MIC-GPU: High-Performance Computing for Medical Imaging on Programmable Graphics Hardware (GPU)

Level: Intermediate Length: 4 hours Format: In-Person Lecture Intended Audience: Anyone who is actively involved in implementing computer code for medical imaging applications and desires greater processing speeds will benefit from this course: researchers, students, and engineers. But also managers will obtain a better understanding of the capabilities of the GPU platform for medical imaging. Some prior background with image processing and computer technology will be helpful. Description: Advanced graphics boards have become a standard ingredient in any mid-range and high-end PC, and aside from enabling stunning interactive graphics effects in computer games, their rich programmability allows speedups (over CPU-based code) of 1-2 orders of magnitude also in general-purpose computations. This course explains, in gentle ways, how to exploit this powerful computing platform to accelerate various popular medical imaging applications, such as CT, MRI, image processing, and data visualization. It begins by introducing the basic GPU architecture and its programming model, which establishes a solid understanding on how general computing tasks must be structured and implemented on the GPU to achieve the desired high speedups. Next, it examines a number of standard 2D and 3D medical imaging operators, such as filtering, sampling, statistical analysis, transforms, projectors, etc, and explains how these can be effectively accelerated on the GPU. Finally, it puts this all together by describing the full GPU-accelerated computing pipeline for a representative set of medical imaging applications, such as analytical and iterative CT, MRI, image enhancement chains, and volume visualization. Learning Outcomes: This course will enable you to: - describe the basic architecture and programming model of the GPU - explain the fundamental concepts for effective general-purpose computing on the GPU - design basic GPU programs for general-purpose computing and identify resources to obtain further information - explain how standard operations in medical imaging are accelerated on the GPU - distinguish GPU-acceleration strategies for various computing pipelines in CT, MRI, visualization, and image processing - estimate the GPU-acceleration potential of unexplored medical computing tasks - learn about GPU-code development with the CUDA and OpenCL environments Instructor(s): Klaus Mueller received an MS in biomedical engineering and PhD in computer science from The Ohio State University. He is an associate professor in the Computer Science Department at Stony Brook University,with co-appointments in the Biomedical Engineering and Radiology Departments. His current research interests are medical imaging, high-performance computing, visual analytics, and computer vision. He won the US National Science Foundation CAREER award in 2001 and the SUNY Chancellor's Award for Excellence in Scholarship and Creative Activity in 2011. He served as a co-chair at various conferences, including IEEE Visualization, the Volume Graphics Symposium, and the Fully 3D Workshop on High-Performance Image Reconstruction. He has authored and co-authored over 140 peer-reviewed journal and conference papers, and participated in 15 tutorials at international conferences on visualization and medical imaging topics. He is a senior member of the IEEE and the IEEE Computer Society. http://www.cs.sunysb.edu/~mueller Sungsoon Ha is a PhD student in computer science department at Stony Brook University working under the supervision of Prof. Klaus Mueller. Before joining the PhD program, he received his Bachelor's degree in Electrical Engineering from the Stony Brook University. His main research interests are medical imaging, computer vision, high-performance computing (GPGPU) and visualization. He is particularly interested in low-dose CT reconstruction/restoration with Big Data, CT metal artifact reduction and developing GPU-accelerated statistical iterative CT reconstruction algorithm. Currently, he is a research assistant in the Visual Analytics Imaging (VAI) Laboratory and more detail information can be found at: www.cs.sunysb.edu/~sunha. Event: SPIE Medical Imaging 2017 Course Held: 11 February 2017