SlideShare a Scribd company logo
1 of 23
Download to read offline
Continuous Conversion of CT Kernel
using Switchable CycleGAN with AdaIN
Serin Yang, Eung Yeop Kim, and Jong Chul Ye
Serin Yang
적응적 인스턴스 정규화가 적용된 전환 가능 CycleGAN을 이용한 연속적인 CT 커널 생성에 관한 연구
2
Introduction
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 3
CT Reconstruction Kernels
Introduction
Soft kernel
Sharp kernel
Window
Level
400
Window
Width
1500
Window
Level
50
Window
Width
120
Sharp kernel (high pass filter)
• preserving higher spatial frequencies
• decreasing lower spatial frequencies
• more noise
• bone
Soft kernel (low pass filter)
• preserving lower spatial frequencies
• reducing higher spatial frequencies
• reduced noise and impaired spatial resolution
• brain or soft tissue
Kernel Properties
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 4
CT Reconstruction Kernels
Introduction
Soft kernel
Sharp kernel
Window
Level
400
Window
Width
1500
Window
Level
50
Window
Width
120
Sharp kernel (high pass filter)
• preserving higher spatial frequencies
• decreasing lower spatial frequencies
• more noise
• bone
Soft kernel (low pass filter)
• preserving lower spatial frequencies
• reducing higher spatial frequencies
• reduced noise and impaired spatial resolution
• brain or soft tissue
Kernel Properties
• Increased size of required storage
• Additional cost and inconvenience
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 5
• Supervised Method with Convolutional Neural Network
• Mapping function between two different kernels or among limited number of pairs.
Sang Min Lee, 2019 Da-in Eun, 2020
Deep Learning based Kernel Conversion
Introduction
6
Proposed Method
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 7
Adaptive Instance Normalization (AdaIN)
Proposed Method
1 − 𝛽 𝑥 + 𝛽 𝜎 𝑦
𝑥 − 𝜇 𝑥
𝜎 𝑥
+ 𝜇 𝑦
Property
• 𝛽 ∈ [𝟎, 𝟏]
• Interpolation between styles of two inputs, 𝒙 and 𝒚
൞
𝑥, 𝛽 = 0
𝜎 𝑦
𝑥 − 𝜇 𝑥
𝜎 𝑥
+ 𝜇 𝑦 , 𝛽 = 1
• 𝒙: content input, 𝒚: style input
• AdaIN aligns the channel-wise mean and variance of 𝒙 to match those of 𝒚
• Not limited to a single style like Instance Normalization(IN)
• Adaptively computes affine parameters from the style input 𝒚
𝐴𝑑𝑎𝐼𝑁(𝑥, 𝑦) = 𝝈 𝒚
𝑥 − 𝜇 𝑥
𝜎 𝑥
+ 𝝁 𝒚
Definition
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 8
Switchable CycleGAN with AdaIN
Proposed Method
[1] Gu, Jawook, 2020
Vanilla CycleGAN
Switchable CycleGAN
in 2 domain[1]
Switchable CycleGAN
in 3 domain
𝐴𝑑𝑎𝐼𝑁(𝑥, 𝑦) = 𝝈 𝒚
𝑥 − 𝜇 𝑥
𝜎 𝑥
+ 𝝁 𝒚
Definition
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 9
