using gpus
play

using GPUs Presenter Dr.Hammad Omer Assistant Professor Group - PowerPoint PPT Presentation

Jul 02, 2023 •482 likes •1.47k views

2019 Accelerating Magnetic Resonance Imaging (MRI) using GPUs Presenter Dr.Hammad Omer Assistant Professor Group Lead: Medical Image Processing Research Group (MIPRG) (www.miprg.com) COMSATS University Islamabad (Pakistan) Thursday, March

  1. 2019 Accelerating Magnetic Resonance Imaging (MRI) using GPUs Presenter Dr.Hammad Omer Assistant Professor Group Lead: Medical Image Processing Research Group (MIPRG) (www.miprg.com) COMSATS University Islamabad (Pakistan) Thursday, March 21, 2019 1

  2. Thursday, March 21, 2019 Outline ► Overview of Magnetic Resonance Imaging (MRI) ► GPU based Advance MR Image Reconstruction ● GPU based GRAPPA Reconstruction using CUDA ● GPU based SENSE Reconstruction using CUDA ● GPU based Gridding using CUDA ► Magnetic Resonance Finger Printing (MRF) ● GPU based MRF using CUDA ► Acknowledgements 2

  3. Thursday, March 21, 2019 What is MRI ? Outline ► MIPRG at Glance ► Overview ● Safe and painless diagnostic procedure ► What is MRI? ● Excellent soft tissue contrast ► MRI Hardware ● No need to change the position of the ► How MRI works? patient ► MR Image Formation ● Non-invasive ► Limitations in conventional Human head MRI ● Diagnoses & monitors treatments such as (Coronal axis) ► Parallel MRI ►  Heart problems Magnetic Resonance Finger printing  Blockage or enlargement of blood ► Acknowledgements vessels  Lungs  Diseases of the liver such as cirrhosis Human head (sagittal axis)  Tumors and other cancer related abnormalities 3

  4. Thursday, March 21, 2019 MRI Hardware Outline ► MIPRG at Glance ► Overview ● Magnets ► What is MRI?  Permanent Magnets ► MRI Hardware  Resistive Magnets ► How MRI works?  Super Conducting Magnets ► MR Image Formation ● RF Coils ► Limitations in conventional MRI  Surface coils MAGNETOM Skyra 3T (Siemens ) ► Parallel MRI  Body coils ► Magnetic Resonance Finger  Head coils printing ► Acknowledgements ● Gradient Coils  Induce non-linear change in the magnetic field 4

  5. Thursday, March 21, 2019 How MRI works Outline ► MIPRG at Glance ► Overview RF-RX ► What is MRI? ► MRI Hardware ► How MRI works? ► MR Image Formation ► Limitations in conventional RF - TX MRI ► Parallel MRI Magnetic Filed ► Magnetic Resonance Finger printing ► Acknowledgements Fourier Transform Image NMR Signal 5

  6. Thursday, March 21, 2019 MR Image Formation Outline ► MIPRG at Glance ● MRI Pulse Sequence and Data Acquisition ► Overview ► What is MRI? Basic Gradient-Echo Pulse Sequence k -Space ► MRI Hardware + 𝒍 𝒛 ► How MRI works? ► MR Image Formation ► Limitations in conventional + 𝒍 𝐲 - 𝒍 𝒚 MRI ► Parallel MRI ► Magnetic Resonance Finger printing ► Acknowledgements - 𝒍 𝐳 𝒍 𝒛 = Phase encoding Direction 𝒍 𝒚 = Frequency encoding Direction 6

  7. Thursday, March 21, 2019 MR Image Formation Outline ► MIPRG at Glance ● MRI Pulse Sequence and Data Acquisition ► Overview ► What is MRI? Basic Gradient-Echo Pulse Sequence k -Space ► MRI Hardware + 𝒍 𝒛 ► How MRI works? ► MR Image Formation ► Limitations in conventional + 𝒍 𝐲 - 𝒍 𝒚 MRI ► Parallel MRI ► Magnetic Resonance Finger printing ► Acknowledgements - 𝒍 𝐳 𝒍 𝒛 = Phase encoding Direction 𝒍 𝒚 = Frequency encoding Direction 7

