SlideShare une entreprise Scribd logo
1  sur  76
Télécharger pour lire hors ligne
Overview of GAN
▪ Generative
–Can generate samples
▪ Adversarial
–Trained by competing each other
▪ Networks
–Use neural networks
Definition
Generative Adversarial Networks
▪ Discriminative Models
–Given X, predict Y
–We learn P(Y | X) directly
–We cannot can generate samples
–Examples
• Logistic regression, SVM, CRF, Decision trees
▪ Generative models
–Given X, predict P(X|Y)
–We learn P(X, Y)
–We can generate samples from P(X)
–Examples
• Markov chains, Naïve Bayes, GMM
Discriminative Models vs Generative Models
Generative Models?
Richard Feynmann
▪ Adversarial Training between Discriminator vs Generator
–Discriminator is a classifier that determines whether given images is real data from the
world or fake data generated by generator.
–Proposed by Ian Goodfellow(NIPS 2014)
Discriminator vs Generator
Adversarial Networks?
https://www.oreilly.com/learning/generative-adversarial-networks-for-beginners?imm_mid=0f6436&cmp=em-data-na-na-newsltr_ai_20170918
VS
▪ Alternate the training of discriminator and generator until convergence(may not happen)
Overview
Training GAN
https://www.slideshare.net/xavigiro/deep-learning-for-computer-vision-generative-models-and-adversarial-training-upc-2016
▪ Fix the generator, then train discriminator to distinguish samples of real images from
samples generated by the generator
Discriminator Training
Training GAN
https://www.slideshare.net/xavigiro/deep-learning-for-computer-vision-generative-models-and-adversarial-training-upc-2016
▪ Fix the discriminator, then train generator from the feedback of discriminator using
samples generated by the generator
Generator Training
Training GAN
https://www.slideshare.net/xavigiro/deep-learning-for-computer-vision-generative-models-and-adversarial-training-upc-2016
▪ Training GAN is a minmax problem where
–The discriminator D tries to maximize its classification accuracy
–The generator G tries to minimize the discriminator’s classification accuracy
–The optimal solution for D
–The optimal solution for G
Mathematical Formulation
Training GAN
Iam Goodfellow et. al, NIPS 2014
Maximized by D Minimized by G
(in practice, we maximize )
Training Algorithm
Training GAN
Iam Goodfellow et. al, NIPS 2014
Discriminator Training
Generator Training
▪ With the optimal discriminator, training GAN is equivalent to minimizing Jensen-Shannon
divergence as
What happens during the training of GAN?
Why GAN Works?
http://videolectures.net/site/normal_dl/tag=1129740/deeplearning2017_courville_generative_models_01.pdf
Christian Leidig et. al, CVPR 2017
the only solution is
Visualization of samples generated from trained Generator
Generating Samples from GAN
Iam Goodfellow et. al, NIPS 2014
Deep Convolutional GAN
Improving Vanilla GAN
Alec Radford et. al, ICLR 2016
▪ LSUN bedroom dataset
Deep Convolutional GAN – Generated Samples
Improving Vanilla GAN
Alec Radford et. al, ICLR 2016
Deep Convolutional GAN – Vector Space Arithmetic
Improving Vanilla GAN
Alec Radford et. al, ICLR 2016
Improvement over Vanilla GAN
“GAN Zoo”
GAN Papers
https://github.com/hindupuravinash/the-gan-zoo
▪ Replace discriminator loss from binary cross entropy to least square loss
Least Square GAN(LS-GAN)
Improving Loss Function of GAN
Xudong Mao et. al, arXiv 2016
They don’t move.
0
1
▪ Is JS divergence good enough to train GAN?
Wasserstein GAN(WGAN)
Improving Loss Function of GAN
Martin Arjovsky et. al, arXiv 2016
Continuous everywhere and differentiable almost everywhere
Vanishing gradient and bad convergence
▪ WGAN objective function
▪ How can we efficiently enforce the Lipschitz
constraint on the critic D ?
–Weight clipping
Wasserstein GAN(WGAN)
Improving Loss Function of GAN
𝐷 𝑥1 − 𝐷 𝑥2 ≤ 𝐾 𝑥1 − 𝑥2 , K=1
Martin Arjovsky et. al, arXiv 2016
▪ Learning curve and sample quality
Wasserstein GAN(WGAN)
Improving Loss Function of GAN
Vanilla GAN
WGAN
Martin Arjovsky et. al, arXiv 2016
▪ Issues with Weight Clipping
–Fail to capture higher moments of the data distribution
–Either exploding or vanishing gradient
Wasserstein GAN with Gradient Penalty(WGAN-GP)
Improving Loss Function of GAN
Weight
Clipping
Gradient
Clipping
Ishaan Gulrajani et. al, NIPS 2017
▪ WGAN with Gradient Penalty
–Penalize the norm of the gradient instead of clipping the weights of critics
Wasserstein GAN with Gradient Penalty(WGAN-GP)
Improving Loss Function of GAN
Ishaan Gulrajani et. al, NIPS 2017
▪ Comparison of various loss functions and their sample quality
Wasserstein GAN with Gradient Penalty(WGAN-GP)
Improving Loss Function of GAN
Ishaan Gulrajani et. al, NIPS 2017
Generation of Conditioned Samples by GANs
▪ Conditioning the model on additional information for better multi-modal learning
Conditional GAN(CGAN)
Conditional Generation
Mirza et. al, arXiv 2014
https://github.com/hwalsuklee/tensorflow-generative-model-collections
▪ Disentangle individual dimensions in latent vector for capturing key attributes
InfoGAN
Conditional Generation
Xi Chen et al arXiv 2016
https://github.com/hwalsuklee/tensorflow-generative-model-collections
▪ Examples
InfoGAN
Conditional Generation
Xi Chen et al arXiv 2016
▪ Use both real/fake and label classifiers for discriminator training
Auxiliary Classifier GAN(AC-GAN)
Conditional Generation
Augustus Odena et al arXiv 2016
https://github.com/hwalsuklee/tensorflow-generative-model-collections
Recent GANs and Their Applications
▪ “Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network”
–Perceptual Loss
GAN for Image Super Resolution
SRGAN
Chrisitan Leidig et al, CVPR 2017
▪ Super Resolution Results
GAN for Image Super Resolution
SRGAN
Chrisitan Leidig et al, CVPR 2017
▪ Super Resolution Results
GAN for Image Super Resolution
SRGAN
Chrisitan Leidig et al, CVPR 2017
▪ “Image-to-Image Translation with Conditional Adversarial Networks”
Conditional GAN for Image Domain Transfer
Image-to-Image Translation
Phillip Isola et al, CVPR 2017
▪ Image Translation Results
Conditional GAN for Image Domain Transfer
Image-to-Image Translation
Phillip Isola et al, CVPR 2017
▪ Image Translation Results
Conditional GAN for Image Domain Transfer
Image-to-Image Translation
Phillip Isola et al, CVPR 2017
▪ “Generative Adversarial Text to Image Synthesis”
–Generator is conditioned on text embedding
–Discriminator uses both visual and textual features by concatenation
Conditional GAN for Text to Image Translation
Text2Image
Scott Reed et al, ICML 2016
▪ Text-to-Image Translation Results
Conditional GAN for Text to Image Translation
Text2Image
Scott Reed et al, ICML 2016
▪ “Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks”
–Generate high-resolution images from text by stacking conditional GANs
Stacked Conditional GAN for Text to Image Translation
StackGAN
Han Zhang et al, ICCV 2017
▪ Text-to-Image Translation Results
Stacked Conditional GAN for Text to Image Translation
StackGAN
Han Zhang et al, ICCV 2017
▪ Text-to-Image Translation Results
Stacked Conditional GAN for Text to Image Translation
StackGAN
Han Zhang et al, ICCV 2017
