SlideShare a Scribd company logo
1 of 23
Deep Learning
Sum-of-Squares Images in
Accelerated Parallel MRI
Joonhyung Lee, Hyunjong Kim, Hyungjin Chung, Jong Chul Ye
ISBI 2020 Oral Session “MRI Reconstruction Methods” (MoPaO1)
Introduction
2
Accelerated (Sub-Nyquist) k-space Sampling
3
Imaging Domains
4
Complex, Fourier Complex, Image Real, Image
Comparison of Images
5
Theoretical Challenges
• The raw k-space data lies in the signal domain, not the image domain.
• The k-space data consists of complex values, not real values.
• MRI machines have many coils to provide redundancy and reduce noise.
• It is not clear how to handle the multiple coils with different sensitivities.
6
Method
7
Solutions to Theoretical Challenges
• Concatenate the coils in the channel axis.
• Use real-valued magnitude images as input, discarding image phase.
• Output a single channel with all coil information (no sum-of-squares).
8
Image Domain
Reconstruction
9
10
Channel Axis Concatenation of Coil Inputs
11
Channel Axis
Overview
12
Channel Axis
BarbellNet
Under-sampled Inputs
Single-Channel
Reconstruction
BarbellNet Network Architecture
13
Model Training Details
• 𝑺𝑺𝑰𝑴 𝟕 as loss function.
• Inputs center cropped to 320x320.
• Adam optimizer with 𝛽1 = 0.9, 𝛽2 = 0.999.
• Initial learning rate of 10−4, eventually reduced to 10−6 during training.
• Single GTX 1080Ti/2080Ti GPU used for training of ~100 epochs.
14
Implementation
15
Practical Challenges
• Approximately 60% of teams could not manage implementation issues.
• Naïve data ETL pipeline has <10% GPU utilization.
• Disk I/O is a bottleneck due to the large size of multi-coil k-space data.
• CPU/GPU load balancing is a bottleneck for pre/post-processing of data.
16
MRI Data
Pipeline
Implementation Tips
• Compress the raw k-space data (HDF5 has native compression functionality).
• Store the data in fast SSD devices. SSDs also support parallel reads, unlike HDDs.
• Perform FFT (which is compute-heavy and parallelizable) on GPU, not CPU.
• Perform disk reading and host-to-device data transfer asynchronously and overlap
them with GPU computation.
18
Results
19
Image Domain Reconstruction Results
20
Ground Truth Reconstruction Ground Truth Reconstruction
Results in Metrics
Acceleration Acquisition NMSE SSIM PSNR
4-fold
All 0.006 0.924 39
PD 0.0029 0.9542 40
PDFS 0.0086 0.8922 38
8-fold
All 0.010 0.897 37
PD 0.0067 0.9280 37
PDFS 0.0135 0.8651 36
21
Comparison with Other Methods
22
Thank You for Listening!
• Code for this project is available at
https://github.com/veritas9872/fastMRI-kspace.
• The slides for this presentation are available at
https://www.slideshare.net/ssuserc416e2/presentations.
• Please contact the authors if you have any questions.
23

More Related Content

What's hot

(2017/06)Practical points of deep learning for medical imaging
(2017/06)Practical points of deep learning for medical imaging(2017/06)Practical points of deep learning for medical imaging
(2017/06)Practical points of deep learning for medical imagingKyuhwan Jung
 
3D Image visualization
3D Image visualization3D Image visualization
3D Image visualizationalok ray
 
YOLOv4: optimal speed and accuracy of object detection review
YOLOv4: optimal speed and accuracy of object detection reviewYOLOv4: optimal speed and accuracy of object detection review
YOLOv4: optimal speed and accuracy of object detection reviewLEE HOSEONG
 
DIGITAL IMAGE PROCESSING - Day 4 Image Transform
DIGITAL IMAGE PROCESSING - Day 4 Image TransformDIGITAL IMAGE PROCESSING - Day 4 Image Transform
DIGITAL IMAGE PROCESSING - Day 4 Image Transformvijayanand Kandaswamy
 
