SlideShare a Scribd company logo
1 of 15
Diffusion adversarial representation learning
for self-supervised vessel segmentation
ICLR 2023
Boah Kim*, Yujin Oh*, and Jong Chul Ye
Research objectives
2
Vessel segmentation
• To analyze vessel structures and therapy planning
X-ray coronary angiography
• To enhance vessel visualization by injecting a contrast
agent into the blood vessels
• To have many tiny branches, confusing structures, etc
→ Hard to extract vessels
Background Angiography
• To segment vascular structures without ground-truth labels
• To adopt the diffusion model in learning semantic information
Research goal
Related works: Diffusion model for segmentation
3
[1] Tomer Amit et al., arXiv 2022. [2] Dmitry Baranchuk, et al., arXiv 2022.
Develop a fast image segmentation method leveraging DDPM without labeled data
Amit et al.
• To train the diffusion model using (image, label) pairs.
• Estimating segmentation maps through the stochastic
generative process → Requiring a long time
Dmitry Baranchuk et al.
• Describing the diffusion model in terms of image
representations
• Learning semantic image segmentation with labeled data
Theory: Diffusion adversarial representation learning
4
Training framework
• Using unpaired angiography images 𝒙𝑎
& background images 𝒙𝑏
• Diffusion module 𝝐𝜃: To estimate latent features
• Generation module 𝑮: To estimate both vessel masks & synthetic angiograms
• Discriminators (𝑫𝑠 𝑫𝑎): To distinguish real and fake images
Theory: Diffusion adversarial representation learning
5
• Utilizing SPADE (spatially adaptive normalization) [1] to perform
semantic image synthesis
• Switchable SPADE (S-SPADE):
[1] Taesung, Park et al., CVPR 2019.
Generation module with switchable SPADE layers
𝒗 =
SPADE(𝒗, 𝒔), if mask 𝒔 is given,
IN(𝒗), otherwise
Generation module, 𝑮
Conv
I
ReLU
I
Conv
ReLU
S
S
×N
Switchable SPADE
ResnetBlock
Ma et al. ICCV 2021
(B) path:
Background fractal mask Synthetic
angiography
Input Output
(A) path:
Angiography Vessel map
Input Output
Theory: Diffusion adversarial representation learning
6
[1] Xudong Mao et al., ICCV 2017.
Loss function
• Training the diffusion model with adversarial learning
• Optimization problem employing LSGAN[1] framework:
Theory: Diffusion adversarial representation learning
7
Loss function
• Diffusion loss 𝓛𝑑𝑖𝑓𝑓: To intensively learn the
distribution of background image signal
• Adversarial loss 𝓛𝑎𝑑𝑣: To generate realistic images in
the both (A) and (B) paths
• Cyclic reconstruction loss 𝓛𝑐𝑦𝑐: For the generator to
capture the vessel semantic information
Theory: Diffusion adversarial representation learning
8
[1] Xudong Mao et al., ICCV 2017.
Inference of vessel segmentation
• Can obtain the vessel segmentation masks of angiography from the (A) path through one step
• The closer 𝑡𝑎 is to zero, the better the vessel segmentation performance
Noisy level of (A) path
Dataset and experiment setting
9
X-ray coronary angiography disease (XCAD) dataset
• Images obtained during stent placement surgery
• Train: 1621 images / Test: 114 images
- Subsampled to 256x256
- Normalized to [-1, 1]
Programming language Python, PyTorch
GPU Nvidia Quadro RTX 6000
Augmentation Horizontal/vertical flipping, rotation with 90
Batch size 1
Baseline network DDPM1(diffusion module) + SPADE2 (generation module)
Training epochs 150
Learning rate 5 × 10−6
Optimization Adam algorithm
Baseline methods SGC3, Redrawing4, DS5, STEGO6, DA7, SSVS8
[1] Jonathan Ho et al., NeurIPS 2020. [2] Taesung, Park et al., CVPR 2019. [3] Ahn et al., 2021. [4] Chen et al., 2019.
[5] Melas-Kyriazi et al., 2022. [6] Hamilton et al., 2022. [7] Mahmood et al., 2019. [8] Ma et al., 2021.
10
Experimental results
Comparison of ours to baselines
• To demonstrate the vessel segmentation performance of our method
Data Metric SGC Redrawing DS STEGO DA SSVS Ours
XCAD
IoU 0.060 0.059 0.366 0.146 0.375 0.410 0.471
Dice 0.111 0.109 0.526 0.249 0.542 0.575 0.636
Precision 0.062 0.139 0.469 0.152 0.557 0.590 0.701
11
Experimental results
Generalization capability
• To verify that our model can be generally used for various images from other machines or other organs
• Only test without training a new model
12
Experimental results
Robustness to noises
• To evaluate the usefulness of our model on noisy angiography images (Simulation with Gaussian noise)
13
Experimental results
Ablation study
• To study on the effect of each component of our model
Module Loss function Metric
Methods Diffusion Generation 𝓛𝑑𝑖𝑓𝑓 𝓛𝑎𝑑𝑣 𝓛𝑐𝑦𝑐 IoU Dice Precision
Ours √ √ √ √ √ 0.471 0.636 0.701
(a) √ √ √ 0.449 0.616 0.646
(b) w/o S-SPADE √ √ 0.439 0.606 0.620
(c) √ √ √ √ 0.322 0.485 0.580
(d) √ √ √ √ L1→CE 0.346 0.508 0.672
(a-b): Ablation models of our diffusion/generation modules
(c-d): Ablation models of the proposed loss function
14
Experimental results
Diffusion module in latent feature estimation
• To show the effectiveness of diffusion module in latent feature estimation
Latent feature estimation IoU Dice Precision
Autoencoder 0.399 0.566 0.621
Diffusion (Ours) 0.471 0.636 0.701
Summary
15
• Proposed method learns vessel representation without labels via adversarial learning.
• The generation with switchable SPADE layers allows the model to generate synthetic angiograms as well as
vessel segmentation masks. → Learning semantic information effectively
• Experimental results using various vessel datasets verified high performance of the proposed method.
• Robustness to image diversity and noise
Propose a novel diffusion-based self-supervised vessel segmentation model by employing DDPM