Architecture of the Generator
Proposed Method
Input
Output
Encoder Decoder
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 10
Architecture of the Generator
Proposed Method
Input
Output
Encoder Decoder
Source Domain
AdaIN code generator
Target Domain
AdaIN code generator
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 11
Loss Function
Proposed Method
where ℓ𝒕𝒐𝒕𝒂𝒍(𝑮, 𝑭, 𝑫𝑺, 𝑫𝑯) = −ℓ𝒅𝒊𝒔𝒄(𝑮, 𝑭, 𝑫𝑺, 𝑫𝑯) + 𝜆𝑐𝑦𝑐ℓ𝒄𝒚𝒄𝒍𝒆(𝑮, 𝑭) + 𝜆𝑖𝑑ℓ𝒊𝒅𝒆𝒏𝒕𝒊𝒕𝒚(𝑮, 𝑭)
min
𝐺,𝐹
max
𝐷𝑆,𝐷𝐻
ℓ𝒕𝒐𝒕𝒂𝒍(𝑮, 𝑭, 𝑫𝑺, 𝑫𝑯),
2 Domain Switchable CycleGAN
G
D𝑆
D𝐻
G
G
G
ℓ𝒄𝒚𝒄𝒍𝒆 𝑮, 𝑭
G
D𝑆
D𝐻
G
G
G
D𝑆
D𝐻
ℓ𝒅𝒊𝒔𝒄 𝑮, 𝑭, 𝑫𝑺, 𝑫𝑯 ℓ𝒊𝒅𝒆𝒏𝒕𝒊𝒕𝒚 𝑮, 𝑭
G
D𝑆
D𝐻
G
G
G
G
G
Reconstructed
output
Input
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 12
Loss Function
Proposed Method
3 Domain Switchable CycleGAN
where ℓ𝒕𝒐𝒕𝒂𝒍 𝑮, 𝑭𝒆, 𝑭𝒅, 𝑫𝑺, 𝑫𝑯, 𝑫𝑴 = −ℓ𝒅𝒊𝒔𝒄 𝑮, 𝑭𝒆, 𝑭𝒅, 𝑫𝑺, 𝑫𝑯, 𝑫𝑴 + 𝜆𝑐𝑦𝑐ℓ𝒄𝒚𝒄𝒍𝒆 𝑮, 𝑭𝒆, 𝑭𝒅
+𝜆𝐴𝐸ℓ𝑨𝑬 𝑮, 𝑭𝒆, 𝑭𝒅 + 𝜆𝑠𝑐ℓ𝒔𝒄 𝑮, 𝑭𝒆, 𝑭𝒅
min
𝐺,𝐹𝑒,𝐹𝑑
max
𝐷𝑆,𝐷𝐻,𝐷𝑀
ℓ𝒕𝒐𝒕𝒂𝒍(𝑮, 𝑭𝒆, 𝑭𝒅, 𝑫𝑺, 𝑫𝑯, 𝑫𝑴),
( 0.0,1.0)
G
( 1.0,0.0)
G
H → M → S
H → S
S → M → H
S → H
13
Experimental Results
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 14
Switchable CycleGAN in 2 domain - Interpolation
Results
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 15
Switchable CycleGAN in 2 domain - Interpolation
Results
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 16
Switchable CycleGAN in 2 domain - Interpolation
Results
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 17
Switchable CycleGAN in 2 domain – Comparative Studies
Results
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 18
Results Switchable CycleGAN in 3 domain
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 19
Results Switchable CycleGAN in 2 domain vs 3 domain
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 20
Results Effectiveness of self-consistency loss
21
Conclusion
Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 22
Conclusion
• Unsupervised deep-learning method for kernel conversion in CT images​
• Switchable CycleGAN combined with AdaIN allows training with single generator
• Preventing the model from overfitting problem in case of small dataset ↓​
• Computationally efficient​
• Various images were generated by synergistically combining the two given kernels at inference stage
• With intermediate kernel images, Switchable CycleGAN can be trained in 3 domain
• Improvement in the quality of the generated kernel images
• Range of interpolation can be controlled
• The improved performance of our proposed model was proved with extensive experimental results
Thank you

