Accelerating compute intensive medical imaging segmentation algorithms using hybrid CPU-GPU implementations

Alsmirat, Mohammad A.; Jararweh, Yaser; Al‐Ayyoub, Mahmoud; Shehab, Mohammed A.; Gupta, Brij B.

doi:10.1007/s11042-016-3884-2

Cited by 66 publications

(16 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These deep learning frameworks have been widely adopted due to their use in well-documented interfaces to Python and MATLAB. Furthermore, these frameworks provide heterogeneous computing implementations [67] (e.g., CPU-GPU), and are also available through platformas-a-service (PaaS) cloud services (e.g., Nvidia GPU Cloud supporting Nvidia DIGITS [68], Amazon Elastic Compute Cloud (EC2), Google Cloud, Microsoft Azure) that also facilitate an off the shelf solution to the computationally intensive processes that are often involved.…”

Section: Deep Learningmentioning

confidence: 99%

Radiogenomics for Precision Medicine With a Big Data Analytics Perspective

Panayides

Pattichis

Leandrou

et al. 2019

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Precision medicine promises better healthcare delivery by improving clinical practice. Using evidencebased substratification of patients, the objective is to achieve better prognosis, diagnosis, and treatment that will transform existing clinical pathways toward optimizing care for the specific needs of each patient. The wealth of today's healthcare data, often characterized as big data, provides invaluable resources toward new knowledge discovery that has the potential to advance precision medicine. The latter requires interdisciplinary efforts that will capitalize the information, know-how, and medical data of newly formed groups fusing different backgrounds and expertise. The objective of this paper is to provide insights with respect to the state-of-the-art research in precision medicine. More specifically, our goal is to highlight the fundamental challenges in emerging fields of radiomics and radiogenomics by reviewing the case studies of Cancer and Alzheimer's disease, describe the computational challenges from a big data analytics perspective, and discuss standardization and open data initiatives that will facilitate the adoption of precision medicine methods and practices.

show abstract

Section: Deep Learningmentioning

confidence: 99%

Radiogenomics for Precision Medicine With a Big Data Analytics Perspective

Panayides

Pattichis

Leandrou

et al. 2019

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

show abstract

“…19 Recently, many research works have been using GPUs to accelerate applications and algorithms in many fields such as image processing. 12,[19][20][21][22] Some studies investigated the GPU capabilities to decrease the execution time of image processing focusing on medical image processing as shown in other works. 21,22,23 Most of previous studies used GPUs technology in medical image processing reported a significant acceleration of existing image analysis.…”

Section: Image Segmentation Using Gpusmentioning

confidence: 99%

Accelerating white blood cells image segmentation using GPUs

Baker

Alsmirat

Balhaf

et al. 2019

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

White Blood Cell (WBC) segmentation is one of the important topics in the medical image processing field. Many researchers proposed several clustering approaches to segment WBC from blood smear microscopic images. However, a fast and robust segmentation of WBCs is still a challenging task. In this work, we propose parallel algorithms that utilize the parallelism capabilities of the Graphics Processing Units (GPUs) to accelerate the segmentation of WBC from microscopic images. In this research, we implement the main image segmentation clustering algorithms using one thread that we run on a single CPU (sequential implementation) and using multiple threads that we run on both the CPU and the GPU (hybrid CPU-GPU). We focus our work on the most common four segmentation algorithms: Standard K-means (SKM), Adaptive K-means (AKM), Fuzzy C-means (FCM), and Fuzzy Possibilistic C-means (FPCM). We implement these algorithms and the pre-processing steps for WBC image segmentation in CUDA programming to take the advantages of the large number of cores in GPUs. In this work, our hybrid implementation accelerated the four studied sequential algorithms by 4X, 3.8X, 3.4X, and 3.4X, respectively, without affecting WBC segmentation quality.

show abstract

“…In the field of medical imaging, GPUs have been used in several computational domains (Eklund et al , 2013), including image reconstruction (Stone et al , 2008; Uecker et al , 2015) image segmentation (Smistad et al , 2015; Alsmirat et al , 2017), image registration (Shamonin, 2014), and in the analysis of functional MRI (Eklund et al. , 2014) and diffusion MRI data (Xu et al , 2012; Hernández et al , 2013; Chang et al , 2014; Hernandez-Fernandez et al , 2016; Harms et al , 2017).…”

Section: Introductionmentioning

confidence: 99%

Using GPUs to accelerate computational diffusion MRI: From microstructure estimation to tractography and connectomes

et al. 2019

View full text Add to dashboard Cite

The great potential of computational diffusion MRI (dMRI) relies on indirect inference of tissue microstructure and brain connections, since modelling and tractography frameworks map diffusion measurements to neuroanatomical features. This mapping however can be computationally highly expensive, particularly given the trend of increasing dataset sizes and the complexity in biophysical modelling. Limitations on computing resources can restrict data exploration and methodology development. A step forward is to take advantage of the computational power offered by recent parallel computing architectures, especially Graphics Processing Units (GPUs). GPUs are massive parallel processors that offer trillions of floating point operations per second, and have made possible the solution of computationally-intensive scientific problems that were intractable before. However, they are not inherently suited for all problems. Here, we present two different frameworks for accelerating dMRI computations using GPUs that cover the most typical dMRI applications: a framework for performing biophysical modelling and microstructure estimation, and a second framework for performing tractography and long-range connectivity estimation. The former provides a front-end and automatically generates a GPU executable file from a user-specified biophysical model, allowing accelerated non-linear model fitting in both deterministic and stochastic ways (Bayesian inference). The latter performs probabilistic tractography, it can generate whole-brain connectomes and supports new functionality for imposing anatomical constraints, such as inherent consideration of surface meshes (GIFTI files) along with volumetric images. We validate the frameworks against well-established CPU-based implementations and we show that despite the very different challenges for parallelising these problems, a single GPU achieves better performances than 200 CPU cores thanks to our parallel designs.

show abstract

Accelerating compute intensive medical imaging segmentation algorithms using hybrid CPU-GPU implementations

Cited by 66 publications

References 20 publications

Radiogenomics for Precision Medicine With a Big Data Analytics Perspective

Radiogenomics for Precision Medicine With a Big Data Analytics Perspective

Accelerating white blood cells image segmentation using GPUs

Using GPUs to accelerate computational diffusion MRI: From microstructure estimation to tractography and connectomes

Contact Info

Product

Resources

About