Ijesrt International Journal of Engineering Sciences & Research Technology Fast Medical Image Denoising Using Latest Gpgpu Technology (original) (raw)

Compressing of Magnetic Resonance Images with Cuda

International Journal of Trend in Scientific Research and Development

One of the most important areas that use image processing is the health sector. In order to detect some diseases, the need to visualize a certain part of the patient's body using medical imaging devices has emerged. This field in the health sector is the Radiology department. MR, Tomography, Ultrasound, X-ray, Echocardiography. Because of the importance of time in the health sector, GPU technologies are a technology that should be used in hospitals. Medical MRI images showed that the unused areas (NON ROI) occupy a large area and this unnecessary area in the image could reduce the image size significantly. In this method developed with CUDA, the ROI (Region of Interest) region within the Medical MR images is determined by sending a 3X3 Kirsch filter matrix t the CUDA cores, and the NON-ROI region is extracted with CUDA from the image. It is then compressed with a new compression method developed. As a result of this method; The parallel application with CUDA solves the problem 34 times faster than the sequential application for each image, while the compressed image takes up 90% less space than the original image size; it takes 40% less space than the compressed size of the original image.

Medical Image Denoising Using Bilateral Filter

International Journal of Image, Graphics and Signal Processing, 2012

Medical image processing is used for the diagnosis of diseases by the physicians or radiologists. Noise is introduced to the medical images due to various factors in medical imaging. Noise corrupts the medical images and the quality of the images degrades. This degradation includes suppression of edges, structural details, blurring boundaries etc. To diagnose diseases edge and details preservation are very important. Medical image denoising can help the physicians to diagnose the diseases. Medical images include MRI, CT scan, x-ray images, ultrasound images etc. In this paper we implemented bilateral filtering for medical image denoising. Its formulation & implementation are easy but the performance of bilateral filter depends upon its parameter. Therefore for obtaining the optimum result parameter must be estimated. We have applied bilateral filtering on medical images which are corrupted by additive white Gaussian noise with different values of variances. It is a nonlinear and local technique that preserves the features while smoothing the images. It removes the additive white Gaussian noise effectively but its performance is poor in removing salt and pepper noise.

ROI Determination and Compression in MRI Using Gradient Method with CUDA

International Journal of Trend in Scientific Research and Development, 2018

Due to the large use of MRI in hospitals, large storage areas are needed to store these images. Also, if you want to access these images over the system repeatedly, a large bandwidth is required. To solve this problem, it will be necessary to compress and store the medical imaging system quickly and without disruption. It has been seen that in the studies made on MRIs, the non-used regions (NON-ROI) occupy a large space and the image size can be reduced significantly when the unnecessary area in the image is cleaned. In this method developed with CUDA, the region of interest (ROI) in the MRI is detected by sending a 3x3 Kirsch filter matrix to the CUDA cores and the NON-ROI region is extracted from the image with CUDA. These operations are first executed by the serial application on CPU, then by a parallel application on GPU. As a result, the application running on the GPU produced 34 times faster results than the application on the CPU. When images are compressed with this new improved method, it takes up 89% less than the original image size and 15% less than the original compressed image.

Survey of using GPU CUDA programming model in medical image analysis

A B S T R A C T With the technology development of medical industry, processing data is expanding rapidly and computation time also increases due to many factors like 3D, 4D treatment planning, the increasing sophistication of MRI pulse sequences and the growing complexity of algorithms. Graphics processing unit (GPU) addresses these problems and gives the solutions for using their features such as, high computation throughput, high memory bandwidth, support for floating-point arithmetic and low cost. Compute unified device architecture (CUDA) is a popular GPU programming model introduced by NVIDIA for parallel computing. This review paper briefly discusses the need of GPU CUDA computing in the medical image analysis. The GPU performances of existing algorithms are analyzed and the computational gain is discussed. A few open issues, hardware configurations and optimization principles of existing methods are discussed. This survey concludes the few optimization techniques with the medical imaging algorithms on GPU. Finally, limitation and future scope of GPU programming are discussed. 1. Introduction Computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography (PET) and ultrasound are famous medical modalities that produce the 2D, 3D and 4D types of medical images which are guiding the diagnosis process and treatment planning. The medical image processing and analysis are computationally expensive while medical imaging data dimension increasing [1]. The conventional CPU with limited multi-core is not sufficient to process these types of huge data. Graphics processing unit (GPU) is a new technology capable for finding out solutions to the computational problems in all the engineering and medical fields. In the medical industry, GPU is more suitable for processing the higher dimension data. GPU computation has provided a huge edge over the central processing units (CPU) with respect to computation speed. GPU is highly parallel, multithread, multiple core processors and has high memory bandwidth to give the solution to the computational problems [2]. The main reason for the evolution of powerful GPUs is the constant demand for greater realism in computer games. During the past few decades, the computational performance of GPUs has increased much more quickly than that of conventional CPUs. Hence it plays a major role in the field of modern industrial research and development. GPU has already achieved a significant speed (2x-1000x) than CPU implementation on various fields [3] [4] [5]. GPU is well suitable to implement the program execution with the different data elements. This process is called as data parallelism. Data parallelism is maps data elements to parallel threads available in GPU [6]. Data parallelism gives high gains in independent processes between data elements. The prime areas of data parallelism are 3D rendering, stereo vision, pattern recognition, image, video and medical industry applications. A large performance gap occurs between GPU and general purpose multi-core CPU. Architectural level comparison of CPU and GPU are given in Fig. 1. The design of a CPU is optimized for sequential programming. It makes use of sophisticated control logic to allow instructions from a single thread of execution to execute in parallel or even out of their sequential order while maintaining the appearance of sequential execution. Modern CPU microprocessors typically have four large processor cores designed to deliver strong sequential code performance but not enough to process the huge data. A basic model of GPU has large number of processor cores, ALU's, control units and various types of memories. In general, heterogeneous CPU and GPU computation is appreciable instead of standalone CPU or GPU implementation. The dependent processes are recommended in CPU and the independent processes can be accelerated by the GPU. GPU with high amount of threads give better performance. This paper reviews the implication of GPU programming model in medical image analysis and illustrated some applications with examples. The general framework of medical image analysis pipeline is given in Fig. 2. The computational complexities of all these fields are increasing