Brain tumor detection by scanning MRI images (using filtering techniques)
Brain tumor detection by scanning MRI images (using filtering techniques)Brain tumor detection by scanning MRI images (using filtering techniques)
Brain tumor detection by scanning MRI images (using filtering techniques)Vivek reddy
 
Real Time Object Tracking
Real Time Object TrackingReal Time Object Tracking
Real Time Object TrackingVanya Valindria
 
Digital Image Fundamentals
Digital Image FundamentalsDigital Image Fundamentals
Digital Image FundamentalsA B Shinde
 
5-IMAGE RECONSTRUCTION in CT Scan-Rohit.pptx
5-IMAGE RECONSTRUCTION in CT Scan-Rohit.pptx5-IMAGE RECONSTRUCTION in CT Scan-Rohit.pptx
5-IMAGE RECONSTRUCTION in CT Scan-Rohit.pptxRohit Bansal
 
Vsat access control protocols
Vsat access control protocolsVsat access control protocols
Vsat access control protocolsSyed Mainul Islam
 
Video object tracking with classification and recognition of objects
Video object tracking with classification and recognition of objectsVideo object tracking with classification and recognition of objects
Video object tracking with classification and recognition of objectsManish Khare
 
COM2304: Digital Image Fundamentals - I
COM2304: Digital Image Fundamentals - I COM2304: Digital Image Fundamentals - I
COM2304: Digital Image Fundamentals - I Hemantha Kulathilake
 
introduction to Digital Image Processing
introduction to Digital Image Processingintroduction to Digital Image Processing
introduction to Digital Image Processingnikesh gadare
 
Mpeg video compression
Mpeg video compressionMpeg video compression
Mpeg video compressionGem WeBlog
 
An Introduction to Microwave Imaging
An Introduction to Microwave ImagingAn Introduction to Microwave Imaging
An Introduction to Microwave ImagingHwa Pyung Kim
 
Application of-image-segmentation-in-brain-tumor-detection
Application of-image-segmentation-in-brain-tumor-detectionApplication of-image-segmentation-in-brain-tumor-detection
Application of-image-segmentation-in-brain-tumor-detectionMyat Myint Zu Thin
 

What's hot (20)

(2017/06)Practical points of deep learning for medical imaging
(2017/06)Practical points of deep learning for medical imaging(2017/06)Practical points of deep learning for medical imaging
(2017/06)Practical points of deep learning for medical imaging
 
3D Image visualization
3D Image visualization3D Image visualization
3D Image visualization
 
YOLOv4: optimal speed and accuracy of object detection review
YOLOv4: optimal speed and accuracy of object detection reviewYOLOv4: optimal speed and accuracy of object detection review
YOLOv4: optimal speed and accuracy of object detection review
 
Medical image analysis
Medical image analysisMedical image analysis
Medical image analysis
 
DIGITAL IMAGE PROCESSING - Day 4 Image Transform
DIGITAL IMAGE PROCESSING - Day 4 Image TransformDIGITAL IMAGE PROCESSING - Day 4 Image Transform
DIGITAL IMAGE PROCESSING - Day 4 Image Transform
 
Microwave Imaging for Breast Cancer Detection and Therapy Monitoring
Microwave Imaging for Breast Cancer Detection and Therapy MonitoringMicrowave Imaging for Breast Cancer Detection and Therapy Monitoring
Microwave Imaging for Breast Cancer Detection and Therapy Monitoring
 
Brain tumor detection by scanning MRI images (using filtering techniques)
Brain tumor detection by scanning MRI images (using filtering techniques)Brain tumor detection by scanning MRI images (using filtering techniques)
Brain tumor detection by scanning MRI images (using filtering techniques)
 
Real Time Object Tracking
Real Time Object TrackingReal Time Object Tracking
Real Time Object Tracking
 
Image Processing Using MATLAB
Image Processing Using MATLABImage Processing Using MATLAB
Image Processing Using MATLAB
 
Digital Image Fundamentals
Digital Image FundamentalsDigital Image Fundamentals
Digital Image Fundamentals
 
5-IMAGE RECONSTRUCTION in CT Scan-Rohit.pptx
5-IMAGE RECONSTRUCTION in CT Scan-Rohit.pptx5-IMAGE RECONSTRUCTION in CT Scan-Rohit.pptx
5-IMAGE RECONSTRUCTION in CT Scan-Rohit.pptx
 