More Related Content

Similar to ICLR2023_DARL.pdf

A UTOMATIC C OMPUTATION OF CDR U SING F UZZY C LUSTERING T ECHNIQUES
A UTOMATIC C OMPUTATION OF CDR U SING F UZZY C LUSTERING T ECHNIQUESA UTOMATIC C OMPUTATION OF CDR U SING F UZZY C LUSTERING T ECHNIQUES
A UTOMATIC C OMPUTATION OF CDR U SING F UZZY C LUSTERING T ECHNIQUEScsandit
 
Segmentation techniques for extraction and description of tumour region from ...
Segmentation techniques for extraction and description of tumour region from ...Segmentation techniques for extraction and description of tumour region from ...
Segmentation techniques for extraction and description of tumour region from ...Swarada Kanap
 
Using HOG Descriptors on Superpixels for Human Detection of UAV Imagery
Using HOG Descriptors on Superpixels for Human Detection of UAV ImageryUsing HOG Descriptors on Superpixels for Human Detection of UAV Imagery
Using HOG Descriptors on Superpixels for Human Detection of UAV ImageryWai Nwe Tun
 
Lec16: Medical Image Registration (Advanced): Deformable Registration
Lec16: Medical Image Registration (Advanced): Deformable RegistrationLec16: Medical Image Registration (Advanced): Deformable Registration
Lec16: Medical Image Registration (Advanced): Deformable RegistrationUlaş Bağcı
 
Enhanced characterness for text detection in the wild
Enhanced characterness for text detection in the wildEnhanced characterness for text detection in the wild
Enhanced characterness for text detection in the wildPrerana Mukherjee
 
Skin melanoma stage detection - CNN.pptx
Skin melanoma stage detection - CNN.pptxSkin melanoma stage detection - CNN.pptx
Skin melanoma stage detection - CNN.pptxVishalLabde
 