  8. Thursday, March 21, 2019 MR Image Formation Outline ► MIPRG at Glance ● MRI Pulse Sequence and Data Acquisition ► Overview ► What is MRI? Basic Gradient-Echo Pulse Sequence k -Space ► MRI Hardware + 𝒍 𝒛 ► How MRI works? ► MR Image Formation ► Limitations in conventional + 𝒍 𝐲 - 𝒍 𝒚 MRI ► Parallel MRI ► Magnetic Resonance Finger printing ► Acknowledgements - 𝒍 𝐳 𝒍 𝒛 = Phase encoding Direction 𝒍 𝒚 = Frequency encoding Direction 8

  9. Thursday, March 21, 2019 MR Image Formation Outline ► MIPRG at Glance ● MRI Pulse Sequence and Data Acquisition ► Overview ► What is MRI? Basic Gradient-Echo Pulse Sequence k -Space ► MRI Hardware + 𝒍 𝒛 ► How MRI works? ► MR Image Formation ► Limitations in conventional + 𝒍 𝐲 - 𝒍 𝒚 MRI ► Parallel MRI ► Magnetic Resonance Finger printing ► Acknowledgements - 𝒍 𝐳 𝒍 𝒛 = Phase encoding Direction 𝒍 𝒚 = Frequency encoding Direction 9

  10. Thursday, March 21, 2019 MR Image Formation Outline ► MIPRG at Glance ● MRI Pulse Sequence and Data Acquisition ► Overview ► What is MRI? Basic Gradient-Echo Pulse Sequence k -Space ► MRI Hardware + 𝒍 𝒛 ► How MRI works? ► MR Image Formation ► Limitations in conventional + 𝒍 𝐲 - 𝒍 𝒚 MRI ► Parallel MRI ► Magnetic Resonance Finger printing ► Acknowledgements - 𝒍 𝐳 𝒍 𝒛 = Phase encoding Direction 𝒍 𝒚 = Frequency encoding Direction 10

  11. Thursday, March 21, 2019 MR Image Formation Outline ► MIPRG at Glance ● MRI Pulse Sequence and Data Acquisition ► Overview ► What is MRI? Basic Gradient-Echo Pulse Sequence k -Space ► MRI Hardware + 𝒍 𝒛 ► How MRI works? ► MR Image Formation ► Limitations in conventional + 𝒍 𝐲 - 𝒍 𝒚 MRI ► Parallel MRI ► Magnetic Resonance Finger printing ► Acknowledgements - 𝒍 𝐳 𝒍 𝒛 = Phase encoding Direction 𝒍 𝒚 = Frequency encoding Direction 11

  12. Thursday, March 21, 2019 MR Image Formation Outline ► MIPRG at Glance ● MRI Pulse Sequence and Data Acquisition ► Overview ► What is MRI? Basic Gradient-Echo Pulse Sequence k -Space ► MRI Hardware + 𝒍 𝒛 ► How MRI works? ► MR Image Formation ► Limitations in conventional + 𝒍 𝐲 - 𝒍 𝒚 MRI ► Parallel MRI ► Magnetic Resonance Finger printing ► Acknowledgements - 𝒍 𝐳 𝒍 𝒛 = Phase encoding Direction 𝒍 𝒚 = Frequency encoding Direction 12

  13. Thursday, March 21, 2019 MR Image Formation Outline ► MIPRG at Glance ● MRI Pulse Sequence and Data Acquisition ► Overview ► What is MRI? Basic Gradient-Echo Pulse Sequence k -Space ► MRI Hardware + 𝒍 𝒛 ► How MRI works? ► MR Image Formation ► Limitations in conventional + 𝒍 𝐲 - 𝒍 𝒚 MRI ► Parallel MRI ► Magnetic Resonance Finger printing ► Acknowledgements - 𝒍 𝐳 𝒍 𝒛 = Phase encoding Direction 𝒍 𝒚 = Frequency encoding Direction 13