▪ “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”
Unpaired Image Translation
CycleGAN
Jun-Yan Zhu et al, ICCV 2017
▪ Paired/Unpaired and Generated Image/Reconstruction
Unpaired Image Translation
CycleGAN
Jun-Yan Zhu et al, ICCV 2017
▪ Image Translation Example
Unpaired Image Translation
CycleGAN
Jun-Yan Zhu et al, ICCV 2017
▪ “StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation”
–Instead of training generators for each source-domain pair, we can train one generator handling
multiple domains to utilize all training dataset for all domain pairs and even for different dataset
Multi-domain Image-to-Image Translation with a Single Network
StarGAN
for real
for fake
Yunjey Choi et. al, CVPR 2018
▪ Multi-domain Translation Result
Multi-domain Image-to-Image Translation with a Single Network
StarGAN
Yunjey Choi et. al, CVPR 2018
▪ Use of ‘mask vector’ to jointly train multiple dataset
Multi-domain Image-to-Image Translation with a Single Network
StarGAN
Yunjey Choi et. al, CVPR 2018
▪ Use of ‘mask vector’ to jointly train multiple dataset
Multi-domain Image-to-Image Translation with a Single Network
StarGAN
Yunjey Choi et. al, CVPR 2018
▪ Multi-domain Translation Results
Multi-domain Image-to-Image Translation with a Single Network
StarGAN
Yunjey Choi et. al, CVPR 2018
▪ “Learning from Simulated and Unsupervised Images through Adversarial Training”
Refining Simulated Image for Data Augmentation
SimGAN
Ashish Shrivastava et. al, CVPR 2017
Self-regularization loss
▪ “Learning from Simulated and Unsupervised Images through Adversarial Training”
Refining Simulated Image for Data Augmentation
SimGAN
Ashish Shrivastava et. al, CVPR 2017
Visual Turing Test d=7 degree
GANs in Medical Imaging
–In many cases, data augmentation techniques used in natural images does not
semantically make sense in medical image
(flips, rotations, scale shifts, color shifts)
–Physically-plausible deformations or morphological transform can be used in limited
cases.
–More augmentation choices for texture classification problems.
Data Augmentation for Effective Training Set Expansion
Medical Data Generation
Source : H. R. Roth et. al., MICCAI, 2015
Generation of synthetic dataset for dataset expansion
Medical Data Generation
M.J.M. Chuquicusma, ISBI 2018
▪ “How To Fool Radiologists with Generative Adversarial Networks? A Visual Turing Test For
Lung Cancer Diagnosis”
Generation of synthetic dataset for dataset expansion
Medical Data Generation
M.J.M. Chuquicusma, ISBI 2018
▪ Visual Turing Test
▪ “Synthetic Medical Images from Dual Generative Adversarial Networks”
Generation of Fundus Image using Dual GANs
Medical Data Generation
John T. Guibas et. al, NIPS Workshop 2017
▪ “Synthetic Medical Images from Dual Generative Adversarial Networks”
Generation of Fundus Image using Dual GANs
Medical Data Generation
John T. Guibas et. al, NIPS Workshop 2017
▪ “Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification”
Liver Lesion Generation for Data Augmentation
Medical Data Generation
Maayan Frid-Ada et. al, ISBI 2018
Real Synthetic
▪ “Generalization of Deep Neural Networks for Chest Pathology Classification in X-ray using
Generative Adversarial Networks”
Chest X-ray Generation for Data Augmentation
Medical Data Generation
Hojjat Salehinejad et. al, ICASSP 2018
▪ Generated Samples and Performance Improvement by Synthetic Augmentation
Chest X-ray Generation for Data Augmentation
Medical Data Generation
Hojjat Salehinejad et. al, ICASSP 2018
▪ “Visual Feature Attribution using Wasserstein GANs “
VA-GAN : Understanding Visual Feature Attribution for Alzheimer Disease
Visual Feature Attribution
Christian F. Baumgatrner et. al, arXiv 2018
Overall Objective
GAN Loss Term
RegularizationTerm
▪ “Visual Feature Attribution using Wasserstein GANs “
VA-GAN : Understanding Visual Feature Attribution for Alzheimer Disease
Visual Feature Attribution
Christian F. Baumgatrner et. al, arXiv 2018
Enhance the quality of low-dose CT to normal-dose CT
Synthesis or Enhancement of Medical Image
Dong Nie et. al, MICCAI 2017
▪ “Medical Image Synthesis using Context-aware Generative Adversarial Networks”
Unpaired image translation from MR to CT using CycleGAN
Synthesis or Enhancement of Medical Image
Jelmer M. Wolterink et. al, MICCAI 2017 Workshop
Setting Mean Absolute Error
Paired Voxel-wise Loss 89.4 ± 6.8 HU
Unpaired Cycle Consistency Loss 73.7 ± 2.3 HU
▪ “Deep MR to CT Synthesis using Unpaired Data”
Enhance the quality of low-dose CT to normal-dose CT
Synthesis or Enhancement of Medical Image
J. M. Wolterink et. al, IEEE Trans. Medical Imaging
▪ “Generative Adversarial Networks for Noise Reduction in Low-Dose CT”
Deep learning for undersampled MRI reconstruction
Synthesis or Enhancement of Medical Image
Tran Min Quan et. al, arXiv 2018
▪ “Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss”
–Problem of compressed sensing MRI reconstruction
–CS-MRI using GAN objective
Deep learning for undersampled MRI reconstruction
Synthesis or Enhancement of Medical Image
Tran Min Quan et. al, arXiv 2018
▪ “Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss”
Deep learning for undersampled MRI reconstruction
Synthesis or Enhancement of Medical Image
Tran Min Quan et. al, arXiv 2018
▪ Experimental Results for Understampled MRI Reconstruction using GAN
Generation of segmentation mask undistinguishable from physician’s mask
Physician Friendly Loss for Segmentation
Source : P. Costa(2017), VUNO(2017)
▪ “Retinal Vessel Segmentation in Fundoscopic Images with Generative Adversarial Networks”
▪ “Adversarial Networks for the Detection of Aggressive Prostate Cancer”
Generation of segmentation mask undistinguishable from physician’s mask
Physician Friendly Loss for Segmentation
Source : S. Kohl et. al(2017)
▪ “SegAN : Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation”
SegAN : Adversarial Network with Multi-scale Loss
Physician Friendly Loss for Segmentation
Yuan Xue et. al, arXiv 2017
▪ “Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-
Consistency Generative Adversarial Network”
Segmentation of Multimodal Images using Image-to-Image Translation
Multimodal Image Segmentation
Zizhao Zhang et. al, CVPR 2018
▪ “Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-
Consistency Generative Adversarial Network”
Segmentation of Multimodal Images using Image-to-Image Translation
Multimodal Image Segmentation
Zizhao Zhang et. al, CVPR 2018
Conclusion
▪ Image Generation
– Generation of rare cases
– Understanding latent structure of lesions
– Improving the performance of diagnostic models
▪ Image Synthesis and Translation
– Noise reduction, modality translation
– Accelerating image acquisition time
– Improving diagnostic performance
▪ Lesion Detection and Segmentation
– More physician friendly training
– Better performance for lesions or organs with complex structure
▪ Future of GANs in Medical Imaging
– More GANs to come in medical imaging with clinical and commercial values
More GANs in Medical Imaging
Future of GANs
khwan.jung@vuno.co
hello@vuno.co
Putting the world’s medical data to work

