Performance of Medical Image Processing Algorithms Implemented in CUDA running on GPU based Machine

Abstract

Abstract-This paper illustrates the design and performance evaluation of few algorithms used for analysing the medical image volumes on the massive parallel graphics processing unit (GPU) with compute unified device architecture (CUDA). These algorithms are selected from the general framework, devised for computer aided diagnostic (CAD) system. The CAD system used for analysing large medical image datasets are usually a pipeline processing that includes a variety of image processing operations. A MRI scanner captures the 3D human head into a series of 2D images. Considerable time spent in pre and post processing of these images. Noise filters, segmentation, image diffusion and enhancement are few such methods. The algorithms are chosen for study requires local information, available in few pixels or global information available in the entire image. These problems are best candidates for GPU implementation, since the parallelism is naturally provided by the proposed Per-Pixel Threading (PPT) or Per-Slice Threading (PST) operations. In this paper implement the algorithms for adaptive filtering, anisotropic diffusion, bilateral filtering, non-local means (NLM) filtering, K-Means segmentation and feature extraction in 1536 core's NVIDIA GPU and estimated the speed up gained. Our experiments show that the GPU based implementation achieved typical speedup values in the range of 3-338 times compared to conventional central processing unit (CPU) processor in PPT model and up to 30 times in PST model.

Medical Image Segmentation Using a Combination of Lattice Boltzmann Method and Fuzzy Clustering Based on GPU CUDA Parallel Processing

“…Based on this table, it can be seen that the use of parallel programming with GPU CUDA can increase the speed significantly, being able to be 39.22 times faster than serial programming with a CPU. The results of this study are the results of Kalaiselvi et al [26] and Chang et al [33]. Improving image resolution also increases the execution time, but the speedup also increases.…”

“…Kumar et al proposed a joint LSM and LBM-based approach for histogram thresholding in image segmentation [25]. Kalaiselvi et al presented medical image processing algorithms implemented in CUDA running on GPU-based Machines [26], and Huang and Li use CUDA to accelerate in parallel computation [27].…”

Efficiently compressing 3D medical images for teleinterventions via CNNs and anisotropic diffusion

“…In this study, it requires 34.7 [32.4–36.8] seconds using the CPU to diffuse a 3D CT image of around 90 slices (see Table II). Yet, according to Kalaiselvi (2018), 71 anisotropic diffusion filters can be sped up by 1–2 orders of magnitude when they are implemented on a modern GPU (such as the NVIDIA QUADRO K5000). Furthermore, Wei et.…”

Accelerating Training of Deep Neural Networks on GPU using CUDA

“…They have developed parallel programs for sorting the data and compared the performance with the sequential implementation and found that the reduced execution time with GPU implementation. T. Kalaiselvi et al have proposed Per-Pixel Threading (PPT) and Per-Slice Threading (PST) and implemented some of the advanced image pre-processing algorithms for accelerating the computer aided diagnosis (CAD) systems in MRI volume analysis [17]. Authors have collected the image dataset from Whole Brain Atlas (WBA) maintained by Harvard Medical School and used for testing purpose.…”