More Related Content

What's hot

Advanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalll
Advanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalllAdvanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalll
Advanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalll
Muddassar Abbasi
 
Medical image fusion using curvelet transform 2-3-4-5
Medical image fusion using curvelet transform 2-3-4-5Medical image fusion using curvelet transform 2-3-4-5
Medical image fusion using curvelet transform 2-3-4-5
IAEME Publication
 
Image resolution enhancement by using wavelet transform 2
Image resolution enhancement by using wavelet transform 2Image resolution enhancement by using wavelet transform 2
Image resolution enhancement by using wavelet transform 2
IAEME Publication
 

What's hot (20)

IRJET- Satellite Image Resolution Enhancement using Dual-tree Complex Wav...
IRJET-  	  Satellite Image Resolution Enhancement using Dual-tree Complex Wav...IRJET-  	  Satellite Image Resolution Enhancement using Dual-tree Complex Wav...
IRJET- Satellite Image Resolution Enhancement using Dual-tree Complex Wav...
 
IRJET-A Review of Underwater Image Enhancement By Wavelet Decomposition using...
IRJET-A Review of Underwater Image Enhancement By Wavelet Decomposition using...IRJET-A Review of Underwater Image Enhancement By Wavelet Decomposition using...
IRJET-A Review of Underwater Image Enhancement By Wavelet Decomposition using...
 
Advanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalll
Advanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalllAdvanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalll
Advanced Image Reconstruction Algorithms in MRIfor ISMRMversion finalll
 
Satellite Image Enhancement Using Dual Tree Complex Wavelet Transform
Satellite Image Enhancement Using Dual Tree Complex Wavelet TransformSatellite Image Enhancement Using Dual Tree Complex Wavelet Transform
Satellite Image Enhancement Using Dual Tree Complex Wavelet Transform
 
Medical image fusion using curvelet transform 2-3-4-5
Medical image fusion using curvelet transform 2-3-4-5Medical image fusion using curvelet transform 2-3-4-5
Medical image fusion using curvelet transform 2-3-4-5
 
37 9144 new technique based peasant multiplication (edit lafi)
37 9144 new technique based peasant multiplication (edit lafi)37 9144 new technique based peasant multiplication (edit lafi)
37 9144 new technique based peasant multiplication (edit lafi)
 
COUPLED FPGA/ASIC IMPLEMENTATION OF ELLIPTIC CURVE CRYPTO-PROCESSOR
COUPLED FPGA/ASIC IMPLEMENTATION OF ELLIPTIC CURVE CRYPTO-PROCESSORCOUPLED FPGA/ASIC IMPLEMENTATION OF ELLIPTIC CURVE CRYPTO-PROCESSOR
COUPLED FPGA/ASIC IMPLEMENTATION OF ELLIPTIC CURVE CRYPTO-PROCESSOR
 
A Review of Different Methods for Booth Multiplier
A Review of Different Methods for Booth MultiplierA Review of Different Methods for Booth Multiplier
A Review of Different Methods for Booth Multiplier
 
第13回 配信講義 計算科学技術特論A(2021)
第13回 配信講義 計算科学技術特論A(2021)第13回 配信講義 計算科学技術特論A(2021)
第13回 配信講義 計算科学技術特論A(2021)
 
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTION
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTIONMEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTION
MEDIAN BASED PARALLEL STEERING KERNEL REGRESSION FOR IMAGE RECONSTRUCTION
 
Median based parallel steering kernel regression for image reconstruction
Median based parallel steering kernel regression for image reconstructionMedian based parallel steering kernel regression for image reconstruction
Median based parallel steering kernel regression for image reconstruction
 
40 9148 satellite image enhancement using dual edit tyas
40 9148 satellite image enhancement using dual edit tyas40 9148 satellite image enhancement using dual edit tyas
40 9148 satellite image enhancement using dual edit tyas
 
IRJET-Underwater Image Enhancement by Wavelet Decomposition using FPGA
IRJET-Underwater Image Enhancement by Wavelet Decomposition using FPGAIRJET-Underwater Image Enhancement by Wavelet Decomposition using FPGA
IRJET-Underwater Image Enhancement by Wavelet Decomposition using FPGA
 
Ijetr011837
Ijetr011837Ijetr011837
Ijetr011837
 
Image resolution enhancement by using wavelet transform 2
Image resolution enhancement by using wavelet transform 2Image resolution enhancement by using wavelet transform 2
Image resolution enhancement by using wavelet transform 2
 
Background Subtraction Based on Phase and Distance Transform Under Sudden Ill...
Background Subtraction Based on Phase and Distance Transform Under Sudden Ill...Background Subtraction Based on Phase and Distance Transform Under Sudden Ill...
Background Subtraction Based on Phase and Distance Transform Under Sudden Ill...
 
(Paper Review)U-GAT-IT: unsupervised generative attentional networks with ada...
(Paper Review)U-GAT-IT: unsupervised generative attentional networks with ada...(Paper Review)U-GAT-IT: unsupervised generative attentional networks with ada...
(Paper Review)U-GAT-IT: unsupervised generative attentional networks with ada...
 