Contenu connexe

Tendances

“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...Edge AI and Vision Alliance
 
GAN - Theory and Applications
GAN - Theory and ApplicationsGAN - Theory and Applications
GAN - Theory and ApplicationsEmanuele Ghelfi
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networksYunjey Choi
 
Generative Adversarial Networks
Generative Adversarial NetworksGenerative Adversarial Networks
Generative Adversarial NetworksMustafa Yagmur
 
Basic Generative Adversarial Networks
Basic Generative Adversarial NetworksBasic Generative Adversarial Networks
Basic Generative Adversarial NetworksDong Heon Cho
 
Explicit Density Models
Explicit Density ModelsExplicit Density Models
Explicit Density ModelsSangwoo Mo
 
Image-to-Image Translation with Conditional Adversarial Nets (UPC Reading Group)
Image-to-Image Translation with Conditional Adversarial Nets (UPC Reading Group)Image-to-Image Translation with Conditional Adversarial Nets (UPC Reading Group)
Image-to-Image Translation with Conditional Adversarial Nets (UPC Reading Group)Universitat Politècnica de Catalunya
 
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
 
A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs)
 A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs) A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs)
A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs)Thomas da Silva Paula
 
Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningMohamed Loey
 
Deep Generative Models
Deep Generative Models Deep Generative Models
Deep Generative Models Chia-Wen Cheng
 
SPIHT(Set Partitioning In Hierarchical Trees)
SPIHT(Set Partitioning In Hierarchical Trees)SPIHT(Set Partitioning In Hierarchical Trees)
SPIHT(Set Partitioning In Hierarchical Trees)M.k. Praveen
 
A Short Introduction to Generative Adversarial Networks
A Short Introduction to Generative Adversarial NetworksA Short Introduction to Generative Adversarial Networks
A Short Introduction to Generative Adversarial NetworksJong Wook Kim
 
Variational Autoencoder
Variational AutoencoderVariational Autoencoder
Variational AutoencoderMark Chang
 
Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Unde...
Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Unde...Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Unde...
Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Unde...Vitaly Bondar
 
GANs Presentation.pptx
GANs Presentation.pptxGANs Presentation.pptx
GANs Presentation.pptxMAHMOUD729246
 
Image classification using CNN
Image classification using CNNImage classification using CNN
Image classification using CNNNoura Hussein
 

Tendances (20)

“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
“An Introduction to Data Augmentation Techniques in ML Frameworks,” a Present...
 