Vsat access control protocols
Vsat access control protocolsVsat access control protocols
Vsat access control protocols
 
CNN Algorithm
CNN AlgorithmCNN Algorithm
CNN Algorithm
 
Video object tracking with classification and recognition of objects
Video object tracking with classification and recognition of objectsVideo object tracking with classification and recognition of objects
Video object tracking with classification and recognition of objects
 
COM2304: Digital Image Fundamentals - I
COM2304: Digital Image Fundamentals - I COM2304: Digital Image Fundamentals - I
COM2304: Digital Image Fundamentals - I
 
introduction to Digital Image Processing
introduction to Digital Image Processingintroduction to Digital Image Processing
introduction to Digital Image Processing
 
Wiener Filter
Wiener FilterWiener Filter
Wiener Filter
 
Mpeg video compression
Mpeg video compressionMpeg video compression
Mpeg video compression
 
An Introduction to Microwave Imaging
An Introduction to Microwave ImagingAn Introduction to Microwave Imaging
An Introduction to Microwave Imaging
 
Application of-image-segmentation-in-brain-tumor-detection
Application of-image-segmentation-in-brain-tumor-detectionApplication of-image-segmentation-in-brain-tumor-detection
Application of-image-segmentation-in-brain-tumor-detection
 

Similar to Deep Learning Fast MRI Using Channel Attention in Magnitude Domain

04 accelerating dl inference with (open)capi and posit numbers
04 accelerating dl inference with (open)capi and posit numbers04 accelerating dl inference with (open)capi and posit numbers
04 accelerating dl inference with (open)capi and posit numbersYutaka Kawai
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)DonghyunKang12
 
DigitRecognition.pptx
DigitRecognition.pptxDigitRecognition.pptx
DigitRecognition.pptxruvex
 
Tutorial-on-DNN-09A-Co-design-Sparsity.pdf
Tutorial-on-DNN-09A-Co-design-Sparsity.pdfTutorial-on-DNN-09A-Co-design-Sparsity.pdf
Tutorial-on-DNN-09A-Co-design-Sparsity.pdfDuy-Hieu Bui
 
Using Many-Core Processors to Improve the Performance of Space Computing Plat...
Using Many-Core Processors to Improve the Performance of Space Computing Plat...Using Many-Core Processors to Improve the Performance of Space Computing Plat...
Using Many-Core Processors to Improve the Performance of Space Computing Plat...Fisnik Kraja
 
240422_Thuy_Labseminar[Large Graph Property Prediction via Graph Segment Trai...
240422_Thuy_Labseminar[Large Graph Property Prediction via Graph Segment Trai...240422_Thuy_Labseminar[Large Graph Property Prediction via Graph Segment Trai...
240422_Thuy_Labseminar[Large Graph Property Prediction via Graph Segment Trai...thanhdowork
 
In datacenter performance analysis of a tensor processing unit
In datacenter performance analysis of a tensor processing unitIn datacenter performance analysis of a tensor processing unit
In datacenter performance analysis of a tensor processing unitJinwon Lee
 
Morph : a novel accelerator
Morph : a novel acceleratorMorph : a novel accelerator
Morph : a novel acceleratorBaharJV
 
Large Scale Parallel FDTD Simulation of Full 3D Photonic Crystal Structures
Large Scale Parallel FDTD Simulation of Full 3D Photonic Crystal StructuresLarge Scale Parallel FDTD Simulation of Full 3D Photonic Crystal Structures
Large Scale Parallel FDTD Simulation of Full 3D Photonic Crystal Structuresayubimoak
 
Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용홍배 김
 
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)Shunta Saito
 
Performance Models for Apache Accumulo
Performance Models for Apache AccumuloPerformance Models for Apache Accumulo
Performance Models for Apache AccumuloSqrrl
 