A Volume of Medical Images Reconstruction on GPGPU Environment

An image before visualization the volume of data sets has to be decompressed because that has to be stored in the compressed format, so every medical imaging system must adopt a compression technique. The process of decompression takes a long time, so we are introducing a boosting method for medical volume decompression using General-Purpose Graphics Processing Units (GPGPU). This is supposed to use parallel processing on GPU architecture owing to that it's acquired less time for decompression. We improved the decompression method by introducing the Embedded Zero-tree Wavelet (EZW) technique to render the volume of images on the GPU environment. Finally, this method allows selective decompression in an alignment with the restore volume visualization and volume of additional decompression through it to obtain a better performance.

GPU based Parallel Computing Approach for Accelerating Image Filters

Graphics processing Unit (GPU) is a dedicated parallel processor optimized for accelerating graphical computations. GPU found wide range of desktops, laptops, supercomputers and mobile also. This paper focused on simple parallel computing approach for filters in images to use graphics card for computation as an alternate of Central Processing Unit (CPU).

Towards on high performance computing of medical imaging based on graphical processing units

2013 15th International Conference on Advanced Computing Technologies (ICACT), 2013

The Design of GPU(Graphical Processing Unit) will well suitable for express the data parallel computations because GPU will specialized for parallel and today's digital images in medical are huge volume of collections in every day, however medical imaging produces demand to improve the medical diagnosis and procedures. This survey is provide graphical processing computations and hardware require to compute and give better information for diagnosis of Cancer Treatment using Radiation Therapy.It is important techniques to increase quality of medical image data clinically under pressure to make enriched data and improve accurate treatment and decrease the complications .

Denoising Volumetric Data on Gpu

Proceedings of the International Conference on Imaging Theory and Applications and International Conference on Information Visualization Theory and Applications, 2011

Volumetric data is currently gradually being used more and more in everyday aspect of our lives. Processing such data is computationally expensive and until now more sophisticated algorithms could not be used. The possibilities of processing such data have considerably widened since the increase of parallel computational power in modern GPUs. We present a novel scheme for running a nonlocal means denoising algorithm on a commodity-grade GPU. The speedup is considerable, shortening the time needed for denoise one abdominal CT scan in minutes instead of hours without compromising the result quality. Such approach allows for example lowering the radiation doses for patients being examined with a CT scan.

MEDICAL IMAGING COMPUTING BASED ON GRAPHICAL PROCESSING UNITS FOR HIGH PERFORMANCE COMPUTING

The Design of GPU(Graphical Processing Unit) will well suitable for express the data parallel computations because GPU will specialized for parallel and today's digital images in medical are huge volume of collections in every day, however medical imaging produces demand to improve the medical diagnosis and procedures. This survey is provide graphical processing computations and hardware require to compute and give better information for diagnosis of Cancer Treatment using Radiation Therapy. It is important techniques to increase quality of medical image data clinically under pressure to make enriched data and improve accurate treatment and decrease the complications.

OPTIMIZATION COMPUTATION ON MRI MEDICAL IMAGES USING ZERO PADDING TECHNIQUE USING GPGPU

This Research aims to compare the execution time of processing raw data (K-Space raw data) into images on CPUs that are processed in serial and processing on GPU processed in parallel. There is one method on the serial implementation of the CPU and there are four implementations of GPU Parallel. The four parallel implementations on GPU are Parallel CUDA I, Parallel OPENCL I, Parallel CUDA II, and Parallel OPENCL II. In addition to the variable execution time, there are also variables of the output image matrix size, the variable number of slices, and the variable number of threads. The results of the serial implementation of CPU and GPU Parallel indicate the larger the size of the output image matrix and the greater the number of slices, the increased acceleration (the result of comparison of serial CPU implementation and GPU Parallel implementation) is greater. If the Serial CPU implementation is compared to the GPU Parallel implementation, GPU Parallel implementation is 4.17 times faster than the Serial CPU implementation, when the output image matrix size is 2048x2048 and the number of processed slices is equal to 4 slices. This shows that parallel implementations are perfect for large data processing.