GAN - Theory and Applications
GAN - Theory and ApplicationsGAN - Theory and Applications
GAN - Theory and Applications
 
Generative adversarial networks
Generative adversarial networksGenerative adversarial networks
Generative adversarial networks
 
Generative Adversarial Networks
Generative Adversarial NetworksGenerative Adversarial Networks
Generative Adversarial Networks
 
Robustness in deep learning
Robustness in deep learningRobustness in deep learning
Robustness in deep learning
 
Basic Generative Adversarial Networks
Basic Generative Adversarial NetworksBasic Generative Adversarial Networks
Basic Generative Adversarial Networks
 
Style gan
Style ganStyle gan
Style gan
 
Explicit Density Models
Explicit Density ModelsExplicit Density Models
Explicit Density Models
 
Image-to-Image Translation with Conditional Adversarial Nets (UPC Reading Group)
Image-to-Image Translation with Conditional Adversarial Nets (UPC Reading Group)Image-to-Image Translation with Conditional Adversarial Nets (UPC Reading Group)
Image-to-Image Translation with Conditional Adversarial Nets (UPC Reading Group)
 
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...
 
A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs)
 A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs) A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs)
A (Very) Gentle Introduction to Generative Adversarial Networks (a.k.a GANs)
 
Convolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep LearningConvolutional Neural Network Models - Deep Learning
Convolutional Neural Network Models - Deep Learning
 
Deep Generative Models
Deep Generative Models Deep Generative Models
Deep Generative Models
 
SPIHT(Set Partitioning In Hierarchical Trees)
SPIHT(Set Partitioning In Hierarchical Trees)SPIHT(Set Partitioning In Hierarchical Trees)
SPIHT(Set Partitioning In Hierarchical Trees)
 
A Short Introduction to Generative Adversarial Networks
A Short Introduction to Generative Adversarial NetworksA Short Introduction to Generative Adversarial Networks
A Short Introduction to Generative Adversarial Networks
 
Variational Autoencoder
Variational AutoencoderVariational Autoencoder
Variational Autoencoder
 
Module 31
Module 31Module 31
Module 31
 
Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Unde...
Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Unde...Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Unde...
Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Unde...
 
GANs Presentation.pptx
GANs Presentation.pptxGANs Presentation.pptx
GANs Presentation.pptx
 
Image classification using CNN
Image classification using CNNImage classification using CNN
Image classification using CNN
 

Similaire à Generative Adversarial Networks and Their Medical Imaging Applications

(20180715) ksiim gan in medical imaging - vuno - kyuhwan jung
(20180715) ksiim   gan in medical imaging - vuno - kyuhwan jung(20180715) ksiim   gan in medical imaging - vuno - kyuhwan jung
(20180715) ksiim gan in medical imaging - vuno - kyuhwan jungKyuhwan Jung
 
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...宏毅 李
 
Generative Adversarial Networks and Their Applications in Medical Imaging
Generative Adversarial Networks  and Their Applications in Medical ImagingGenerative Adversarial Networks  and Their Applications in Medical Imaging
Generative Adversarial Networks and Their Applications in Medical ImagingSanghoon Hong
 
Generative Adversarial Networks 2
Generative Adversarial Networks 2Generative Adversarial Networks 2
Generative Adversarial Networks 2Alireza Shafaei
 
Generative adversarial network and its applications to speech signal and natu...
Generative adversarial network and its applications to speech signal and natu...Generative adversarial network and its applications to speech signal and natu...
Generative adversarial network and its applications to speech signal and natu...宏毅 李
 
Generative Adversarial Network and its Applications to Speech Processing an...
Generative Adversarial Network and its Applications to Speech Processing an...Generative Adversarial Network and its Applications to Speech Processing an...
Generative Adversarial Network and its Applications to Speech Processing an...宏毅 李
 
Face-GAN project report.pptx
Face-GAN project report.pptxFace-GAN project report.pptx
Face-GAN project report.pptxAndleebFatima16
 
[PR12] intro. to gans jaejun yoo
[PR12] intro. to gans   jaejun yoo[PR12] intro. to gans   jaejun yoo
[PR12] intro. to gans jaejun yooJaeJun Yoo
 
PROGRESSIVE GROWING OF GAN S FOR I MPROVED QUALITY , STABILITY , AND VARIATION
PROGRESSIVE GROWING OF GAN S FOR I MPROVED QUALITY , STABILITY , AND VARIATIONPROGRESSIVE GROWING OF GAN S FOR I MPROVED QUALITY , STABILITY , AND VARIATION
PROGRESSIVE GROWING OF GAN S FOR I MPROVED QUALITY , STABILITY , AND VARIATIONWilly Marroquin (WillyDevNET)
 
보다 유연한 이미지 변환을 하려면?
보다 유연한 이미지 변환을 하려면?보다 유연한 이미지 변환을 하려면?
보다 유연한 이미지 변환을 하려면?광희 이
 
brief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANsbrief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANsParham Zilouchian
 
(20180728) kosaim workshop vuno - kyuhwan jung
(20180728) kosaim workshop   vuno - kyuhwan jung(20180728) kosaim workshop   vuno - kyuhwan jung
(20180728) kosaim workshop vuno - kyuhwan jungKyuhwan Jung
 
Google Dev Group Yangon (2020) AI Talk (Creative AI in Action)
Google Dev Group Yangon (2020)  AI Talk (Creative AI in Action)Google Dev Group Yangon (2020)  AI Talk (Creative AI in Action)
Google Dev Group Yangon (2020) AI Talk (Creative AI in Action)WaiYanNyeinNaing
 
Pratik ibm-open power-ppt
Pratik ibm-open power-pptPratik ibm-open power-ppt
Pratik ibm-open power-pptVaibhav R
 
Webpage Personalization and User Profiling
Webpage Personalization and User ProfilingWebpage Personalization and User Profiling
Webpage Personalization and User Profilingyingfeng
 
Reading group gan - 20170417
Reading group   gan - 20170417Reading group   gan - 20170417
Reading group gan - 20170417Shuai Zhang
 
Automatic Attendance System using CNN
Automatic Attendance System using CNNAutomatic Attendance System using CNN
Automatic Attendance System using CNNPinaki Ranjan Sarkar
 

Similaire à Generative Adversarial Networks and Their Medical Imaging Applications (20)

(20180715) ksiim gan in medical imaging - vuno - kyuhwan jung
(20180715) ksiim   gan in medical imaging - vuno - kyuhwan jung(20180715) ksiim   gan in medical imaging - vuno - kyuhwan jung
(20180715) ksiim gan in medical imaging - vuno - kyuhwan jung
 
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
ICASSP 2018 Tutorial: Generative Adversarial Network and its Applications to ...
 