A Hybrid Technique for the Automated Segmentation of Corpus Callosum in Midsa...
A Hybrid Technique for the Automated Segmentation of Corpus Callosum in Midsa...A Hybrid Technique for the Automated Segmentation of Corpus Callosum in Midsa...
A Hybrid Technique for the Automated Segmentation of Corpus Callosum in Midsa...IJERA Editor
 
Learning-based vertebra segmentation, identification and partioning
Learning-based vertebra segmentation, identification and partioningLearning-based vertebra segmentation, identification and partioning
Learning-based vertebra segmentation, identification and partioningRadboud University Medical Center
 
Retinal Vessel Segmentation in U-Net Using Deep Learning
Retinal Vessel Segmentation in U-Net Using Deep LearningRetinal Vessel Segmentation in U-Net Using Deep Learning
Retinal Vessel Segmentation in U-Net Using Deep LearningIRJET Journal
 
CycleMorph: Cycle consistent unsupervised deformable image registration
CycleMorph: Cycle consistent unsupervised deformable image registrationCycleMorph: Cycle consistent unsupervised deformable image registration
CycleMorph: Cycle consistent unsupervised deformable image registrationBoahKim2
 
Progressive Image Denoising Through Hybrid Graph Laplacian Regularization: A ...
Progressive Image Denoising Through Hybrid Graph Laplacian Regularization: A ...Progressive Image Denoising Through Hybrid Graph Laplacian Regularization: A ...
Progressive Image Denoising Through Hybrid Graph Laplacian Regularization: A ...john236zaq
 
Autogenous Diabetic Retinopathy Censor for Ophthalmologists - AKSHI
Autogenous Diabetic Retinopathy Censor for Ophthalmologists - AKSHIAutogenous Diabetic Retinopathy Censor for Ophthalmologists - AKSHI
Autogenous Diabetic Retinopathy Censor for Ophthalmologists - AKSHIAsiri Wijesinghe
 
Artifacts Detection by Extracting Edge Features and Error Block Analysis from...
Artifacts Detection by Extracting Edge Features and Error Block Analysis from...Artifacts Detection by Extracting Edge Features and Error Block Analysis from...
Artifacts Detection by Extracting Edge Features and Error Block Analysis from...Md. Mehedi Hasan
 
Neuron Reconstruction and Analysis Workshop
Neuron Reconstruction and Analysis WorkshopNeuron Reconstruction and Analysis Workshop
Neuron Reconstruction and Analysis WorkshopMBF Bioscience
 
MahdiMarsousi_PhD_FOE_PresentationSlides
MahdiMarsousi_PhD_FOE_PresentationSlidesMahdiMarsousi_PhD_FOE_PresentationSlides
MahdiMarsousi_PhD_FOE_PresentationSlidesMahdi Marsousi
 

Similar to ICLR2023_DARL.pdf (20)

A UTOMATIC C OMPUTATION OF CDR U SING F UZZY C LUSTERING T ECHNIQUES
A UTOMATIC C OMPUTATION OF CDR U SING F UZZY C LUSTERING T ECHNIQUESA UTOMATIC C OMPUTATION OF CDR U SING F UZZY C LUSTERING T ECHNIQUES
A UTOMATIC C OMPUTATION OF CDR U SING F UZZY C LUSTERING T ECHNIQUES
 
Declarative data analysis
Declarative data analysisDeclarative data analysis
Declarative data analysis
 
Introduction to image processing
Introduction to image processingIntroduction to image processing
Introduction to image processing
 
Segmentation techniques for extraction and description of tumour region from ...
Segmentation techniques for extraction and description of tumour region from ...Segmentation techniques for extraction and description of tumour region from ...
Segmentation techniques for extraction and description of tumour region from ...
 