  14. Thursday, March 21, 2019 MR Image Formation Outline ► MIPRG at Glance ● MRI Pulse Sequence and Data Acquisition ► Overview ► What is MRI? Basic Gradient-Echo Pulse Sequence k -Space ► MRI Hardware + 𝒍 𝒛 ► How MRI works? ► MR Image Formation ► Limitations in conventional + 𝒍 𝐲 - 𝒍 𝒚 MRI ► Parallel MRI ► Magnetic Resonance Finger printing ► Acknowledgements - 𝒍 𝐳 𝒍 𝒛 = Phase encoding Direction 𝒍 𝒚 = Frequency encoding Direction 14

  15. Thursday, March 21, 2019 MR Image Formation Outline ► MIPRG at Glance ● MR Pulse Sequence and Data Acquisition ► Overview ► The Total acquisition time ( 𝑈 What is MRI? 𝐵 ) (fully sampled k -space) ► MRI Hardware 𝑼 𝑩 = 𝑼 𝑺 × 𝑶 𝒛 ► How MRI works? Where, ► MR Image 𝑼 𝑺 = Time required to collect a single line of k -space Formation 𝑶 𝒛 = Total number of PE lines that must be acquired ► Limitations in conventional MRI ► Parallel MRI ► Magnetic Resonance Finger printing FFT ► Acknowledgements 15

  16. Thursday, March 21, 2019 MR Image Formation Outline ► MIPRG at Glance ● Image Resolution and Contrast ► Overview ∆𝑦 ∆𝑙 𝑦 ► What is MRI? ∆𝑙 𝑧 ► ∆𝑧 MRI Hardware ► How MRI works? ► MR Image Fourier Transform Formation ► Limitations in conventional MRI ► Parallel MRI ► Magnetic Resonance Finger printing ► Acknowledgements 16

  17. Friday, March 15, 2019 9 MR Image Formation Outline ► MIPRG at Glance ● k -space sampling trajectories ► Overview ► What is MRI? ► MRI Hardware ► How MRI works? ► MR Image Formation ► Limitations in conventional MRI ► Parallel MRI ► Magnetic Resonance Finger printing ► Acknowledgements Thursday, March 21, 2019 17

  18. Thursday, March 21, 2019 Limitations in Conventional MRI Outline ► MIPRG at Glance ● Major Limitations ► Overview ► What is MRI?  Scan duration of conventional MRI (30 to 40 mins) ► MRI Hardware ► How MRI works?  Too expensive (typically £350-£500 per hour) ► MR Image Formation ► Limitations in  Long Breath hold (abdominal imaging) conventional MRI  Moving structures (e.g. heart) ► Parallel MRI ► Magnetic Resonance Finger  printing Contrast changes( Flowing blood ) ► Acknowledgements 18

  19. Thursday, March 21, 2019 Parallel MRI Outline ► MPIRG at Glance ● Key properties of pMRI techniques ● Multichannel receiver coils ► Overview 1. Acceleration factors ● Reduce acquisition time ► Parallel MRI 2. Reconstruction accuracy ● Advanced pMRI Techniques ► Magnetic Resonance Finger 3. Reconstruction time printing (GRAPPA, SENSE etc.) ► Acknowledgements Parallel Imaging using multi-channel receiver coils Example of 4-channe receiver coil 19

  20. Thursday, March 21, 2019 Parallel MRI Outline ► MPIRG at Glance ► Overview Image based reconstruction ► Parallel MRI ► Magnetic Resonance Finger printing ► Acknowledgements k -space based reconstruction 20

Recommend

Why use GPUs for graph processing? FOSDEM 2020 2 GPUs and Graphs Graphs GPUs Found

Why use GPUs for graph processing? FOSDEM 2020 2 GPUs and Graphs Graphs GPUs Found

Gunrock High-Performance Graph Analytics for the GPU Muhammad Osama University of California, Davis Why use GPUs for graph processing? FOSDEM 2020 2 GPUs and Graphs Graphs GPUs Found everywhere Found everywhere Road &