Generative Adversarial Networks and Their Applications in Medical Imaging
Generative Adversarial Networks  and Their Applications in Medical ImagingGenerative Adversarial Networks  and Their Applications in Medical Imaging
Generative Adversarial Networks and Their Applications in Medical Imaging
 
Generative Adversarial Networks 2
Generative Adversarial Networks 2Generative Adversarial Networks 2
Generative Adversarial Networks 2
 
Gan intro
Gan introGan intro
Gan intro
 
Generative adversarial network and its applications to speech signal and natu...
Generative adversarial network and its applications to speech signal and natu...Generative adversarial network and its applications to speech signal and natu...
Generative adversarial network and its applications to speech signal and natu...
 
Generative Adversarial Network and its Applications to Speech Processing an...
Generative Adversarial Network and its Applications to Speech Processing an...Generative Adversarial Network and its Applications to Speech Processing an...
Generative Adversarial Network and its Applications to Speech Processing an...
 
Face-GAN project report.pptx
Face-GAN project report.pptxFace-GAN project report.pptx
Face-GAN project report.pptx
 
Face-GAN project report
Face-GAN project reportFace-GAN project report
Face-GAN project report
 
[PR12] intro. to gans jaejun yoo
[PR12] intro. to gans   jaejun yoo[PR12] intro. to gans   jaejun yoo
[PR12] intro. to gans jaejun yoo
 
PROGRESSIVE GROWING OF GAN S FOR I MPROVED QUALITY , STABILITY , AND VARIATION
PROGRESSIVE GROWING OF GAN S FOR I MPROVED QUALITY , STABILITY , AND VARIATIONPROGRESSIVE GROWING OF GAN S FOR I MPROVED QUALITY , STABILITY , AND VARIATION
PROGRESSIVE GROWING OF GAN S FOR I MPROVED QUALITY , STABILITY , AND VARIATION
 
보다 유연한 이미지 변환을 하려면?
보다 유연한 이미지 변환을 하려면?보다 유연한 이미지 변환을 하려면?
보다 유연한 이미지 변환을 하려면?
 
brief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANsbrief Introduction to Different Kinds of GANs
brief Introduction to Different Kinds of GANs
 
(20180728) kosaim workshop vuno - kyuhwan jung
(20180728) kosaim workshop   vuno - kyuhwan jung(20180728) kosaim workshop   vuno - kyuhwan jung
(20180728) kosaim workshop vuno - kyuhwan jung
 
Google Dev Group Yangon (2020) AI Talk (Creative AI in Action)
Google Dev Group Yangon (2020)  AI Talk (Creative AI in Action)Google Dev Group Yangon (2020)  AI Talk (Creative AI in Action)
Google Dev Group Yangon (2020) AI Talk (Creative AI in Action)
 
Pratik ibm-open power-ppt
Pratik ibm-open power-pptPratik ibm-open power-ppt
Pratik ibm-open power-ppt
 
Webpage Personalization and User Profiling
Webpage Personalization and User ProfilingWebpage Personalization and User Profiling
Webpage Personalization and User Profiling
 
gan.pdf
gan.pdfgan.pdf
gan.pdf
 
Reading group gan - 20170417
Reading group   gan - 20170417Reading group   gan - 20170417
Reading group gan - 20170417
 
Automatic Attendance System using CNN
Automatic Attendance System using CNNAutomatic Attendance System using CNN
Automatic Attendance System using CNN
 

Dernier

NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...Amil Baba Dawood bangali
 
LLMs, LMMs, their Improvement Suggestions and the Path towards AGI
LLMs, LMMs, their Improvement Suggestions and the Path towards AGILLMs, LMMs, their Improvement Suggestions and the Path towards AGI
LLMs, LMMs, their Improvement Suggestions and the Path towards AGIThomas Poetter
 
Conf42-LLM_Adding Generative AI to Real-Time Streaming Pipelines
Conf42-LLM_Adding Generative AI to Real-Time Streaming PipelinesConf42-LLM_Adding Generative AI to Real-Time Streaming Pipelines
Conf42-LLM_Adding Generative AI to Real-Time Streaming PipelinesTimothy Spann
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改yuu sss
 
Semantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxSemantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxMike Bennett
 
Real-Time AI Streaming - AI Max Princeton
Real-Time AI  Streaming - AI Max PrincetonReal-Time AI  Streaming - AI Max Princeton
Real-Time AI Streaming - AI Max PrincetonTimothy Spann
 
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理e4aez8ss
 
RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.natarajan8993
 
Multiple time frame trading analysis -brianshannon.pdf
Multiple time frame trading analysis -brianshannon.pdfMultiple time frame trading analysis -brianshannon.pdf
Multiple time frame trading analysis -brianshannon.pdfchwongval
 
Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Cathrine Wilhelmsen
 
毕业文凭制作#回国入职#diploma#degree美国加州州立大学北岭分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#de...
毕业文凭制作#回国入职#diploma#degree美国加州州立大学北岭分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#de...毕业文凭制作#回国入职#diploma#degree美国加州州立大学北岭分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#de...
毕业文凭制作#回国入职#diploma#degree美国加州州立大学北岭分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#de...ttt fff
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queensdataanalyticsqueen03
 
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default  Presentation : Data Analysis Project PPTPredictive Analysis for Loan Default  Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPTBoston Institute of Analytics
 
FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024
FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024
FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024Susanna-Assunta Sansone
 