Using HOG Descriptors on Superpixels for Human Detection of UAV Imagery
Using HOG Descriptors on Superpixels for Human Detection of UAV ImageryUsing HOG Descriptors on Superpixels for Human Detection of UAV Imagery
Using HOG Descriptors on Superpixels for Human Detection of UAV Imagery
 
Lec16: Medical Image Registration (Advanced): Deformable Registration
Lec16: Medical Image Registration (Advanced): Deformable RegistrationLec16: Medical Image Registration (Advanced): Deformable Registration
Lec16: Medical Image Registration (Advanced): Deformable Registration
 
Enhanced characterness for text detection in the wild
Enhanced characterness for text detection in the wildEnhanced characterness for text detection in the wild
Enhanced characterness for text detection in the wild
 
Skin melanoma stage detection - CNN.pptx
Skin melanoma stage detection - CNN.pptxSkin melanoma stage detection - CNN.pptx
Skin melanoma stage detection - CNN.pptx
 
A Hybrid Technique for the Automated Segmentation of Corpus Callosum in Midsa...
A Hybrid Technique for the Automated Segmentation of Corpus Callosum in Midsa...A Hybrid Technique for the Automated Segmentation of Corpus Callosum in Midsa...
A Hybrid Technique for the Automated Segmentation of Corpus Callosum in Midsa...
 
Learning-based vertebra segmentation, identification and partioning
Learning-based vertebra segmentation, identification and partioningLearning-based vertebra segmentation, identification and partioning
Learning-based vertebra segmentation, identification and partioning
 
Kulakov_Mykhailo.pptx
Kulakov_Mykhailo.pptxKulakov_Mykhailo.pptx
Kulakov_Mykhailo.pptx
 
Retinal Vessel Segmentation in U-Net Using Deep Learning
Retinal Vessel Segmentation in U-Net Using Deep LearningRetinal Vessel Segmentation in U-Net Using Deep Learning
Retinal Vessel Segmentation in U-Net Using Deep Learning
 
CycleMorph: Cycle consistent unsupervised deformable image registration
CycleMorph: Cycle consistent unsupervised deformable image registrationCycleMorph: Cycle consistent unsupervised deformable image registration
CycleMorph: Cycle consistent unsupervised deformable image registration
 
Progressive Image Denoising Through Hybrid Graph Laplacian Regularization: A ...
Progressive Image Denoising Through Hybrid Graph Laplacian Regularization: A ...Progressive Image Denoising Through Hybrid Graph Laplacian Regularization: A ...
Progressive Image Denoising Through Hybrid Graph Laplacian Regularization: A ...
 
DOC-20221128-WA0000..pptx
DOC-20221128-WA0000..pptxDOC-20221128-WA0000..pptx
DOC-20221128-WA0000..pptx
 
Autogenous Diabetic Retinopathy Censor for Ophthalmologists - AKSHI
Autogenous Diabetic Retinopathy Censor for Ophthalmologists - AKSHIAutogenous Diabetic Retinopathy Censor for Ophthalmologists - AKSHI
Autogenous Diabetic Retinopathy Censor for Ophthalmologists - AKSHI
 
Skin_Cancer.pptx
Skin_Cancer.pptxSkin_Cancer.pptx
Skin_Cancer.pptx
 
Artifacts Detection by Extracting Edge Features and Error Block Analysis from...
Artifacts Detection by Extracting Edge Features and Error Block Analysis from...Artifacts Detection by Extracting Edge Features and Error Block Analysis from...
Artifacts Detection by Extracting Edge Features and Error Block Analysis from...
 
Neuron Reconstruction and Analysis Workshop
Neuron Reconstruction and Analysis WorkshopNeuron Reconstruction and Analysis Workshop
Neuron Reconstruction and Analysis Workshop
 
MahdiMarsousi_PhD_FOE_PresentationSlides
MahdiMarsousi_PhD_FOE_PresentationSlidesMahdiMarsousi_PhD_FOE_PresentationSlides
MahdiMarsousi_PhD_FOE_PresentationSlides
 

More from BoahKim2

TIP_TAViT_presentation.pdf
TIP_TAViT_presentation.pdfTIP_TAViT_presentation.pdf
TIP_TAViT_presentation.pdfBoahKim2
 
DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion Model
DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion ModelDiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion Model
DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion ModelBoahKim2
 
