Current Issue : July - September Volume : 2015 Issue Number : 3 Articles : 6 Articles
Dementia is an evolving challenge in society, and no disease-modifying treatment exists. Diagnosis can be demanding and MR\nimaging may aid as a noninvasive method to increase prediction accuracy. We explored the use of 2D local binary pattern (LBP)\nextracted from FLAIR and T1 MR images of the brain combined with a Random Forest classifier in an attempt to discern patients\nwith Alzheimer�s disease (AD), Lewy body dementia (LBD), and normal controls (NC). Analysis was conducted in areas with white\nmatter lesions (WML) and all of white matter (WM). Results from 10-fold nested cross validation are reported as mean accuracy,\nprecision, and recall with standard deviation in brackets. The best result we achieved was in the two-class problem NC versus AD +\nLBD with total accuracy of 0.98 (0.04). In the three-class problem AD versus LBD versus NC and the two-class problem AD versus\nLBD, we achieved 0.87 (0.08) and 0.74 (0.16), respectively.The performance using 3DT1 images was notably better than when using\nFLAIR images.Theresults fromtheWMregion gave similar results as in theWMLregion. Our study demonstrates that LBP texture\nanalysis in brain MR images can be successfully used for computer based dementia diagnosis....
We describe a new computational approach to edge detection and its application to biomedical images. Our digital algorithm\ntransforms the image by emulating the propagation of light through a physical medium with specific warped diffractive property.\nWe show that the output phase of the transform reveals transitions in image intensity and can be used for edge detection....
Fourier volume rendering (FVR) is a significant visualization technique that has been used widely in digital radiography. As a result\nof its O(N2 log N) time complexity, it provides a faster alternative to spatial domain volume rendering algorithms that are O(N3)\ncomputationally complex. Relying on the Fourier projection-slice theorem, this technique operates on the spectral representation of a\n3D volume instead of processing its spatial representation to generate attenuation-only projections that look like X-ray radiographs.\nDue to the rapid evolution of its underlying architecture, the graphics processing unit (GPU) became an attractive competent\nplatform that can deliver giant computational raw power compared to the central processing unit (CPU) on a per-dollar-basis.\nThe introduction of the compute unified device architecture (CUDA) technology enables embarrassingly-parallel algorithms to\nrun efficiently on CUDA-capable GPU architectures. In this work, a high performance GPU-accelerated implementation of the\nFVR pipeline on CUDA-enabled GPUs is presented. This proposed implementation can achieve a speed-up of 117x compared to\na single-threaded hybrid implementation that uses the CPU and GPU together by taking advantage of executing the rendering\npipeline entirely on recent GPU architectures....
Theincidence of sensorineural hearing loss (SNHL) increased gradually in the past decades.High-resolution computed tomography\n(HRCT) andmagnetic resonance (MR) imaging, as an important part of preimplantation evaluation for children with SNHL, could\nprovide the detailed information about the inner ear, the vestibulocochlear nerve, and the brain, so as to select suitable candidate\nfor cochlear implantation (CI). Brain abnormalities were not rare in the brainMR imaging of SNHL children; however, its influence\non the effect of CI has not been clarified. After retrospectively analyzing the CT and MR imaging of 157 children with SNHL that\naccepted preoperative evaluation fromJune 2011 to February 2013 in our hospital and following them during a period of 14.09�±5.08\nmonths, we found that the white matter change, which might be associated with the history of medical condition, was the most\ncommon brain abnormality. Usually CI was still beneficial to the children with brain abnormalities, and the short-term hearing\nimprovement could be achieved. Further study with more patients and longer follow-up time was needed to confirm our results....
A well-established method for diagnosis of glaucoma is the examination of the optic nerve head based on fundus image as\nglaucomatous patients tend to have larger cup-to-disc ratios. The difficulty of optic segmentation is due to the fuzzy boundaries\nand peripapillary atrophy (PPA). In this paper a novel method for optic nerve head segmentation is proposed. It uses template\nmatching to find the region of interest (ROI). The method of vessel erasing in the ROI is based on PDE inpainting which will make\nthe boundary smoother. A novel optic disc segmentation approach using image texture is explored in this paper. A cluster method\nbased on image texture is employed before the optic disc segmentation step to remove the edge noise such as cup boundary and\nvessels. We replace image force in the snake with image texture and the initial contour of the balloon snake is inside the optic\ndisc to avoid the PPA.The experimental results show the superior performance of the proposed method when compared to some\ntraditional segmentation approaches. An average segmentation dice coefficient of 94% has been obtained....
Medical diagnosis judges the status of polyp fromthe size and the 3D shape of the polyp fromits medical endoscope image.However\nthemedical doctor judges the status empirically fromthe endoscope image and more accurate 3D shape recovery fromits 2Dimage\nhas been demanded to support this judgment. As a method to recover 3D shape with high speed, VBW (Vogel-Breu�Ÿ-Weickert)\nmodel is proposed to recover 3D shape under the condition of point light source illumination and perspective projection. However,\nVBWmodel recovers the relative shape but there is a problem that the shape cannot be recovered with the exact size. Here, shape\nmodification is introduced to recover the exact shape with modification fromthat with VBWmodel. RBF-NN is introduced for the\nmapping between input and output. Input is given as the output of gradient parameters of VBW model for the generated sphere.\nOutput is given as the true gradient parameters of true values of the generated sphere. Learning mapping with NN can modify the\ngradient and the depth can be recovered according to the modified gradient parameters. Performance of the proposed approach is\nconfirmed via computer simulation and real experiment....
Loading....