Kernel Descriptors for Visual Recognition
Kernel Descriptors for Visual RecognitionKernel Descriptors for Visual Recognition
Kernel Descriptors for Visual Recognition
 
Performance Evaluation of Percent Root Mean Square Difference for ECG Signals...
Performance Evaluation of Percent Root Mean Square Difference for ECG Signals...Performance Evaluation of Percent Root Mean Square Difference for ECG Signals...
Performance Evaluation of Percent Root Mean Square Difference for ECG Signals...
 
Implementation of Low Power and Area-Efficient Carry Select Adder
Implementation of Low Power and Area-Efficient Carry Select AdderImplementation of Low Power and Area-Efficient Carry Select Adder
Implementation of Low Power and Area-Efficient Carry Select Adder
 

Similar to Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN

LVTS - Image Resolution Monitor for Litho-Metrology
LVTS - Image Resolution Monitor for Litho-MetrologyLVTS - Image Resolution Monitor for Litho-Metrology
LVTS - Image Resolution Monitor for Litho-Metrology
Vladislav Kaplan
 
MICROPROCESSOR BASED SUN TRACKING SOLAR PANEL SYSTEM TO MAXIMIZE ENERGY GENER...
MICROPROCESSOR BASED SUN TRACKING SOLAR PANEL SYSTEM TO MAXIMIZE ENERGY GENER...MICROPROCESSOR BASED SUN TRACKING SOLAR PANEL SYSTEM TO MAXIMIZE ENERGY GENER...
MICROPROCESSOR BASED SUN TRACKING SOLAR PANEL SYSTEM TO MAXIMIZE ENERGY GENER...
moiz89
 
DESIGN AND ASIC IMPLEMENTATION OF DUC/DDC FOR COMMUNICATION SYSTEMS
DESIGN AND ASIC IMPLEMENTATION OF DUC/DDC FOR COMMUNICATION SYSTEMSDESIGN AND ASIC IMPLEMENTATION OF DUC/DDC FOR COMMUNICATION SYSTEMS
DESIGN AND ASIC IMPLEMENTATION OF DUC/DDC FOR COMMUNICATION SYSTEMS
VLSICS Design
 
Design and ASIC Implemenatation of DUC/DDC for Communication Systems
Design and ASIC Implemenatation of DUC/DDC for Communication Systems  Design and ASIC Implemenatation of DUC/DDC for Communication Systems
Design and ASIC Implemenatation of DUC/DDC for Communication Systems
VLSICS Design
 
Resume_Karthik_Koneru_Analog_and_Mixed Signal
Resume_Karthik_Koneru_Analog_and_Mixed SignalResume_Karthik_Koneru_Analog_and_Mixed Signal
Resume_Karthik_Koneru_Analog_and_Mixed Signal
Arizona State University
 
Resume_Karthik_Koneru_Analog_and_Mixed Signal
Resume_Karthik_Koneru_Analog_and_Mixed SignalResume_Karthik_Koneru_Analog_and_Mixed Signal
Resume_Karthik_Koneru_Analog_and_Mixed Signal
Arizona State University
 

Similar to Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN (20)

A Technique for Dynamic Range Improvement of Intermodulation Distortion Produ...
A Technique for Dynamic Range Improvement of Intermodulation Distortion Produ...A Technique for Dynamic Range Improvement of Intermodulation Distortion Produ...
A Technique for Dynamic Range Improvement of Intermodulation Distortion Produ...
 
Design of 17-Bit Audio Band Delta-Sigma Analog to Digital Converter
Design of 17-Bit Audio Band Delta-Sigma Analog to Digital ConverterDesign of 17-Bit Audio Band Delta-Sigma Analog to Digital Converter
Design of 17-Bit Audio Band Delta-Sigma Analog to Digital Converter
 
FPGA Implementation of Optimized CIC Filter for Sample Rate Conversion in Sof...
FPGA Implementation of Optimized CIC Filter for Sample Rate Conversion in Sof...FPGA Implementation of Optimized CIC Filter for Sample Rate Conversion in Sof...
FPGA Implementation of Optimized CIC Filter for Sample Rate Conversion in Sof...
 