Unsupervised Deformable Image Registration Using Cycle-Consistent CNN
Unsupervised Deformable Image Registration Using Cycle-Consistent CNNUnsupervised Deformable Image Registration Using Cycle-Consistent CNN
Unsupervised Deformable Image Registration Using Cycle-Consistent CNNBoahKim2
 
Mumford-Shah Loss Functional for Image Segmentation With Deep Learning
Mumford-Shah Loss Functional for Image Segmentation With Deep LearningMumford-Shah Loss Functional for Image Segmentation With Deep Learning
Mumford-Shah Loss Functional for Image Segmentation With Deep LearningBoahKim2
 
Medical Image Synthesis with Improved Cycle-GAN: CT from CECT
Medical Image Synthesis with Improved Cycle-GAN: CT from CECT Medical Image Synthesis with Improved Cycle-GAN: CT from CECT
Medical Image Synthesis with Improved Cycle-GAN: CT from CECT BoahKim2
 
Multi-energy Bone Subtraction in Chest Radiography by Eigenvalue Decomposition
Multi-energy Bone Subtraction in Chest Radiography by Eigenvalue DecompositionMulti-energy Bone Subtraction in Chest Radiography by Eigenvalue Decomposition
Multi-energy Bone Subtraction in Chest Radiography by Eigenvalue DecompositionBoahKim2
 

More from BoahKim2 (6)

TIP_TAViT_presentation.pdf
TIP_TAViT_presentation.pdfTIP_TAViT_presentation.pdf
TIP_TAViT_presentation.pdf
 
DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion Model
DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion ModelDiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion Model
DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion Model
 
Unsupervised Deformable Image Registration Using Cycle-Consistent CNN
Unsupervised Deformable Image Registration Using Cycle-Consistent CNNUnsupervised Deformable Image Registration Using Cycle-Consistent CNN
Unsupervised Deformable Image Registration Using Cycle-Consistent CNN
 
Mumford-Shah Loss Functional for Image Segmentation With Deep Learning
Mumford-Shah Loss Functional for Image Segmentation With Deep LearningMumford-Shah Loss Functional for Image Segmentation With Deep Learning
Mumford-Shah Loss Functional for Image Segmentation With Deep Learning
 
Medical Image Synthesis with Improved Cycle-GAN: CT from CECT
Medical Image Synthesis with Improved Cycle-GAN: CT from CECT Medical Image Synthesis with Improved Cycle-GAN: CT from CECT
Medical Image Synthesis with Improved Cycle-GAN: CT from CECT
 
Multi-energy Bone Subtraction in Chest Radiography by Eigenvalue Decomposition
Multi-energy Bone Subtraction in Chest Radiography by Eigenvalue DecompositionMulti-energy Bone Subtraction in Chest Radiography by Eigenvalue Decomposition
Multi-energy Bone Subtraction in Chest Radiography by Eigenvalue Decomposition
 

Recently uploaded

(TARA) Talegaon Dabhade Call Girls Just Call 7001035870 [ Cash on Delivery ] ...
(TARA) Talegaon Dabhade Call Girls Just Call 7001035870 [ Cash on Delivery ] ...(TARA) Talegaon Dabhade Call Girls Just Call 7001035870 [ Cash on Delivery ] ...
(TARA) Talegaon Dabhade Call Girls Just Call 7001035870 [ Cash on Delivery ] ...ranjana rawat
 
Processing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxProcessing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxpranjaldaimarysona
 
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSAPPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSKurinjimalarL3
 
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...ranjana rawat
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxpurnimasatapathy1234
 
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Dr.Costas Sachpazis
 
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingrakeshbaidya232001
 
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130Suhani Kapoor
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
the ladakh protest in leh ladakh 2024 sonam wangchuk.pptx
the ladakh protest in leh ladakh 2024 sonam wangchuk.pptxthe ladakh protest in leh ladakh 2024 sonam wangchuk.pptx
the ladakh protest in leh ladakh 2024 sonam wangchuk.pptxhumanexperienceaaa
 
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escortsranjana rawat
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Christo Ananth
 