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一F La
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFAAndrei Kaleshka
 
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一F sss
 
Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 217djon017
 
ASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel CanterASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel Cantervoginip
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDRafezzaman
 

Dernier (20)

NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
 
LLMs, LMMs, their Improvement Suggestions and the Path towards AGI
LLMs, LMMs, their Improvement Suggestions and the Path towards AGILLMs, LMMs, their Improvement Suggestions and the Path towards AGI
LLMs, LMMs, their Improvement Suggestions and the Path towards AGI
 
Conf42-LLM_Adding Generative AI to Real-Time Streaming Pipelines
Conf42-LLM_Adding Generative AI to Real-Time Streaming PipelinesConf42-LLM_Adding Generative AI to Real-Time Streaming Pipelines
Conf42-LLM_Adding Generative AI to Real-Time Streaming Pipelines
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
 
Semantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptxSemantic Shed - Squashing and Squeezing.pptx
Semantic Shed - Squashing and Squeezing.pptx
 
Real-Time AI Streaming - AI Max Princeton
Real-Time AI  Streaming - AI Max PrincetonReal-Time AI  Streaming - AI Max Princeton
Real-Time AI Streaming - AI Max Princeton
 
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
科罗拉多大学波尔得分校毕业证学位证成绩单-可办理
 
RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.
 
Multiple time frame trading analysis -brianshannon.pdf
Multiple time frame trading analysis -brianshannon.pdfMultiple time frame trading analysis -brianshannon.pdf
Multiple time frame trading analysis -brianshannon.pdf
 
Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)
 
毕业文凭制作#回国入职#diploma#degree美国加州州立大学北岭分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#de...
毕业文凭制作#回国入职#diploma#degree美国加州州立大学北岭分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#de...毕业文凭制作#回国入职#diploma#degree美国加州州立大学北岭分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#de...
毕业文凭制作#回国入职#diploma#degree美国加州州立大学北岭分校毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#de...
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queens
 
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default  Presentation : Data Analysis Project PPTPredictive Analysis for Loan Default  Presentation : Data Analysis Project PPT
Predictive Analysis for Loan Default Presentation : Data Analysis Project PPT
 
FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024
FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024
FAIR, FAIRsharing, FAIR Cookbook and ELIXIR - Sansone SA - Boston 2024
 
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
办理(Vancouver毕业证书)加拿大温哥华岛大学毕业证成绩单原版一比一
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFA
 
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
 
Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2Easter Eggs From Star Wars and in cars 1 and 2
Easter Eggs From Star Wars and in cars 1 and 2
 
ASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel CanterASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel Canter
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
 

