SlideShare uma empresa Scribd logo
1 de 41
Inverse problems in medical
imaging
Nikita Moriakov
Diagnostic Image Analysis Group
Department of Radiology and Nuclear Medicine
Radboud University Medical Center, Nijmegen
Plan
• Inverse problems
• Deep Learning in Inverse Problems: Fully
learned inversion vs. Learned iterative
schemes
• Results and future work
Inverse problems
What is inverse problem?
• 𝑓𝑡𝑟𝑢𝑒 ∈ 𝑋 is an unknown true model parameter, 𝑔 ∈ 𝑌 is data, 𝑒 is sample
from measurement noise and 𝐴: 𝑋 → 𝑌 is a continuous operator mapping
model parameter to data (in the absence of noise)
• Examples: CT & MR reconstruction, denoising, inpainting.
Examples: Radon Transform
• Let 𝑓 ∈ 𝐿1 ℝ2 be a function such
that 𝑓(𝑥, 𝑦) is the attenuation
coefficient of scanned object at
point (𝑥, 𝑦)
• If X-ray going along the line 𝐿 has
incident intensity 𝐼0, the outcoming
intensity equals 𝐼0 𝑒
− 𝑥,𝑦 ∈𝐿
𝑓 𝑥,𝑦 𝑑𝐿
Examples: Radon Transform
• Parametrize all lines by the angle 𝜃 and
the distance 𝑠 to the origin
• The Radon transform of 𝑓 is a function of
𝑠 ∈ ℝ, 𝜃 ∈ [0, 2 𝜋) given by
Radon, 1907
Back projection (key for inversion)
Examples: Radon Transform
• This direct analytic inversion is called
Filtered Back Projection today.
• Radon transform is invertible (when we
know projections from all directions and
all rays intersecting the object).
Examples: DBT
• Available since late 2000s.
• Rapidly replacing Digital
Mammography
• Can have resolution as high as DM
standards.
Examples: DBT
• The x-ray tube moves in an arc
over the compressed breast
capturing multiple images of each
breast from different angles in a
continuous or step-and-shoot
fashion.
Examples: MR
• Fourier transform ℱ maps images
to frequency domain.
• Some measurements in this domain
are taken, giving subsampling mask
𝑃.
• Inverse Fourier transform maps
back to the image domain.
• Reconstructed image can deviate
from target if k-space is
undersampled.
Problems with inverse problems?
• 𝐴 can have non-trivial kernel. E.g., for CT with limited number of view
angles the following holds:
• 𝐴 can have discontinuous inverse, thus variations in noise can have strong
effect on reconstruction.
Bayesian view and regularization,
MAP
• Finding most likely reconstruction given measurements amounts to
finding 𝑎𝑟𝑔𝑚𝑎𝑥𝑖𝑚𝑎𝑔𝑒 𝑃 𝐼𝑚𝑎𝑔𝑒 𝑀𝑒𝑎𝑠).
• 𝑎𝑟𝑔𝑚𝑎𝑥𝑖𝑚𝑎𝑔𝑒 𝑃 𝐼𝑚𝑎𝑔𝑒 𝑀𝑒𝑎𝑠) = 𝑎𝑟𝑔𝑚𝑎𝑥𝑖𝑚𝑎𝑔𝑒
𝑃 𝑀𝑒𝑎𝑠 𝐼𝑚𝑎𝑔𝑒)⋅𝑃 𝐼𝑚𝑎𝑔𝑒
𝑃(𝑀𝑒𝑎𝑠)
=
𝑎𝑟𝑔𝑚𝑎𝑥𝑖𝑚𝑎𝑔𝑒 (log 𝑃 𝑀𝑒𝑎𝑠 𝐼𝑚𝑎𝑔𝑒 + log 𝑃(𝐼𝑚𝑎𝑔𝑒))
• log 𝑃(𝑀𝑒𝑎𝑠|𝐼𝑚𝑎𝑔𝑒) is the log-likelihood of observed data, log 𝑃(𝐼𝑚𝑎𝑔𝑒)
is the prior term.
• Prior term is used for regularization such as TV regularization.
Deep Learning for Inverse
Problems
Inverse problems with DL
Fully learned data driven
reconstruction
• Generic parametrization by a neural
network to find an inverse mapping
𝑅 𝜃: 𝑌 → 𝑋 with 𝜃 being the neural
network weights
• No need to have explicit forward
operator or data likelihood
• Need to use fully connected layers
and hence requires a lot of
parameters.
Learned iterative schemes