Matrix based AC-DC converter
Matrix based AC-DC converterMatrix based AC-DC converter
Matrix based AC-DC converter
 
Dsp 2018 foehu - lec 10 - multi-rate digital signal processing
Dsp 2018 foehu - lec 10 - multi-rate digital signal processingDsp 2018 foehu - lec 10 - multi-rate digital signal processing
Dsp 2018 foehu - lec 10 - multi-rate digital signal processing
 
LVTS - Image Resolution Monitor for Litho-Metrology
LVTS - Image Resolution Monitor for Litho-MetrologyLVTS - Image Resolution Monitor for Litho-Metrology
LVTS - Image Resolution Monitor for Litho-Metrology
 
Thesis
ThesisThesis
Thesis
 
adaptive_ecg_cdr_edittedforpublic.pptx
adaptive_ecg_cdr_edittedforpublic.pptxadaptive_ecg_cdr_edittedforpublic.pptx
adaptive_ecg_cdr_edittedforpublic.pptx
 
AREA OPTIMIZED FPGA IMPLEMENTATION FOR GENERATION OF RADAR PULSE COM-PRESSION...
AREA OPTIMIZED FPGA IMPLEMENTATION FOR GENERATION OF RADAR PULSE COM-PRESSION...AREA OPTIMIZED FPGA IMPLEMENTATION FOR GENERATION OF RADAR PULSE COM-PRESSION...
AREA OPTIMIZED FPGA IMPLEMENTATION FOR GENERATION OF RADAR PULSE COM-PRESSION...
 
Compensator Based Performance Enhancement Strategy for a SIQO Buck Converter
Compensator Based Performance Enhancement Strategy for a SIQO Buck ConverterCompensator Based Performance Enhancement Strategy for a SIQO Buck Converter
Compensator Based Performance Enhancement Strategy for a SIQO Buck Converter
 
MICROPROCESSOR BASED SUN TRACKING SOLAR PANEL SYSTEM TO MAXIMIZE ENERGY GENER...
MICROPROCESSOR BASED SUN TRACKING SOLAR PANEL SYSTEM TO MAXIMIZE ENERGY GENER...MICROPROCESSOR BASED SUN TRACKING SOLAR PANEL SYSTEM TO MAXIMIZE ENERGY GENER...
MICROPROCESSOR BASED SUN TRACKING SOLAR PANEL SYSTEM TO MAXIMIZE ENERGY GENER...
 
SAR_ADC__Resumo
SAR_ADC__ResumoSAR_ADC__Resumo
SAR_ADC__Resumo
 
Sigma Delta ADC for Implantable Cardiac Sensing
Sigma Delta ADC for Implantable Cardiac SensingSigma Delta ADC for Implantable Cardiac Sensing
Sigma Delta ADC for Implantable Cardiac Sensing
 
DESIGN AND ASIC IMPLEMENTATION OF DUC/DDC FOR COMMUNICATION SYSTEMS
DESIGN AND ASIC IMPLEMENTATION OF DUC/DDC FOR COMMUNICATION SYSTEMSDESIGN AND ASIC IMPLEMENTATION OF DUC/DDC FOR COMMUNICATION SYSTEMS
DESIGN AND ASIC IMPLEMENTATION OF DUC/DDC FOR COMMUNICATION SYSTEMS
 
Design and ASIC Implemenatation of DUC/DDC for Communication Systems
Design and ASIC Implemenatation of DUC/DDC for Communication Systems  Design and ASIC Implemenatation of DUC/DDC for Communication Systems
Design and ASIC Implemenatation of DUC/DDC for Communication Systems
 
Efficient signal acquisition in multi channel neural systems
Efficient signal acquisition in multi channel neural systemsEfficient signal acquisition in multi channel neural systems
Efficient signal acquisition in multi channel neural systems
 
Resume_Karthik_Koneru_Analog_and_Mixed Signal
Resume_Karthik_Koneru_Analog_and_Mixed SignalResume_Karthik_Koneru_Analog_and_Mixed Signal
Resume_Karthik_Koneru_Analog_and_Mixed Signal
 
Resume_Karthik_Koneru_Analog_and_Mixed Signal
Resume_Karthik_Koneru_Analog_and_Mixed SignalResume_Karthik_Koneru_Analog_and_Mixed Signal
Resume_Karthik_Koneru_Analog_and_Mixed Signal
 