Generative Adversarial Networks and Their Medical Imaging Applications

  • 1.
  • 3. ▪ Generative –Can generate samples ▪ Adversarial –Trained by competing each other ▪ Networks –Use neural networks Definition Generative Adversarial Networks
  • 4. ▪ Discriminative Models –Given X, predict Y –We learn P(Y | X) directly –We cannot can generate samples –Examples • Logistic regression, SVM, CRF, Decision trees ▪ Generative models –Given X, predict P(X|Y) –We learn P(X, Y) –We can generate samples from P(X) –Examples • Markov chains, Naïve Bayes, GMM Discriminative Models vs Generative Models Generative Models? Richard Feynmann
  • 5. ▪ Adversarial Training between Discriminator vs Generator –Discriminator is a classifier that determines whether given images is real data from the world or fake data generated by generator. –Proposed by Ian Goodfellow(NIPS 2014) Discriminator vs Generator Adversarial Networks? https://www.oreilly.com/learning/generative-adversarial-networks-for-beginners?imm_mid=0f6436&cmp=em-data-na-na-newsltr_ai_20170918 VS
  • 6. ▪ Alternate the training of discriminator and generator until convergence(may not happen) Overview Training GAN https://www.slideshare.net/xavigiro/deep-learning-for-computer-vision-generative-models-and-adversarial-training-upc-2016
  • 7. ▪ Fix the generator, then train discriminator to distinguish samples of real images from samples generated by the generator Discriminator Training Training GAN https://www.slideshare.net/xavigiro/deep-learning-for-computer-vision-generative-models-and-adversarial-training-upc-2016
  • 8. ▪ Fix the discriminator, then train generator from the feedback of discriminator using samples generated by the generator Generator Training Training GAN https://www.slideshare.net/xavigiro/deep-learning-for-computer-vision-generative-models-and-adversarial-training-upc-2016
  • 9. ▪ Training GAN is a minmax problem where –The discriminator D tries to maximize its classification accuracy –The generator G tries to minimize the discriminator’s classification accuracy –The optimal solution for D –The optimal solution for G Mathematical Formulation Training GAN Iam Goodfellow et. al, NIPS 2014 Maximized by D Minimized by G (in practice, we maximize )
  • 10. Training Algorithm Training GAN Iam Goodfellow et. al, NIPS 2014 Discriminator Training Generator Training
  • 11. ▪ With the optimal discriminator, training GAN is equivalent to minimizing Jensen-Shannon divergence as What happens during the training of GAN? Why GAN Works? http://videolectures.net/site/normal_dl/tag=1129740/deeplearning2017_courville_generative_models_01.pdf Christian Leidig et. al, CVPR 2017 the only solution is
  • 12. Visualization of samples generated from trained Generator Generating Samples from GAN Iam Goodfellow et. al, NIPS 2014
  • 13. Deep Convolutional GAN Improving Vanilla GAN Alec Radford et. al, ICLR 2016
  • 14. ▪ LSUN bedroom dataset Deep Convolutional GAN – Generated Samples Improving Vanilla GAN Alec Radford et. al, ICLR 2016
  • 15. Deep Convolutional GAN – Vector Space Arithmetic Improving Vanilla GAN Alec Radford et. al, ICLR 2016
  • 18. ▪ Replace discriminator loss from binary cross entropy to least square loss Least Square GAN(LS-GAN) Improving Loss Function of GAN Xudong Mao et. al, arXiv 2016 They don’t move. 0 1
  • 19. ▪ Is JS divergence good enough to train GAN? Wasserstein GAN(WGAN) Improving Loss Function of GAN Martin Arjovsky et. al, arXiv 2016 Continuous everywhere and differentiable almost everywhere Vanishing gradient and bad convergence
  • 20. ▪ WGAN objective function ▪ How can we efficiently enforce the Lipschitz constraint on the critic D ? –Weight clipping Wasserstein GAN(WGAN) Improving Loss Function of GAN 𝐷 𝑥1 − 𝐷 𝑥2 ≤ 𝐾 𝑥1 − 𝑥2 , K=1 Martin Arjovsky et. al, arXiv 2016
  • 21. ▪ Learning curve and sample quality Wasserstein GAN(WGAN) Improving Loss Function of GAN Vanilla GAN WGAN Martin Arjovsky et. al, arXiv 2016
  • 22. ▪ Issues with Weight Clipping –Fail to capture higher moments of the data distribution –Either exploding or vanishing gradient Wasserstein GAN with Gradient Penalty(WGAN-GP) Improving Loss Function of GAN Weight Clipping Gradient Clipping Ishaan Gulrajani et. al, NIPS 2017
  • 23. ▪ WGAN with Gradient Penalty –Penalize the norm of the gradient instead of clipping the weights of critics Wasserstein GAN with Gradient Penalty(WGAN-GP) Improving Loss Function of GAN Ishaan Gulrajani et. al, NIPS 2017
  • 24. ▪ Comparison of various loss functions and their sample quality Wasserstein GAN with Gradient Penalty(WGAN-GP) Improving Loss Function of GAN Ishaan Gulrajani et. al, NIPS 2017
  • 25. Generation of Conditioned Samples by GANs
  • 26. ▪ Conditioning the model on additional information for better multi-modal learning Conditional GAN(CGAN) Conditional Generation Mirza et. al, arXiv 2014 https://github.com/hwalsuklee/tensorflow-generative-model-collections
  • 27. ▪ Disentangle individual dimensions in latent vector for capturing key attributes InfoGAN Conditional Generation Xi Chen et al arXiv 2016 https://github.com/hwalsuklee/tensorflow-generative-model-collections
  • 29. ▪ Use both real/fake and label classifiers for discriminator training Auxiliary Classifier GAN(AC-GAN) Conditional Generation Augustus Odena et al arXiv 2016 https://github.com/hwalsuklee/tensorflow-generative-model-collections
  • 30. Recent GANs and Their Applications
  • 31. ▪ “Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network” –Perceptual Loss GAN for Image Super Resolution SRGAN Chrisitan Leidig et al, CVPR 2017
  • 32. ▪ Super Resolution Results GAN for Image Super Resolution SRGAN Chrisitan Leidig et al, CVPR 2017
  • 33. ▪ Super Resolution Results GAN for Image Super Resolution SRGAN Chrisitan Leidig et al, CVPR 2017
  • 34. ▪ “Image-to-Image Translation with Conditional Adversarial Networks” Conditional GAN for Image Domain Transfer Image-to-Image Translation Phillip Isola et al, CVPR 2017
  • 35. ▪ Image Translation Results Conditional GAN for Image Domain Transfer Image-to-Image Translation Phillip Isola et al, CVPR 2017
  • 36. ▪ Image Translation Results Conditional GAN for Image Domain Transfer Image-to-Image Translation Phillip Isola et al, CVPR 2017
  • 37. ▪ “Generative Adversarial Text to Image Synthesis” –Generator is conditioned on text embedding –Discriminator uses both visual and textual features by concatenation Conditional GAN for Text to Image Translation Text2Image Scott Reed et al, ICML 2016
  • 38. ▪ Text-to-Image Translation Results Conditional GAN for Text to Image Translation Text2Image Scott Reed et al, ICML 2016
  • 39. ▪ “Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks” –Generate high-resolution images from text by stacking conditional GANs Stacked Conditional GAN for Text to Image Translation StackGAN Han Zhang et al, ICCV 2017
  • 40. ▪ Text-to-Image Translation Results Stacked Conditional GAN for Text to Image Translation StackGAN Han Zhang et al, ICCV 2017
  • 41. ▪ Text-to-Image Translation Results Stacked Conditional GAN for Text to Image Translation StackGAN Han Zhang et al, ICCV 2017