• Contains explicit knowledge of
forward operator built in the
architecture of 𝑅 𝜃: 𝑌 → 𝑋
• Architecture motivated by existing
optimization algorithms
Inverse problems with DL
Learned regularizers
• Train a regularizer 𝑆 𝜃: 𝑋 → ℝ
separately, which is parametrized
by a neural network, and is ideally
proportional to the image prior
(Bayesian view).
• Can be trained adversarily.
Fully learned inference
• Zhu, Liu, Rosen, Rosen “Image reconstruction by domain transform
manifold learning” 2018
Learned Iterative Schemes: LPD
• Learned Primal-Dual (LPD) is an example of learned iterative schemes.
• Architecture motivated by Primal-Dual Hybrid Gradient Method.
Learned Primal-Dual
• A deep neural network
• Iterative procedure inspired by
Primal-Dual Hybrid Gradient
algorithm
• Consists of a primal/dual
reconstruction blocks which
performs small “steps” in
image and projection space
respectively.
Network architecture
Results (Adler & Öktem)
Learned Iterative Schemes: RIM
• The goal in MAP estimate is finding
• This is often done in via an iterative scheme
• To avoid the need to learn prior, we can “generalize” this to the form
• So can optimize this as a recurrent neural network.
Recurrent Inference Machines for MR
Lonning, Putzky, Caan, Welling Recurrent Inference Machines for Accelerated MRI Reconstruction 2018
RIM for MRI Reconstruction
Lonning, Putzky, Caan, Welling Recurrent Inference Machines for Accelerated MRI Reconstruction 2018
Results and future work
SPIE 2019 Medical Imaging
Data for the experiment
• Synthetic breast images generated by realistic digital breast
phantom (from I. Sechopoulos et al.)
• 25 view angles: [-24, -22, … , 22, 24] deg
Results (LPD on DBT)
Network architecture (LPD)
LPD for DBT architecture (DBToR)
𝑚
𝑇(𝑚)
Results (beginning of training)
Results (end of training)
Results
Future work
Compressed breast phantom
Classification
Image Segmentation:
Skin – Adipose – Glandular
Caballo M. et al . 2018 “An Unsupervised Automatic Segmentation algorithm for breast tissue” – Med. Phys.
Finite Element
Compression
BCT images acquired
from patients at Radboudumc
Finite Element Compression
Breast Density Map
• Create a mesh of the breast
• Simulate the compression of soft tissue (adipose,
glandular & skin) using the high-performance explicit
finite element solver, developed for medical application
Compression
Compression
The breast support is move up by 20
mm (to make the bottom flat);
the compression is performed by
moving down the compression paddle
Voxel Resolution of (0.273 mm)3
Results
Sources
• Arridge, Maass, Öktem, Schönlieb “Solving Inverse Problems Using Data
Driven Models”, Acta Numerica 2019.
• Adler, Öktem “Learned Primal-dual Reconstruction”
• Markoe, “Analytic Tomography”
• Zhu, Liu, Rosen, Rosen “Image reconstruction by domain transform
manifold learning”, Nature 2018
• Lønning, Putzky, Caan, Welling “Recurrent Inference Machines for
Accelerated MRI Reconstruction”, Medical Image Analysis, 2018
Thank you!