OpenCAPI-based Image Analysis Pipeline for 18 GB/s kilohertz-framerate X-ray ...
OpenCAPI-based Image Analysis Pipeline for 18 GB/s kilohertz-framerate X-ray ...OpenCAPI-based Image Analysis Pipeline for 18 GB/s kilohertz-framerate X-ray ...
OpenCAPI-based Image Analysis Pipeline for 18 GB/s kilohertz-framerate X-ray ...Ganesan Narayanasamy
 
Introduction to computer vision
Introduction to computer visionIntroduction to computer vision
Introduction to computer visionMarcin Jedyk
 
Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...
Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...
Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...changedaeoh
 
DVLSI_project_presentation_template.pptx
DVLSI_project_presentation_template.pptxDVLSI_project_presentation_template.pptx
DVLSI_project_presentation_template.pptxAkshitAgiwal1
 

Similar to Deep Learning Fast MRI Using Channel Attention in Magnitude Domain (20)

04 accelerating dl inference with (open)capi and posit numbers
04 accelerating dl inference with (open)capi and posit numbers04 accelerating dl inference with (open)capi and posit numbers
04 accelerating dl inference with (open)capi and posit numbers
 
Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)Cvpr 2018 papers review (efficient computing)
Cvpr 2018 papers review (efficient computing)
 
DigitRecognition.pptx
DigitRecognition.pptxDigitRecognition.pptx
DigitRecognition.pptx
 
Tutorial-on-DNN-09A-Co-design-Sparsity.pdf
Tutorial-on-DNN-09A-Co-design-Sparsity.pdfTutorial-on-DNN-09A-Co-design-Sparsity.pdf
Tutorial-on-DNN-09A-Co-design-Sparsity.pdf
 
Using Many-Core Processors to Improve the Performance of Space Computing Plat...
Using Many-Core Processors to Improve the Performance of Space Computing Plat...Using Many-Core Processors to Improve the Performance of Space Computing Plat...
Using Many-Core Processors to Improve the Performance of Space Computing Plat...
 
240422_Thuy_Labseminar[Large Graph Property Prediction via Graph Segment Trai...
240422_Thuy_Labseminar[Large Graph Property Prediction via Graph Segment Trai...240422_Thuy_Labseminar[Large Graph Property Prediction via Graph Segment Trai...
240422_Thuy_Labseminar[Large Graph Property Prediction via Graph Segment Trai...
 
Manycores for the Masses
Manycores for the MassesManycores for the Masses
Manycores for the Masses
 
In datacenter performance analysis of a tensor processing unit
In datacenter performance analysis of a tensor processing unitIn datacenter performance analysis of a tensor processing unit
In datacenter performance analysis of a tensor processing unit
 
Morph : a novel accelerator
Morph : a novel acceleratorMorph : a novel accelerator
Morph : a novel accelerator
 
Large Scale Parallel FDTD Simulation of Full 3D Photonic Crystal Structures
Large Scale Parallel FDTD Simulation of Full 3D Photonic Crystal StructuresLarge Scale Parallel FDTD Simulation of Full 3D Photonic Crystal Structures
Large Scale Parallel FDTD Simulation of Full 3D Photonic Crystal Structures
 
Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용Convolutional neural networks 이론과 응용
Convolutional neural networks 이론과 응용
 
lec6a.ppt
lec6a.pptlec6a.ppt
lec6a.ppt
 
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
 
Performance Models for Apache Accumulo
Performance Models for Apache AccumuloPerformance Models for Apache Accumulo
Performance Models for Apache Accumulo
 
OpenCAPI-based Image Analysis Pipeline for 18 GB/s kilohertz-framerate X-ray ...
OpenCAPI-based Image Analysis Pipeline for 18 GB/s kilohertz-framerate X-ray ...OpenCAPI-based Image Analysis Pipeline for 18 GB/s kilohertz-framerate X-ray ...
OpenCAPI-based Image Analysis Pipeline for 18 GB/s kilohertz-framerate X-ray ...
 
OOW-IMC-final
OOW-IMC-finalOOW-IMC-final
OOW-IMC-final
 
Dl2 computing gpu
Dl2 computing gpuDl2 computing gpu
Dl2 computing gpu
 
Introduction to computer vision
Introduction to computer visionIntroduction to computer vision
Introduction to computer vision
 
Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...
Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...
Vision Transformer(ViT) / An Image is Worth 16*16 Words: Transformers for Ima...
 