  • 42. ▪ “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks” Unpaired Image Translation CycleGAN Jun-Yan Zhu et al, ICCV 2017
  • 43. ▪ Paired/Unpaired and Generated Image/Reconstruction Unpaired Image Translation CycleGAN Jun-Yan Zhu et al, ICCV 2017
  • 44. ▪ Image Translation Example Unpaired Image Translation CycleGAN Jun-Yan Zhu et al, ICCV 2017
  • 45. ▪ “StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation” –Instead of training generators for each source-domain pair, we can train one generator handling multiple domains to utilize all training dataset for all domain pairs and even for different dataset Multi-domain Image-to-Image Translation with a Single Network StarGAN for real for fake Yunjey Choi et. al, CVPR 2018
  • 46. ▪ Multi-domain Translation Result Multi-domain Image-to-Image Translation with a Single Network StarGAN Yunjey Choi et. al, CVPR 2018
  • 47. ▪ Use of ‘mask vector’ to jointly train multiple dataset Multi-domain Image-to-Image Translation with a Single Network StarGAN Yunjey Choi et. al, CVPR 2018
  • 48. ▪ Use of ‘mask vector’ to jointly train multiple dataset Multi-domain Image-to-Image Translation with a Single Network StarGAN Yunjey Choi et. al, CVPR 2018
  • 49. ▪ Multi-domain Translation Results Multi-domain Image-to-Image Translation with a Single Network StarGAN Yunjey Choi et. al, CVPR 2018
  • 50. ▪ “Learning from Simulated and Unsupervised Images through Adversarial Training” Refining Simulated Image for Data Augmentation SimGAN Ashish Shrivastava et. al, CVPR 2017 Self-regularization loss
  • 51. ▪ “Learning from Simulated and Unsupervised Images through Adversarial Training” Refining Simulated Image for Data Augmentation SimGAN Ashish Shrivastava et. al, CVPR 2017 Visual Turing Test d=7 degree
  • 52. GANs in Medical Imaging
  • 53. –In many cases, data augmentation techniques used in natural images does not semantically make sense in medical image (flips, rotations, scale shifts, color shifts) –Physically-plausible deformations or morphological transform can be used in limited cases. –More augmentation choices for texture classification problems. Data Augmentation for Effective Training Set Expansion Medical Data Generation Source : H. R. Roth et. al., MICCAI, 2015
  • 54. Generation of synthetic dataset for dataset expansion Medical Data Generation M.J.M. Chuquicusma, ISBI 2018 ▪ “How To Fool Radiologists with Generative Adversarial Networks? A Visual Turing Test For Lung Cancer Diagnosis”
  • 55. Generation of synthetic dataset for dataset expansion Medical Data Generation M.J.M. Chuquicusma, ISBI 2018 ▪ Visual Turing Test
  • 56. ▪ “Synthetic Medical Images from Dual Generative Adversarial Networks” Generation of Fundus Image using Dual GANs Medical Data Generation John T. Guibas et. al, NIPS Workshop 2017
  • 57. ▪ “Synthetic Medical Images from Dual Generative Adversarial Networks” Generation of Fundus Image using Dual GANs Medical Data Generation John T. Guibas et. al, NIPS Workshop 2017
  • 58. ▪ “Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification” Liver Lesion Generation for Data Augmentation Medical Data Generation Maayan Frid-Ada et. al, ISBI 2018 Real Synthetic
  • 59. ▪ “Generalization of Deep Neural Networks for Chest Pathology Classification in X-ray using Generative Adversarial Networks” Chest X-ray Generation for Data Augmentation Medical Data Generation Hojjat Salehinejad et. al, ICASSP 2018
  • 60. ▪ Generated Samples and Performance Improvement by Synthetic Augmentation Chest X-ray Generation for Data Augmentation Medical Data Generation Hojjat Salehinejad et. al, ICASSP 2018
  • 61. ▪ “Visual Feature Attribution using Wasserstein GANs “ VA-GAN : Understanding Visual Feature Attribution for Alzheimer Disease Visual Feature Attribution Christian F. Baumgatrner et. al, arXiv 2018 Overall Objective GAN Loss Term RegularizationTerm
  • 62. ▪ “Visual Feature Attribution using Wasserstein GANs “ VA-GAN : Understanding Visual Feature Attribution for Alzheimer Disease Visual Feature Attribution Christian F. Baumgatrner et. al, arXiv 2018
  • 63. Enhance the quality of low-dose CT to normal-dose CT Synthesis or Enhancement of Medical Image Dong Nie et. al, MICCAI 2017 ▪ “Medical Image Synthesis using Context-aware Generative Adversarial Networks”
  • 64. Unpaired image translation from MR to CT using CycleGAN Synthesis or Enhancement of Medical Image Jelmer M. Wolterink et. al, MICCAI 2017 Workshop Setting Mean Absolute Error Paired Voxel-wise Loss 89.4 ± 6.8 HU Unpaired Cycle Consistency Loss 73.7 ± 2.3 HU ▪ “Deep MR to CT Synthesis using Unpaired Data”
  • 65. Enhance the quality of low-dose CT to normal-dose CT Synthesis or Enhancement of Medical Image J. M. Wolterink et. al, IEEE Trans. Medical Imaging ▪ “Generative Adversarial Networks for Noise Reduction in Low-Dose CT”
  • 66. Deep learning for undersampled MRI reconstruction Synthesis or Enhancement of Medical Image Tran Min Quan et. al, arXiv 2018 ▪ “Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss” –Problem of compressed sensing MRI reconstruction –CS-MRI using GAN objective
  • 67. Deep learning for undersampled MRI reconstruction Synthesis or Enhancement of Medical Image Tran Min Quan et. al, arXiv 2018 ▪ “Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss”
  • 68. Deep learning for undersampled MRI reconstruction Synthesis or Enhancement of Medical Image Tran Min Quan et. al, arXiv 2018 ▪ Experimental Results for Understampled MRI Reconstruction using GAN
  • 69. Generation of segmentation mask undistinguishable from physician’s mask Physician Friendly Loss for Segmentation Source : P. Costa(2017), VUNO(2017) ▪ “Retinal Vessel Segmentation in Fundoscopic Images with Generative Adversarial Networks”
  • 70. ▪ “Adversarial Networks for the Detection of Aggressive Prostate Cancer” Generation of segmentation mask undistinguishable from physician’s mask Physician Friendly Loss for Segmentation Source : S. Kohl et. al(2017)
  • 71. ▪ “SegAN : Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation” SegAN : Adversarial Network with Multi-scale Loss Physician Friendly Loss for Segmentation Yuan Xue et. al, arXiv 2017
  • 72. ▪ “Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape- Consistency Generative Adversarial Network” Segmentation of Multimodal Images using Image-to-Image Translation Multimodal Image Segmentation Zizhao Zhang et. al, CVPR 2018
  • 73. ▪ “Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape- Consistency Generative Adversarial Network” Segmentation of Multimodal Images using Image-to-Image Translation Multimodal Image Segmentation Zizhao Zhang et. al, CVPR 2018
  • 75. ▪ Image Generation – Generation of rare cases – Understanding latent structure of lesions – Improving the performance of diagnostic models ▪ Image Synthesis and Translation – Noise reduction, modality translation – Accelerating image acquisition time – Improving diagnostic performance ▪ Lesion Detection and Segmentation – More physician friendly training – Better performance for lesions or organs with complex structure ▪ Future of GANs in Medical Imaging – More GANs to come in medical imaging with clinical and commercial values More GANs in Medical Imaging Future of GANs