560 views • 23 slides
Scott Le Grand Some Things Never Change (GPUs vs the World) How Best to Exploit GPUs

Scott Le Grand Some Things Never Change (GPUs vs the World) How Best to Exploit GPUs

Scott Le Grand Some Things Never Change (GPUs vs the World) How Best to Exploit GPUs Molecular Dynamics or Matrix Factorization? Determinism and Numerical Stability Dynamic Range for both MD and NNs Latest AMBER PME Numbers

1.18k views • 90 slides
Unleashing the Power of GPUs over the Web Vishal Vaidyanathan Royal Caliber LLC GPUs are

Unleashing the Power of GPUs over the Web Vishal Vaidyanathan Royal Caliber LLC GPUs are

Unleashing the Power of GPUs over the Web Vishal Vaidyanathan Royal Caliber LLC GPUs are great... high compute throughput increasingly energy efficient high density but? http://onu.io

639 views • 16 slides
Clusters of GPUs Michael LeBeane mlebeane@utexas.edu Advisor : Lizy K. John Problem Statement

Clusters of GPUs Michael LeBeane mlebeane@utexas.edu Advisor : Lizy K. John Problem Statement

PhD Defense Optimizing Communication for Clusters of GPUs Michael LeBeane mlebeane@utexas.edu Advisor : Lizy K. John Problem Statement GPUs and Networks in the Wild GPUs are everywhere in HPC, Big Data, Machine Learning, and beyond

1.07k views • 61 slides
MD5 Chosen-Prefix Collisions on GPUs Marc Bevand m.bevand@gmail.com marc.bevand@rapid7.com

MD5 Chosen-Prefix Collisions on GPUs Marc Bevand m.bevand@gmail.com marc.bevand@rapid7.com

MD5 Chosen-Prefix Collisions on GPUs Marc Bevand m.bevand@gmail.com marc.bevand@rapid7.com Agenda MD5 on GPUs Dec 2008: rogue CA certificate on PS3 cluster MD5 birthday search Results & performance MD5 on GPUs MD5 is

448 views • 18 slides
(Toward) Radiative transfer on AMR with GPUs Dominique Aubert Universit de Strasbourg

(Toward) Radiative transfer on AMR with GPUs Dominique Aubert Universit de Strasbourg

(Toward) Radiative transfer on AMR with GPUs Dominique Aubert Universit de Strasbourg Austin, TX, 14.12.12 jeudi 13 dcembre 2012 A few words about GPUs Cache and control replaced by calculation units Large number of

500 views • 31 slides
Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice

Deep Learning on GPUs March 2016 What is Deep Learning? GPUs and DL AGENDA DL in practice Scaling up DL 2 What is Deep Learning? 3 DEEP LEARNING EVERYWHERE INTERNET & CLOUD MEDICINE & BIOLOGY SECURITY & DEFENSE MEDIA &

1.45k views • 39 slides
Understanding The Security of Discrete GPUs Zhiting Zhu 1 , Sangman Kim 1 , Yuri Rozhanski 2 ,

Understanding The Security of Discrete GPUs Zhiting Zhu 1 , Sangman Kim 1 , Yuri Rozhanski 2 ,

Understanding The Security of Discrete GPUs Zhiting Zhu 1 , Sangman Kim 1 , Yuri Rozhanski 2 , Yige Hu 1 , Emmett Witchel 1 , Mark Silberstein 2 1.The University of Texas at Austin 2.Technion-Israel Institute of Technology Outline Can GPUs

869 views • 60 slides
Full Virtualization for GPUs Reconsidered Revisit -- Suzuki, Yusuke, et al. GPUvm: Why not

Full Virtualization for GPUs Reconsidered Revisit -- Suzuki, Yusuke, et al. GPUvm: Why not

Full Virtualization for GPUs Reconsidered Revisit -- Suzuki, Yusuke, et al. GPUvm: Why not virtualizing GPUs at the hypervisor?. USENIX ATC 14. Hangchen Yu 1 , Christopher J. Rossbach 1,2 1 The University of Texas at Austin 2 VMware

880 views • 40 slides
Efficiency of general Krylov methods on GPUs An experimental study H. Anzt, M. Kreutzer, M.