DVLSI_project_presentation_template.pptx
DVLSI_project_presentation_template.pptxDVLSI_project_presentation_template.pptx
DVLSI_project_presentation_template.pptx
 

More from Joonhyung Lee

Rethinking Attention with Performers
Rethinking Attention with PerformersRethinking Attention with Performers
Rethinking Attention with PerformersJoonhyung Lee
 
Denoising Unpaired Low Dose CT Images with Self-Ensembled CycleGAN
Denoising Unpaired Low Dose CT Images with Self-Ensembled CycleGANDenoising Unpaired Low Dose CT Images with Self-Ensembled CycleGAN
Denoising Unpaired Low Dose CT Images with Self-Ensembled CycleGANJoonhyung Lee
 
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...Joonhyung Lee
 
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable ...
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable ...CutMix: Regularization Strategy to Train Strong Classifiers with Localizable ...
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable ...Joonhyung Lee
 
AlphaZero: A General Reinforcement Learning Algorithm that Masters Chess, Sho...
AlphaZero: A General Reinforcement Learning Algorithm that Masters Chess, Sho...AlphaZero: A General Reinforcement Learning Algorithm that Masters Chess, Sho...
AlphaZero: A General Reinforcement Learning Algorithm that Masters Chess, Sho...Joonhyung Lee
 
Squeeze Excitation Networks, The simple idea that won the final ImageNet Chal...
Squeeze Excitation Networks, The simple idea that won the final ImageNet Chal...Squeeze Excitation Networks, The simple idea that won the final ImageNet Chal...
Squeeze Excitation Networks, The simple idea that won the final ImageNet Chal...Joonhyung Lee
 
DeepLab V3+: Encoder-Decoder with Atrous Separable Convolution for Semantic I...
DeepLab V3+: Encoder-Decoder with Atrous Separable Convolution for Semantic I...DeepLab V3+: Encoder-Decoder with Atrous Separable Convolution for Semantic I...
DeepLab V3+: Encoder-Decoder with Atrous Separable Convolution for Semantic I...Joonhyung Lee
 
AlphaGo Zero: Mastering the Game of Go Without Human Knowledge
AlphaGo Zero: Mastering the Game of Go Without Human KnowledgeAlphaGo Zero: Mastering the Game of Go Without Human Knowledge
AlphaGo Zero: Mastering the Game of Go Without Human KnowledgeJoonhyung Lee
 
Deep Learning in Bio-Medical Imaging
Deep Learning in Bio-Medical ImagingDeep Learning in Bio-Medical Imaging
Deep Learning in Bio-Medical ImagingJoonhyung Lee
 

More from Joonhyung Lee (11)

nnUNet
nnUNetnnUNet
nnUNet
 
Rethinking Attention with Performers
Rethinking Attention with PerformersRethinking Attention with Performers
Rethinking Attention with Performers
 
Denoising Unpaired Low Dose CT Images with Self-Ensembled CycleGAN
Denoising Unpaired Low Dose CT Images with Self-Ensembled CycleGANDenoising Unpaired Low Dose CT Images with Self-Ensembled CycleGAN
Denoising Unpaired Low Dose CT Images with Self-Ensembled CycleGAN
 
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
InfoGAN: Interpretable Representation Learning by Information Maximizing Gene...
 
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable ...
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable ...CutMix: Regularization Strategy to Train Strong Classifiers with Localizable ...
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable ...
 
AlphaZero: A General Reinforcement Learning Algorithm that Masters Chess, Sho...
AlphaZero: A General Reinforcement Learning Algorithm that Masters Chess, Sho...AlphaZero: A General Reinforcement Learning Algorithm that Masters Chess, Sho...
AlphaZero: A General Reinforcement Learning Algorithm that Masters Chess, Sho...
 
Squeeze Excitation Networks, The simple idea that won the final ImageNet Chal...
Squeeze Excitation Networks, The simple idea that won the final ImageNet Chal...Squeeze Excitation Networks, The simple idea that won the final ImageNet Chal...
Squeeze Excitation Networks, The simple idea that won the final ImageNet Chal...
 
