected by the way the shape is represented and the form of transformation used to move the source sha...
详细信息
Shape registration is one of the most challenging problems in computervision and medical imaging. The process is affected by the way the shape is represented and the form of transformation used to move the source shape. Our paper handles the elastic shape registration by combining the incremental free form deformation (IFFD) with the point-based registration technique using the sum of least squares method. The iterative closest point (ICP) algorithm is used as a criteria to establish point correspondences in each level of the IFFD framework. The free form deformation (FFD) is well known in the literature and works by forming a lattice of control points that can move and hence deform the domain grid points smoothly and uniformly under some shape constrains. The control lattice resolution is increased step by step to achieve a satisfactory deformation of the source shape to exactly match the target boundaries. Our point-based registration is based on least squares that measure the Euclidean distance between source and target boundaries in addition to the shape constrains. The minimization gives a closed form solution of the lattice control points positions. Promising results will be demonstrated for closed and open shapes and structures. The approach can also work for structures that contain multiple parts without any problems.
Our paper handles the elastic shape registration by combining the incremental free form deformation (IFFD) with the point- based registration technique using the sum of least squares method. The iterative closest poin...
详细信息
Our paper handles the elastic shape registration by combining the incremental free form deformation (IFFD) with the point- based registration technique using the sum of least squares method. The iterative closest point (ICP) algorithm is used as criteria to establish point correspondences in each level of the IFFD framework. The IFFD control lattice resolution is in- creased step by step to achieve a satisfactory deformation of the source shape to exactly match the target boundaries. Our point-based registration is based on least squares that measure the Euclidean distance between source and target boundaries in addition to the shape constrains. The minimization gives a closed form solution of the lattice control points positions. Promising results will be demonstrated for closed and open shapes and structures. The approach can also work for structures that contain multiple parts without any problems.
This paper introduces a fuzzy framework for the simultaneous segmentation and registration in addition to bias field correction of MRI datasets. The framework utilizes prior information which may be available about th...
详细信息
This paper introduces a fuzzy framework for the simultaneous segmentation and registration in addition to bias field correction of MRI datasets. The framework utilizes prior information which may be available about the tissues' mean intensities and tissues' distribution through the datasets. Moreover it works on the given, original image intensities without any logarithmic transformation and thus produces more accurate results and faster performance. The algorithm is evaluated using simulated and real brain MRI data. The results show that the algorithm has indeed improved the segmentation accuracy.
In this paper, we propose a methodology to incorporate 3D shape prior information in multi-view stereo. This is important for applications that deal with specific category of objects. The methodology is based on a new...
详细信息
In this paper, we propose a methodology to incorporate 3D shape prior information in multi-view stereo. This is important for applications that deal with specific category of objects. The methodology is based on a new formulation of a level-set based energy functional. Shape prior model is then embedded in the energy functional to allow the reconstruction of an object with shape variations consistent with the training model examples. Several experiments to evaluate the proposed methodology are presented.
暂无评论