PPT FINAL (1)-1 (1).ppt
PPT FINAL (1)-1 (1).pptPPT FINAL (1)-1 (1).ppt
PPT FINAL (1)-1 (1).ppt
 
IRJET- Implementation of 16-Bit Pipelined ADC using 180nm CMOS Technology
IRJET-  	  Implementation of 16-Bit Pipelined ADC using 180nm CMOS TechnologyIRJET-  	  Implementation of 16-Bit Pipelined ADC using 180nm CMOS Technology
IRJET- Implementation of 16-Bit Pipelined ADC using 180nm CMOS Technology
 

Recently uploaded

Digital Communication Essentials: DPCM, DM, and ADM .pptx
Digital Communication Essentials: DPCM, DM, and ADM .pptxDigital Communication Essentials: DPCM, DM, and ADM .pptx
Digital Communication Essentials: DPCM, DM, and ADM .pptx
pritamlangde
 
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
AldoGarca30
 

Recently uploaded (20)

AIRCANVAS[1].pdf mini project for btech students
AIRCANVAS[1].pdf mini project for btech studentsAIRCANVAS[1].pdf mini project for btech students
AIRCANVAS[1].pdf mini project for btech students
 
S1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptx
S1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptxS1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptx
S1S2 B.Arch MGU - HOA1&2 Module 3 -Temple Architecture of Kerala.pptx
 
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced LoadsFEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
 
Jaipur ❤CALL GIRL 0000000000❤CALL GIRLS IN Jaipur ESCORT SERVICE❤CALL GIRL IN...
Jaipur ❤CALL GIRL 0000000000❤CALL GIRLS IN Jaipur ESCORT SERVICE❤CALL GIRL IN...Jaipur ❤CALL GIRL 0000000000❤CALL GIRLS IN Jaipur ESCORT SERVICE❤CALL GIRL IN...
Jaipur ❤CALL GIRL 0000000000❤CALL GIRLS IN Jaipur ESCORT SERVICE❤CALL GIRL IN...
 
Computer Graphics Introduction To Curves
Computer Graphics Introduction To CurvesComputer Graphics Introduction To Curves
Computer Graphics Introduction To Curves
 
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Service
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best ServiceTamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Service
Tamil Call Girls Bhayandar WhatsApp +91-9930687706, Best Service
 
Theory of Time 2024 (Universal Theory for Everything)
Theory of Time 2024 (Universal Theory for Everything)Theory of Time 2024 (Universal Theory for Everything)
Theory of Time 2024 (Universal Theory for Everything)
 
Digital Communication Essentials: DPCM, DM, and ADM .pptx
Digital Communication Essentials: DPCM, DM, and ADM .pptxDigital Communication Essentials: DPCM, DM, and ADM .pptx
Digital Communication Essentials: DPCM, DM, and ADM .pptx
 
Ghuma $ Russian Call Girls Ahmedabad ₹7.5k Pick Up & Drop With Cash Payment 8...
Ghuma $ Russian Call Girls Ahmedabad ₹7.5k Pick Up & Drop With Cash Payment 8...Ghuma $ Russian Call Girls Ahmedabad ₹7.5k Pick Up & Drop With Cash Payment 8...
Ghuma $ Russian Call Girls Ahmedabad ₹7.5k Pick Up & Drop With Cash Payment 8...
 
Online food ordering system project report.pdf
Online food ordering system project report.pdfOnline food ordering system project report.pdf
Online food ordering system project report.pdf
 
Ground Improvement Technique: Earth Reinforcement
Ground Improvement Technique: Earth ReinforcementGround Improvement Technique: Earth Reinforcement
Ground Improvement Technique: Earth Reinforcement
 
Max. shear stress theory-Maximum Shear Stress Theory ​ Maximum Distortional ...
Max. shear stress theory-Maximum Shear Stress Theory ​  Maximum Distortional ...Max. shear stress theory-Maximum Shear Stress Theory ​  Maximum Distortional ...
Max. shear stress theory-Maximum Shear Stress Theory ​ Maximum Distortional ...
 