DeepLab V3+: Encoder-Decoder with Atrous Separable Convolution for Semantic I...
DeepLab V3+: Encoder-Decoder with Atrous Separable Convolution for Semantic I...DeepLab V3+: Encoder-Decoder with Atrous Separable Convolution for Semantic I...
DeepLab V3+: Encoder-Decoder with Atrous Separable Convolution for Semantic I...
 
AlphaGo Zero: Mastering the Game of Go Without Human Knowledge
AlphaGo Zero: Mastering the Game of Go Without Human KnowledgeAlphaGo Zero: Mastering the Game of Go Without Human Knowledge
AlphaGo Zero: Mastering the Game of Go Without Human Knowledge
 
StarGAN
StarGANStarGAN
StarGAN
 
Deep Learning in Bio-Medical Imaging
Deep Learning in Bio-Medical ImagingDeep Learning in Bio-Medical Imaging
Deep Learning in Bio-Medical Imaging
 

Recently uploaded

STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCESTERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCEPRINCE C P
 
Neurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 trNeurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 trssuser06f238
 
Boyles law module in the grade 10 science
Boyles law module in the grade 10 scienceBoyles law module in the grade 10 science
Boyles law module in the grade 10 sciencefloriejanemacaya1
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxUmerFayaz5
 
Genomic DNA And Complementary DNA Libraries construction.
Genomic DNA And Complementary DNA Libraries construction.Genomic DNA And Complementary DNA Libraries construction.
Genomic DNA And Complementary DNA Libraries construction.k64182334
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptxanandsmhk
 
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfAnalytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfSwapnil Therkar
 
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
Scheme-of-Work-Science-Stage-4 cambridge science.docx
Scheme-of-Work-Science-Stage-4 cambridge science.docxScheme-of-Work-Science-Stage-4 cambridge science.docx
Scheme-of-Work-Science-Stage-4 cambridge science.docxyaramohamed343013
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Nistarini College, Purulia (W.B) India
 
zoogeography of pakistan.pptx fauna of Pakistan
zoogeography of pakistan.pptx fauna of Pakistanzoogeography of pakistan.pptx fauna of Pakistan
zoogeography of pakistan.pptx fauna of Pakistanzohaibmir069
 
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tantaDashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tantaPraksha3
 
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |aasikanpl
 
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.PraveenaKalaiselvan1
 
Physiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptxPhysiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptxAArockiyaNisha
 
Ahmedabad Call Girls Service 9537192988 can satisfy every one of your dreams
Ahmedabad Call Girls Service 9537192988 can satisfy every one of your dreamsAhmedabad Call Girls Service 9537192988 can satisfy every one of your dreams
Ahmedabad Call Girls Service 9537192988 can satisfy every one of your dreamsoolala9823
 
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsSérgio Sacani
 
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxSOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxkessiyaTpeter
 

Recently uploaded (20)

STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCESTERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
STERILITY TESTING OF PHARMACEUTICALS ppt by DR.C.P.PRINCE
 
Neurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 trNeurodevelopmental disorders according to the dsm 5 tr
Neurodevelopmental disorders according to the dsm 5 tr
 
Boyles law module in the grade 10 science
Boyles law module in the grade 10 scienceBoyles law module in the grade 10 science
Boyles law module in the grade 10 science
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptx
 
Genomic DNA And Complementary DNA Libraries construction.
Genomic DNA And Complementary DNA Libraries construction.Genomic DNA And Complementary DNA Libraries construction.
Genomic DNA And Complementary DNA Libraries construction.
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
 
Engler and Prantl system of classification in plant taxonomy
Engler and Prantl system of classification in plant taxonomyEngler and Prantl system of classification in plant taxonomy
Engler and Prantl system of classification in plant taxonomy
 
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdfAnalytical Profile of Coleus Forskohlii | Forskolin .pdf
Analytical Profile of Coleus Forskohlii | Forskolin .pdf
 
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Munirka Delhi 💯Call Us 🔝8264348440🔝
 
Scheme-of-Work-Science-Stage-4 cambridge science.docx
Scheme-of-Work-Science-Stage-4 cambridge science.docxScheme-of-Work-Science-Stage-4 cambridge science.docx
Scheme-of-Work-Science-Stage-4 cambridge science.docx
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...
 