Efficiency of general Krylov methods on GPUs An experimental study H. Anzt, M. Kreutzer, M.

6 th AsHES workshop May 26 th , 2016, Chicago, USA Efficiency of general Krylov methods on GPUs An experimental study H. Anzt, M. Kreutzer, M. Koehler, G. Wellein, J. Dongarra Piotr Luszczek Solving large sparse linear systems on GPUs

390 views • 13 slides
Analyzing Throughput of GPUs Analyzing Throughput of GPUs Exploiting Within-Die Core-to-Core

Analyzing Throughput of GPUs Analyzing Throughput of GPUs Exploiting Within-Die Core-to-Core

Analyzing Throughput of GPUs Analyzing Throughput of GPUs Exploiting Within-Die Core-to-Core Exploiting Within-Die Core-to-Core Frequency Variation Frequency Variation Jungseob Lee, Paritosh Ajgaonkar, Nam Sung Kim Apr 12, 2011 Department of

578 views • 20 slides
Bandwidth Bottlenecks Across the Memory Hierarchy in GPUs Saumay Dublish, Vijay Nagarajan, Nigel

Bandwidth Bottlenecks Across the Memory Hierarchy in GPUs Saumay Dublish, Vijay Nagarajan, Nigel

Evaluating and Mitigating Bandwidth Bottlenecks Across the Memory Hierarchy in GPUs Saumay Dublish, Vijay Nagarajan, Nigel Topham The University of Edinburgh ISPASS 2017 25 th April Santa Rosa, California Multithreading on GPUs Hardware

547 views • 44 slides
Efficient Video Decoding on GPUs Efficient Video Decoding on GPUs by Point Based Rendering by

Efficient Video Decoding on GPUs Efficient Video Decoding on GPUs by Point Based Rendering by

Efficient Video Decoding on GPUs Efficient Video Decoding on GPUs by Point Based Rendering by Point Based Rendering Bo Han, Bingfeng Zhou Peking University Outline Outline Motivation and Goal Previous work Review of video decoding

741 views • 30 slides
Bigger GPUs and Bigger Nodes Carl Pearson (pearson@illinois.edu) PhD Candidate, advised by

Bigger GPUs and Bigger Nodes Carl Pearson (pearson@illinois.edu) PhD Candidate, advised by

Bigger GPUs and Bigger Nodes Carl Pearson (pearson@illinois.edu) PhD Candidate, advised by Professor Wen-Mei Hwu 1 Outline Experiences from working with domain experts to develop GPU codes on Blue Waters Kepler and Volta GPUs HPC

364 views • 20 slides
How Walmart Improves Forecast Accuracy with NVIDIA GPUs March 19, 2019 Agenda Walmarts

How Walmart Improves Forecast Accuracy with NVIDIA GPUs March 19, 2019 Agenda Walmarts

How Walmart Improves Forecast Accuracy with NVIDIA GPUs March 19, 2019 Agenda Walmarts forecasting problem Initial (non-GPU) approach Algorithms Pipeline Integrating GPUs into every aspect of the solution History

612 views • 23 slides
How to Deal with Radiation: Evaluation and Mitigation of GPUs Soft-Errors Paolo Rech

How to Deal with Radiation: Evaluation and Mitigation of GPUs Soft-Errors Paolo Rech

April 6 th 2015 San Jos, CA How to Deal with Radiation: Evaluation and Mitigation of GPUs Soft-Errors Paolo Rech Motivation: Automotive Applications Pedestrian Detection System: embedded GPUs increase cars security Paolo Rech

895 views • 61 slides
Native Offload of Haskell Repa Programs to Integrated GPUs Hai (Paul) Liu with Laurence Day, Neal

Native Offload of Haskell Repa Programs to Integrated GPUs Hai (Paul) Liu with Laurence Day, Neal