Electromagnetic relays used for power system .pptx
Electromagnetic relays used for power system .pptxElectromagnetic relays used for power system .pptx
Electromagnetic relays used for power system .pptx
 
School management system project Report.pdf
School management system project Report.pdfSchool management system project Report.pdf
School management system project Report.pdf
 
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
Navigating Complexity: The Role of Trusted Partners and VIAS3D in Dassault Sy...
 
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptxHOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
HOA1&2 - Module 3 - PREHISTORCI ARCHITECTURE OF KERALA.pptx
 
💚Trustworthy Call Girls Pune Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top...
💚Trustworthy Call Girls Pune Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top...💚Trustworthy Call Girls Pune Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top...
💚Trustworthy Call Girls Pune Call Girls Service Just Call 🍑👄6378878445 🍑👄 Top...
 
A Study of Urban Area Plan for Pabna Municipality
A Study of Urban Area Plan for Pabna MunicipalityA Study of Urban Area Plan for Pabna Municipality
A Study of Urban Area Plan for Pabna Municipality
 
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
1_Introduction + EAM Vocabulary + how to navigate in EAM.pdf
 
Linux Systems Programming: Inter Process Communication (IPC) using Pipes
Linux Systems Programming: Inter Process Communication (IPC) using PipesLinux Systems Programming: Inter Process Communication (IPC) using Pipes
Linux Systems Programming: Inter Process Communication (IPC) using Pipes
 

Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN

  • 1. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN Serin Yang, Eung Yeop Kim, and Jong Chul Ye Serin Yang 적응적 인스턴스 정규화가 적용된 전환 가능 CycleGAN을 이용한 연속적인 CT 커널 생성에 관한 연구
  • 3. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 3 CT Reconstruction Kernels Introduction Soft kernel Sharp kernel Window Level 400 Window Width 1500 Window Level 50 Window Width 120 Sharp kernel (high pass filter) • preserving higher spatial frequencies • decreasing lower spatial frequencies • more noise • bone Soft kernel (low pass filter) • preserving lower spatial frequencies • reducing higher spatial frequencies • reduced noise and impaired spatial resolution • brain or soft tissue Kernel Properties
  • 4. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 4 CT Reconstruction Kernels Introduction Soft kernel Sharp kernel Window Level 400 Window Width 1500 Window Level 50 Window Width 120 Sharp kernel (high pass filter) • preserving higher spatial frequencies • decreasing lower spatial frequencies • more noise • bone Soft kernel (low pass filter) • preserving lower spatial frequencies • reducing higher spatial frequencies • reduced noise and impaired spatial resolution • brain or soft tissue Kernel Properties • Increased size of required storage • Additional cost and inconvenience
  • 5. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 5 • Supervised Method with Convolutional Neural Network • Mapping function between two different kernels or among limited number of pairs. Sang Min Lee, 2019 Da-in Eun, 2020 Deep Learning based Kernel Conversion Introduction
  • 7. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 7 Adaptive Instance Normalization (AdaIN) Proposed Method 1 − 𝛽 𝑥 + 𝛽 𝜎 𝑦 𝑥 − 𝜇 𝑥 𝜎 𝑥 + 𝜇 𝑦 Property • 𝛽 ∈ [𝟎, 𝟏] • Interpolation between styles of two inputs, 𝒙 and 𝒚 ൞ 𝑥, 𝛽 = 0 𝜎 𝑦 𝑥 − 𝜇 𝑥 𝜎 𝑥 + 𝜇 𝑦 , 𝛽 = 1 • 𝒙: content input, 𝒚: style input • AdaIN aligns the channel-wise mean and variance of 𝒙 to match those of 𝒚 • Not limited to a single style like Instance Normalization(IN) • Adaptively computes affine parameters from the style input 𝒚 𝐴𝑑𝑎𝐼𝑁(𝑥, 𝑦) = 𝝈 𝒚 𝑥 − 𝜇 𝑥 𝜎 𝑥 + 𝝁 𝒚 Definition
  • 8. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 8 Switchable CycleGAN with AdaIN Proposed Method [1] Gu, Jawook, 2020 Vanilla CycleGAN Switchable CycleGAN in 2 domain[1] Switchable CycleGAN in 3 domain 𝐴𝑑𝑎𝐼𝑁(𝑥, 𝑦) = 𝝈 𝒚 𝑥 − 𝜇 𝑥 𝜎 𝑥 + 𝝁 𝒚 Definition
  • 9. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 9 Architecture of the Generator Proposed Method Input Output Encoder Decoder
  • 10. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 10 Architecture of the Generator Proposed Method Input Output Encoder Decoder Source Domain AdaIN code generator Target Domain AdaIN code generator
  • 11. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 11 Loss Function Proposed Method where ℓ𝒕𝒐𝒕𝒂𝒍(𝑮, 𝑭, 𝑫𝑺, 𝑫𝑯) = −ℓ𝒅𝒊𝒔𝒄(𝑮, 𝑭, 𝑫𝑺, 𝑫𝑯) + 𝜆𝑐𝑦𝑐ℓ𝒄𝒚𝒄𝒍𝒆(𝑮, 𝑭) + 𝜆𝑖𝑑ℓ𝒊𝒅𝒆𝒏𝒕𝒊𝒕𝒚(𝑮, 𝑭) min 𝐺,𝐹 max 𝐷𝑆,𝐷𝐻 ℓ𝒕𝒐𝒕𝒂𝒍(𝑮, 𝑭, 𝑫𝑺, 𝑫𝑯), 2 Domain Switchable CycleGAN G D𝑆 D𝐻 G G G ℓ𝒄𝒚𝒄𝒍𝒆 𝑮, 𝑭 G D𝑆 D𝐻 G G G D𝑆 D𝐻 ℓ𝒅𝒊𝒔𝒄 𝑮, 𝑭, 𝑫𝑺, 𝑫𝑯 ℓ𝒊𝒅𝒆𝒏𝒕𝒊𝒕𝒚 𝑮, 𝑭 G D𝑆 D𝐻 G G G G G Reconstructed output Input
  • 12. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 12 Loss Function Proposed Method 3 Domain Switchable CycleGAN where ℓ𝒕𝒐𝒕𝒂𝒍 𝑮, 𝑭𝒆, 𝑭𝒅, 𝑫𝑺, 𝑫𝑯, 𝑫𝑴 = −ℓ𝒅𝒊𝒔𝒄 𝑮, 𝑭𝒆, 𝑭𝒅, 𝑫𝑺, 𝑫𝑯, 𝑫𝑴 + 𝜆𝑐𝑦𝑐ℓ𝒄𝒚𝒄𝒍𝒆 𝑮, 𝑭𝒆, 𝑭𝒅 +𝜆𝐴𝐸ℓ𝑨𝑬 𝑮, 𝑭𝒆, 𝑭𝒅 + 𝜆𝑠𝑐ℓ𝒔𝒄 𝑮, 𝑭𝒆, 𝑭𝒅 min 𝐺,𝐹𝑒,𝐹𝑑 max 𝐷𝑆,𝐷𝐻,𝐷𝑀 ℓ𝒕𝒐𝒕𝒂𝒍(𝑮, 𝑭𝒆, 𝑭𝒅, 𝑫𝑺, 𝑫𝑯, 𝑫𝑴), ( 0.0,1.0) G ( 1.0,0.0) G H → M → S H → S S → M → H S → H
  • 14. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 14 Switchable CycleGAN in 2 domain - Interpolation Results
  • 15. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 15 Switchable CycleGAN in 2 domain - Interpolation Results
  • 16. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 16 Switchable CycleGAN in 2 domain - Interpolation Results
  • 17. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 17 Switchable CycleGAN in 2 domain – Comparative Studies Results
  • 18. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 18 Results Switchable CycleGAN in 3 domain
  • 19. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 19 Results Switchable CycleGAN in 2 domain vs 3 domain
  • 20. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 20 Results Effectiveness of self-consistency loss
  • 22. Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN 22 Conclusion • Unsupervised deep-learning method for kernel conversion in CT images​ • Switchable CycleGAN combined with AdaIN allows training with single generator • Preventing the model from overfitting problem in case of small dataset ↓​ • Computationally efficient​ • Various images were generated by synergistically combining the two given kernels at inference stage • With intermediate kernel images, Switchable CycleGAN can be trained in 3 domain • Improvement in the quality of the generated kernel images • Range of interpolation can be controlled • The improved performance of our proposed model was proved with extensive experimental results