zoogeography of pakistan.pptx fauna of Pakistan
zoogeography of pakistan.pptx fauna of Pakistanzoogeography of pakistan.pptx fauna of Pakistan
zoogeography of pakistan.pptx fauna of Pakistan
 
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tantaDashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
Dashanga agada a formulation of Agada tantra dealt in 3 Rd year bams agada tanta
 
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
Call Us ≽ 9953322196 ≼ Call Girls In Mukherjee Nagar(Delhi) |
 
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
BIOETHICS IN RECOMBINANT DNA TECHNOLOGY.
 
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
 
Physiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptxPhysiochemical properties of nanomaterials and its nanotoxicity.pptx
Physiochemical properties of nanomaterials and its nanotoxicity.pptx
 
Ahmedabad Call Girls Service 9537192988 can satisfy every one of your dreams
Ahmedabad Call Girls Service 9537192988 can satisfy every one of your dreamsAhmedabad Call Girls Service 9537192988 can satisfy every one of your dreams
Ahmedabad Call Girls Service 9537192988 can satisfy every one of your dreams
 
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
 
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxSOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
 

Deep Learning Fast MRI Using Channel Attention in Magnitude Domain

Editor's Notes

  1. Hello, ISBI 2020. My name is Joonhyung Lee and today, I will introduce our work on MRI acceleration, which was done during our participation in the 2019 fastMRI Challenge.
  2. I will begin with a brief introduction into the problems that we face.
  3. Magnetic Resonance Imaging, or MRI, works by acquiring radio-frequency signals in the Fourier Domain. This information is set in a grid known as k-space. According to the Nyquist Sampling Theorem, a signal must be sampled at at least double the maximum frequency to produce a sound analog representation. However, MRI scans take a long time and a major research goal in MRI is to reduce scanning times. Because most of the information in an image is concentrated in the low frequency region at the center of k-space, we can reduce the amount of sampling in higher frequency regions while retaining most of the information. We can thus reduce the acquisition time significantly with minimal loss of information. The image on the right shows an 8-fold acceleration with 4% sampled at the low frequency ACS region.
  4. After acquiring the k-space signal, the inverse Fourier Transform is applied to create an image of the underlying object. This image will be a complex-valued image. We create a real-valued image from the magnitude values of this complex-valued image. Also, modern MRI machines have multiple radio-frequency coils, which create separate images with different sensitivities to different locations. A single image is formed by performing a root-sum-of-squares on the magnitude image of each coil.
  5. As you can see from the knee images, even with 8-fold acceleration of the high frequency regions, the general outline of the underlying object is still visible. However, we wish to reconstruct an image suitable for use in medical diagnosis. To this end, we use deep learning produce a high-quality image from the information latent within the under-sampled data.
  6. However, due to the unique nature of MRI, several theoretical challenges arise that need to be solved. First, k-space data lies in the signal domain, where each point contains information about the entire image. Second, k-space consists of complex numbers, whereas almost all deep learning models use real numbers. Third, modern MRI machines have multiple radio-frequency coils, each with different sensitivities to different locations. Moreover, the number of coils and the location of each coil is different for each device.
  7. In the following section, I will discuss our solutions to these problems.
  8. After much experimentation, we arrived at the following solutions. First, we concatenate the coils in the channel axis. Second, we used the magnitude images for each coil as the input. Finally, we found that outputting a single-channel image for the final reconstruction produced much superior results than producing results for each coil separately.
  9. Image domain reconstruction is the form used by the vast majority of deep learning image reconstruction models. Over the last few years, through extensive experimentation, it has been proven to work on a wide array of images. While this discards the complex-image phase information, this solved the problem of handling complex numbers.
  10. Image domain learning for MRI loses the phase information of the complex-valued image. The images above show the magnitude and phase from a single coil in a slice in an MRI scan. While this means that the images cannot be converted back into k-space, for k-space input consistency, we find that the magnitude images contain enough information to allow high quality reconstruction.