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )Tsuyoshi Horigome
 
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Serviceranjana rawat
 
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).pptssuser5c9d4b1
 
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)Suman Mia
 
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxDecoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxJoão Esperancinha
 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls in Nagpur High Profile
 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxupamatechverse
 

Recently uploaded (20)

(TARA) Talegaon Dabhade Call Girls Just Call 7001035870 [ Cash on Delivery ] ...
(TARA) Talegaon Dabhade Call Girls Just Call 7001035870 [ Cash on Delivery ] ...(TARA) Talegaon Dabhade Call Girls Just Call 7001035870 [ Cash on Delivery ] ...
(TARA) Talegaon Dabhade Call Girls Just Call 7001035870 [ Cash on Delivery ] ...
 
Processing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxProcessing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptx
 
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSAPPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
 
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptx
 
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
Structural Analysis and Design of Foundations: A Comprehensive Handbook for S...
 
Porous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writingPorous Ceramics seminar and technical writing
Porous Ceramics seminar and technical writing
 
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
VIP Call Girls Service Hitech City Hyderabad Call +91-8250192130
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
the ladakh protest in leh ladakh 2024 sonam wangchuk.pptx
the ladakh protest in leh ladakh 2024 sonam wangchuk.pptxthe ladakh protest in leh ladakh 2024 sonam wangchuk.pptx
the ladakh protest in leh ladakh 2024 sonam wangchuk.pptx
 
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(MEERA) Dapodi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
 
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
Call for Papers - African Journal of Biological Sciences, E-ISSN: 2663-2187, ...
 
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )
 
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
(RIA) Call Girls Bhosari ( 7001035870 ) HI-Fi Pune Escorts Service
 
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
247267395-1-Symmetric-and-distributed-shared-memory-architectures-ppt (1).ppt
 
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)Software Development Life Cycle By  Team Orange (Dept. of Pharmacy)
Software Development Life Cycle By Team Orange (Dept. of Pharmacy)
 
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxDecoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptx
 