Native Offload of Haskell Repa Programs to Integrated GPUs Hai (Paul) Liu with Laurence Day, Neal Glew, Todd Anderson, Rajkishore Barik Intel Labs. September 28, 2016 General purpose computing on integrated GPUs More than 90% of processors

797 views • 56 slides
Can GPUs Cure Cancer? Multi-scale Integrative Analysis Predict treatment outcome, select,

Can GPUs Cure Cancer? Multi-scale Integrative Analysis Predict treatment outcome, select,

Extreme Computing, Clinical Medicine and GPUs or Can GPUs Cure Cancer? Multi-scale Integrative Analysis Predict treatment outcome, select, monitor treatments Computer assisted exploration of new classification schemes Tumor

410 views • 30 slides
A Dynamic Programming-based MCMC Framework for Solving DCOPs with GPUs Ferdinando Fioretto 1(2)

A Dynamic Programming-based MCMC Framework for Solving DCOPs with GPUs Ferdinando Fioretto 1(2)

A Dynamic Programming-based MCMC Framework for Solving DCOPs with GPUs Ferdinando Fioretto 1(2) (joint work with) William Yeoh 2 and Enrico Pontelli 2 1 University of Michigan 2 New Mexico State University CP 2016, Toulouse Introduction GPUs

796 views • 27 slides
ACCELERATING STEREO 360 STITCHING USING MULTI-GPUS Ken Turkowski & Trevor Smith, GTC 2017

ACCELERATING STEREO 360 STITCHING USING MULTI-GPUS Ken Turkowski & Trevor Smith, GTC 2017

ACCELERATING STEREO 360 STITCHING USING MULTI-GPUS Ken Turkowski & Trevor Smith, GTC 2017 OVERVIEW What is a stereo panorama? [Ken] How do we stitch? [Ken] How do we handle real-time videos? GPUs! [Trevor] Demo in the VR Village, until

695 views • 38 slides
CudaDMA: Optimizing GPU Memory Bandwidth via Warp Specialization Michael Bauer (Stanford) Henry

CudaDMA: Optimizing GPU Memory Bandwidth via Warp Specialization Michael Bauer (Stanford) Henry

CudaDMA: Optimizing GPU Memory Bandwidth via Warp Specialization Michael Bauer (Stanford) Henry Cook (UC Berkeley) Brucek Khailany (NVIDIA Research) 1 GPUs Are Ubiquitous GPUs are in many supercomputers today GPUs are great High

725 views • 31 slides
Multi-parameter Waveform Inversion with GPUs for the Cloud A Pipelined Implementation Huy Le*,

Multi-parameter Waveform Inversion with GPUs for the Cloud A Pipelined Implementation Huy Le*,

Multi-parameter Waveform Inversion with GPUs for the Cloud A Pipelined Implementation Huy Le*, Stewart A. Levin, and Robert G. Clapp Geophysics Department, Stanford University March 28, 2018 Huy Le Multi-parameter Waveform Inversion with GPUs

532 views • 24 slides
Energy-Efficiency in GPUs By: Ehsan Sharifi Esfahani Outlines Upward trend of using accelerator

Energy-Efficiency in GPUs By: Ehsan Sharifi Esfahani Outlines Upward trend of using accelerator

A Survey on Energy-Efficiency in GPUs By: Ehsan Sharifi Esfahani Outlines Upward trend of using accelerator in supercomputers An Argument about TOP500 website Motivations Challenges Source of energy consumption in GPUs

553 views • 21 slides
Efficient GPU-only Tree Walks in ChaNGa Jianqiao Liu, Milind Kulkarni Purdue University gpus!

Efficient GPU-only Tree Walks in ChaNGa Jianqiao Liu, Milind Kulkarni Purdue University gpus!

Efficient GPU-only Tree Walks in ChaNGa Jianqiao Liu, Milind Kulkarni Purdue University gpus! GPUs are an important component of modern supercomputers, and are becoming increasingly important to obtain peak performance Blue Waters (2007)

189 views • 16 slides

More recommend