ÀÇ·á ¿µ»óÀº °¡Àå ºü¸£°Ô ¹ßÀüÀÌ µÇ°í ÀÖ´Â ºÐ¾ß ÁßÀÇ ÇÏ³ªÀÌ´Ù. ½ÇÁ¦·Î ÇÑ±¹¿¡ ÀÖ´Â ¸¹Àº ´ëÇÐµéÀÌ ÀÇ·á ¿µ»ó¿¡ °ü½ÉÀ» º¸ÀÌ°í ÀÖÀ¸¸ç FX5800°ú C1060À» Á¶ÇÕÇÑ ½Ã½ºÅÛÀ» ±¸ÃàÇÏ¿© ¿¬±¸¸¦ ÁøÇàÇÏ°í ÀÖ´Ù. ÀÇ·á ¿µ»ó ºÐ¾ß´Â Å©°Ô

1. X-ray¸¦ 3D ¿µ»óÈ ÀÛ¾÷

2. MRIÀÇ 3D ¿µ»ó ÇØ¼®

µî¿¡ Àû¿ëÀÌ µÇ°í ÀÖ´Ù.

**Fast Hardware-Accelerated Volume Rendering of CT Scans**

As CT scanning is a very common medical imaging method, we propose new hardware-based algorithms using GPU (Graphical Processor Unit) programming for rapid visualization. Firstly, 3D volumes are constructed from CT scans. Then volume rendering is used to display anatomical structures via algorithms founded on improved ray casting and 2D textures. Our methods achieve interactive rendering rates and require an ordinary PC with an off-the-shelf graphics card. We expect our approach to be useful to medical practitioners for handling modern, large-scale medical datasets.

**Fast Deformable Registration on the GPU: A CUDA Implementation of Demons**

In the medical imaging field, we need fast deformable registration methods especially in intra-operative settings characterized by their time-critical applications. Image registration studies which are based on Graphics Processing Units (GPUs) provide fast implementations. However, only a small number of these GPU-based studies concentrate on deformable registration. We implemented Demons, a widely used deformable image registration algorithm, on NVIDIA's Quadro FX 5600 GPU with the Compute Unified Device Architecture (CUDA) programming environment. Using our code, we registered 3D CT lung images of patients. Our results show that we achieved the fastest runtime among the available GPU-based Demons implementations. Additionally, regardless of the given dataset size, we provided a factor of 55 speedup over an optimized CPU-based implementation. Hence, this study addresses the need for on-line deformable registration methods in intra-operative settings by providing the fastest and most scalable Demons implementation available to date. In addition, it provides an implementation of a deformable registration algorithm on a GPU, an understudied type of registration in the general-purpose computation on graphics processors (GPGPU) community.

**Sparse Matrix-Vector Multiplication Toolkit for Graphics Processing Units**

Sparse Matrix-Vector Multiplication Toolkit for Graphics Processing Units (SpMV4GPU) is a library optimized for NVIDIA Graphics Processing Units (GPUs). The GPU is fast emerging as the ideal architecture to use as an accelerator in a heterogenous computing environment. Modern GPUs are designed not only for accelerating traditional graphics kernels, but also for general-purpose computationally intensive kernels. The state-of-the art GPUs exhibit very high computational capabilities at a reasonable price. These GPUs also support high-level parallel programming models, for example, NVIDIA's Common Unified Device Architecture (CUDA) or Brook+ from AMD, that enable users to develop parallel applications that use the CPU as the host and the GPU as an accelerator. Sparse Matrix-Vector Multiplication is a core numerical analysis kernel used for a wide range of application domains, such as graphics, data mining, and image processing. SpMV4GPU is a sparse matrix-vector multiplication library optimized for the NVIDIA GPUs. It is developed using the NVIDIA CUDA interfaces, and works on all NVIDIA GPUs that support this library. SpMV4GPU uses the standard sparse matrix storage formats, such as compressed row and column storage formats. It hides the intricacies of GPU programming by using an abstract interface. The SpMV4GPU interface also allows users to provide optional performance hints, and optionally use special storage representations. Experimental evaluation demonstrate that the SpMV library provides two to four times improvement over the equivalent solution provided by the NVIDIA's CUDPP library. While the current implementation of the SpMV code uses the CUDA interfaces, the code can be easily migrated to use the upcoming OpenCL standard. This will allow the SpMV code to execute on a wide range of GPU architectures.

**GPU Acceleration of 2D-DWT Image Compression in MATLAB with CUDA**

This article will present the details about the acceleration of 2D wavelet-based medical data (image) compression on MATLAB with CUDA. It is obvious that the diagnostic materials (mostly as acertain type of image) are increasingly acquired in a digital format. Therefore, common need to daily manipulate huge amount of data brought about the issue of compression within a very less stipulated amount of time. Attention will be given to the acceleration processing flow which exploits the massive parallel computational power offered by the latest NVIDIA graphics processor unit (GPU). It brings a compute device that can be programmed using a C-like language using CUDA, (Compute Unified Device Architecture). In the same time, a number of attractive features can be exploited for a broad class of intensive data parallel computation tasks. The final part of discussion outlines possible directions towards future improvements of compression ratio and processing speed.

**Clinical Evaluation of GPU-Based Cone Beam Computed Tomography**

The use of cone beam computed tomography (CBCT) is growing in the clinical arena due to its ability to provide 3-D information during interventions, its high diagnostic quality (sub-millimeter resolution), and its short scanning times (60 seconds). In many situations, the short scanning time of CBCT is followed by a time consuming 3-D reconstruction. The standard reconstruction algorithm for CBCT data is the filtered backprojection, which for a volume of size 2563 takes up to 25 minutes on a standard system. Recent developments in the area of Graphic Processing Units (GPUs) make it possible to have access to high performance computing solutions at a low cost, allowing for use in applications to many scientific problems. We have implemented an algorithm for 3-D reconstruction of CBCT data using the Compute Unified Device Architecture (CUDA) provided by NVIDIA (NVIDIA Cor., Santa Clara, California),which was executed on a NVIDIA GeForce 8800GT. Our implementation results in improved reconstruction times from on the order of minutes, and perhaps hours, to a matter of seconds, while also giving the clinician the ability to view 3-D volumetric data at higher resolutions. We evaluated our implementation on ten clinical data sets and one phantom data set to observe differences that can occur between CPU and GPU based reconstructions. By using our approach, the computation time for 2563 is reduced from 25 minutes on the CPU to 4.8 seconds on the GPU. The GPU reconstruction time for 5123 is 11.3 seconds, and 10243 is 61.4 seconds.