Mais conteúdo relacionado

Mais procurados

Simultaneous Smoothing and Sharpening of Color Images
Simultaneous Smoothing and Sharpening of Color ImagesSimultaneous Smoothing and Sharpening of Color Images
Simultaneous Smoothing and Sharpening of Color ImagesCristina Pérez Benito
 
Fourier transforms
Fourier transformsFourier transforms
Fourier transformsIffat Anjum
 
Fast Fourier Transform
Fast Fourier TransformFast Fourier Transform
Fast Fourier Transformop205
 
Lecture 16 KL Transform in Image Processing
Lecture 16 KL Transform in Image ProcessingLecture 16 KL Transform in Image Processing
Lecture 16 KL Transform in Image ProcessingVARUN KUMAR
 
Predictive coding
Predictive codingPredictive coding
Predictive codingp_ayal
 
Image processing fundamentals
Image processing fundamentalsImage processing fundamentals
Image processing fundamentalsA B Shinde
 
Image Restoration (Order Statistics Filters)
Image Restoration (Order Statistics Filters)Image Restoration (Order Statistics Filters)
Image Restoration (Order Statistics Filters)Kalyan Acharjya
 
Digital Image Processing: Digital Image Fundamentals
Digital Image Processing: Digital Image FundamentalsDigital Image Processing: Digital Image Fundamentals
Digital Image Processing: Digital Image FundamentalsMostafa G. M. Mostafa
 
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...PyData
 
Enhancement in frequency domain
Enhancement in frequency domainEnhancement in frequency domain
Enhancement in frequency domainAshish Kumar
 
Image processing, Noise, Noise Removal filters
Image processing, Noise, Noise Removal filtersImage processing, Noise, Noise Removal filters
Image processing, Noise, Noise Removal filtersKuppusamy P
 
Image Restoration
Image RestorationImage Restoration
Image RestorationPoonam Seth
 
Smoothing Filters in Spatial Domain
Smoothing Filters in Spatial DomainSmoothing Filters in Spatial Domain
Smoothing Filters in Spatial DomainMadhu Bala
 
Convolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsKasun Chinthaka Piyarathna
 

Mais procurados (20)

Simultaneous Smoothing and Sharpening of Color Images
Simultaneous Smoothing and Sharpening of Color ImagesSimultaneous Smoothing and Sharpening of Color Images
Simultaneous Smoothing and Sharpening of Color Images
 
Runge kutta
Runge kuttaRunge kutta
Runge kutta
 
Fourier transforms
Fourier transformsFourier transforms
Fourier transforms
 
Fast Fourier Transform
Fast Fourier TransformFast Fourier Transform
Fast Fourier Transform
 
Lecture 16 KL Transform in Image Processing
Lecture 16 KL Transform in Image ProcessingLecture 16 KL Transform in Image Processing
Lecture 16 KL Transform in Image Processing
 
Predictive coding
Predictive codingPredictive coding
Predictive coding
 
Image processing fundamentals
Image processing fundamentalsImage processing fundamentals
Image processing fundamentals
 
Image Restoration (Order Statistics Filters)
Image Restoration (Order Statistics Filters)Image Restoration (Order Statistics Filters)
Image Restoration (Order Statistics Filters)
 
Convolution&Correlation
Convolution&CorrelationConvolution&Correlation
Convolution&Correlation
 
Digital Image Processing: Digital Image Fundamentals
Digital Image Processing: Digital Image FundamentalsDigital Image Processing: Digital Image Fundamentals
Digital Image Processing: Digital Image Fundamentals
 
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jef...
 
digital filter design
digital filter designdigital filter design
digital filter design
 
Fourier Transform
Fourier TransformFourier Transform
Fourier Transform
 
Object Recognition
Object RecognitionObject Recognition
Object Recognition
 
Wiener Filter
Wiener FilterWiener Filter
Wiener Filter
 
Enhancement in frequency domain
Enhancement in frequency domainEnhancement in frequency domain
Enhancement in frequency domain
 
Image processing, Noise, Noise Removal filters
Image processing, Noise, Noise Removal filtersImage processing, Noise, Noise Removal filters
Image processing, Noise, Noise Removal filters
 