  11. Concatenating the coils in the channel axis allows the model to utilize the information from each coil while dramatically reducing the amount of computation compared to other methods. For example, concatenation in the batch axis would have entailed a 15-fold increase in memory and computation time on the fastMRI dataset. Also, the different coil sensitivities are available to the entire model all the time. One limitation is that this requires all data to have the same number of coils, each with the same sensitivity information. Channel concatenation was possible on the fastMRI knee dataset because it consists entirely of MRI scans with 15 coils.
  12. Finally, we take the magnitude images from each coil and, instead of performing a root-sum-of-squares operation, input the coil images into a neural network. The output is a single image that is compared to the ground-truth root-sum-of-squares image. This method produces better results than separate generation of coil images. We suspect that this is because this allows the model to learn the best method to combine the coil information.
  13. Our model is loosely based on the U-Net architecture but has a long chain of residual channel attention blocks, or RCABs, in the middle and multiple DenseBlocks for efficient feature extraction. The residual blocks were based on the EDSR residual block, which is optimized for image reconstruction. No feature normalization layers were included in the model to reduce computation and improve metric performance by preserving the original distribution and allowing for greater representational capacity of the model. The channel attention mechanism is identical to the Squeeze Excitation channel attention mechanism. Channel attention of this type has been shown to be very effective for both high-level tasks such as classification as well as low-level image denoising and super-resolution. We also found that it helped stabilize network training, which was very important because the lack of normalization layers caused training instability. We termed our model “BarbellNet” due to its resemblance to a barbell.
  14. During training, we used structural similarity (SSIM) with kernel size 7 as the sole loss function as this was the primary metric of the fastMRI challenge. Inputs were center cropped to 320x320 to reduce computation and create a uniform input size. Learning rate decay was used to reduce the learning rate from 10^-4 to 10^-6. Finally, all models were trained on a single GTX 1080Ti or RTX 2080Ti GPU. These hardware requirements are within the reach of most researchers.
  15. Finally, I would like to mention some challenges in implementation.
  16. The unique nature of k-space data poses not only theoretical challenges but also practical challenges in implementation that mean that standard deep learning pipelines are very inefficient. A naïve data pipeline will significantly under-utilize GPU, but the causes of this under-utilization will not be obvious. Because of this, approximately 60% of challenge contestants could not participate in the multi-coil challenge but only applied to the single-coil track, which consists of synthetic data derived from the multi-coil raw data.
  17. The biggest problem is the very large size of each MRI slice or volume. Reading data from HDD is very slow. This means that the CPU and GPU are idle most of the time, waiting for data to arrive. The second issue is data pre-processing. The Fourier Transform is very computationally intensive and performing it on CPU on such a large amount of data will form a bottleneck, no matter how efficiently implemented.
  18. To solve these problems, we offer these solutions. First, to solve the problem of disk I/O, the simplest solution is to use an SSD storage device to store the data. Additionally, you can compress the data file to reduce the amount of raw data that must be read from disk, although this comes at the cost of increased CPU computation. Second, perform Fourier Transforms on GPU, not CPU. There are many highly optimized Fourier Transform libraries on GPU. Finally, overlap disk reading on multiple processes and overlap it with GPU computation. This will prevent the GPU from being idle for too long.
  19. Finally, our results.
  20. We have here a qualitative comparison between the ground truth and reconstruction images. Compared to the inputs, they are much clearer and show no obvious artifacts. One limitation is that there is a loss of detail in the horizontal direction, the direction of down-sampling.
  21. The chart shows our results in more quantitative form. One can see that different accelerations and different acquisition methods have very different average metrics. 4-fold acceleration with 8% ACS sampling has superior results compared to 8-fold acceleration with 4% ACS sampling because the former has more signal in the input data. PD, or Proton Density images have better metrics than PDFS, or Proton Density Fat Suppression because the fat suppression acquisition sequence increases the amount of noise, although it also reduces the visibility of fat.
  22. Our methods were very close to competitors in terms of metrics. Even compared to the first-place results, there was only a small difference in SSIM. Our results are therefore comparable to even state-of-the art methods, despite using fewer computational resources.
  23. This is the end of the session. Thank you for listening. Please contact us if you have any questions and have a good day.