ICLR2023_DARL.pdf

  • 1. Diffusion adversarial representation learning for self-supervised vessel segmentation ICLR 2023 Boah Kim*, Yujin Oh*, and Jong Chul Ye
  • 2. Research objectives 2 Vessel segmentation • To analyze vessel structures and therapy planning X-ray coronary angiography • To enhance vessel visualization by injecting a contrast agent into the blood vessels • To have many tiny branches, confusing structures, etc → Hard to extract vessels Background Angiography • To segment vascular structures without ground-truth labels • To adopt the diffusion model in learning semantic information Research goal
  • 3. Related works: Diffusion model for segmentation 3 [1] Tomer Amit et al., arXiv 2022. [2] Dmitry Baranchuk, et al., arXiv 2022. Develop a fast image segmentation method leveraging DDPM without labeled data Amit et al. • To train the diffusion model using (image, label) pairs. • Estimating segmentation maps through the stochastic generative process → Requiring a long time Dmitry Baranchuk et al. • Describing the diffusion model in terms of image representations • Learning semantic image segmentation with labeled data
  • 4. Theory: Diffusion adversarial representation learning 4 Training framework • Using unpaired angiography images 𝒙𝑎 & background images 𝒙𝑏 • Diffusion module 𝝐𝜃: To estimate latent features • Generation module 𝑮: To estimate both vessel masks & synthetic angiograms • Discriminators (𝑫𝑠 𝑫𝑎): To distinguish real and fake images
  • 5. Theory: Diffusion adversarial representation learning 5 • Utilizing SPADE (spatially adaptive normalization) [1] to perform semantic image synthesis • Switchable SPADE (S-SPADE): [1] Taesung, Park et al., CVPR 2019. Generation module with switchable SPADE layers 𝒗 = SPADE(𝒗, 𝒔), if mask 𝒔 is given, IN(𝒗), otherwise Generation module, 𝑮 Conv I ReLU I Conv ReLU S S ×N Switchable SPADE ResnetBlock Ma et al. ICCV 2021 (B) path: Background fractal mask Synthetic angiography Input Output (A) path: Angiography Vessel map Input Output
  • 6. Theory: Diffusion adversarial representation learning 6 [1] Xudong Mao et al., ICCV 2017. Loss function • Training the diffusion model with adversarial learning • Optimization problem employing LSGAN[1] framework:
  • 7. Theory: Diffusion adversarial representation learning 7 Loss function • Diffusion loss 𝓛𝑑𝑖𝑓𝑓: To intensively learn the distribution of background image signal • Adversarial loss 𝓛𝑎𝑑𝑣: To generate realistic images in the both (A) and (B) paths • Cyclic reconstruction loss 𝓛𝑐𝑦𝑐: For the generator to capture the vessel semantic information
  • 8. Theory: Diffusion adversarial representation learning 8 [1] Xudong Mao et al., ICCV 2017. Inference of vessel segmentation • Can obtain the vessel segmentation masks of angiography from the (A) path through one step • The closer 𝑡𝑎 is to zero, the better the vessel segmentation performance Noisy level of (A) path
  • 9. Dataset and experiment setting 9 X-ray coronary angiography disease (XCAD) dataset • Images obtained during stent placement surgery • Train: 1621 images / Test: 114 images - Subsampled to 256x256 - Normalized to [-1, 1] Programming language Python, PyTorch GPU Nvidia Quadro RTX 6000 Augmentation Horizontal/vertical flipping, rotation with 90 Batch size 1 Baseline network DDPM1(diffusion module) + SPADE2 (generation module) Training epochs 150 Learning rate 5 × 10−6 Optimization Adam algorithm Baseline methods SGC3, Redrawing4, DS5, STEGO6, DA7, SSVS8 [1] Jonathan Ho et al., NeurIPS 2020. [2] Taesung, Park et al., CVPR 2019. [3] Ahn et al., 2021. [4] Chen et al., 2019. [5] Melas-Kyriazi et al., 2022. [6] Hamilton et al., 2022. [7] Mahmood et al., 2019. [8] Ma et al., 2021.
  • 10. 10 Experimental results Comparison of ours to baselines • To demonstrate the vessel segmentation performance of our method Data Metric SGC Redrawing DS STEGO DA SSVS Ours XCAD IoU 0.060 0.059 0.366 0.146 0.375 0.410 0.471 Dice 0.111 0.109 0.526 0.249 0.542 0.575 0.636 Precision 0.062 0.139 0.469 0.152 0.557 0.590 0.701
  • 11. 11 Experimental results Generalization capability • To verify that our model can be generally used for various images from other machines or other organs • Only test without training a new model
  • 12. 12 Experimental results Robustness to noises • To evaluate the usefulness of our model on noisy angiography images (Simulation with Gaussian noise)
  • 13. 13 Experimental results Ablation study • To study on the effect of each component of our model Module Loss function Metric Methods Diffusion Generation 𝓛𝑑𝑖𝑓𝑓 𝓛𝑎𝑑𝑣 𝓛𝑐𝑦𝑐 IoU Dice Precision Ours √ √ √ √ √ 0.471 0.636 0.701 (a) √ √ √ 0.449 0.616 0.646 (b) w/o S-SPADE √ √ 0.439 0.606 0.620 (c) √ √ √ √ 0.322 0.485 0.580 (d) √ √ √ √ L1→CE 0.346 0.508 0.672 (a-b): Ablation models of our diffusion/generation modules (c-d): Ablation models of the proposed loss function
  • 14. 14 Experimental results Diffusion module in latent feature estimation • To show the effectiveness of diffusion module in latent feature estimation Latent feature estimation IoU Dice Precision Autoencoder 0.399 0.566 0.621 Diffusion (Ours) 0.471 0.636 0.701
  • 15. Summary 15 • Proposed method learns vessel representation without labels via adversarial learning. • The generation with switchable SPADE layers allows the model to generate synthetic angiograms as well as vessel segmentation masks. → Learning semantic information effectively • Experimental results using various vessel datasets verified high performance of the proposed method. • Robustness to image diversity and noise Propose a novel diffusion-based self-supervised vessel segmentation model by employing DDPM