Image Restoration
Image RestorationImage Restoration
Image Restoration
 
Smoothing Filters in Spatial Domain
Smoothing Filters in Spatial DomainSmoothing Filters in Spatial Domain
Smoothing Filters in Spatial Domain
 
Convolutional Neural Network and Its Applications
Convolutional Neural Network and Its ApplicationsConvolutional Neural Network and Its Applications
Convolutional Neural Network and Its Applications
 

Semelhante a Inverse problems in medical imaging

Machine learning for Tomographic Imaging.pdf
Machine learning for Tomographic Imaging.pdfMachine learning for Tomographic Imaging.pdf
Machine learning for Tomographic Imaging.pdfMunir Ahmad
 
Machine learning for Tomographic Imaging.pptx
Machine learning for Tomographic Imaging.pptxMachine learning for Tomographic Imaging.pptx
Machine learning for Tomographic Imaging.pptxMunir Ahmad
 
Seminar_Thoracic EIT_UWO
Seminar_Thoracic EIT_UWOSeminar_Thoracic EIT_UWO
Seminar_Thoracic EIT_UWOPeyman Rahmati
 
SPICE-MATEX @ DAC15
SPICE-MATEX @ DAC15SPICE-MATEX @ DAC15
SPICE-MATEX @ DAC15Hao Zhuang
 
Super resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooSuper resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooJaeJun Yoo
 
Two Dimensional Image Reconstruction Algorithms
Two Dimensional Image Reconstruction AlgorithmsTwo Dimensional Image Reconstruction Algorithms
Two Dimensional Image Reconstruction Algorithmsmastersrihari
 
CARI-2020, Application of LSTM architectures for next frame forecasting in Se...
CARI-2020, Application of LSTM architectures for next frame forecasting in Se...CARI-2020, Application of LSTM architectures for next frame forecasting in Se...
CARI-2020, Application of LSTM architectures for next frame forecasting in Se...Mokhtar SELLAMI
 
Image Reconstruction in Computed Tomography
Image Reconstruction in Computed TomographyImage Reconstruction in Computed Tomography
Image Reconstruction in Computed TomographyAnjan Dangal
 
SPIE 10059-36(Reheman Baikejiang)
SPIE 10059-36(Reheman Baikejiang)SPIE 10059-36(Reheman Baikejiang)
SPIE 10059-36(Reheman Baikejiang)Reheman Baikejiang
 
Sparse Sampling in Digital Image Processing
Sparse Sampling in Digital Image ProcessingSparse Sampling in Digital Image Processing
Sparse Sampling in Digital Image ProcessingEswar Publications
 
Multi-class Classification on Riemannian Manifolds for Video Surveillance
Multi-class Classification on Riemannian Manifolds for Video SurveillanceMulti-class Classification on Riemannian Manifolds for Video Surveillance
Multi-class Classification on Riemannian Manifolds for Video SurveillanceDiego Tosato
 
ct_meeting_final_jcy (1).pdf
ct_meeting_final_jcy (1).pdfct_meeting_final_jcy (1).pdf
ct_meeting_final_jcy (1).pdfssuser2c7393
 
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
 
various methods for image segmentation
various methods for image segmentationvarious methods for image segmentation
various methods for image segmentationRaveesh Methi
 
Unsupervised Learning for Compressed Sensing MRI Using CycleGAN
Unsupervised Learning for Compressed Sensing MRI Using CycleGANUnsupervised Learning for Compressed Sensing MRI Using CycleGAN
Unsupervised Learning for Compressed Sensing MRI Using CycleGANGyutaek Oh
 
Deep Implicit Layers: Learning Structured Problems with Neural Networks
Deep Implicit Layers: Learning Structured Problems with Neural NetworksDeep Implicit Layers: Learning Structured Problems with Neural Networks
Deep Implicit Layers: Learning Structured Problems with Neural NetworksSangwoo Mo
 
2019-06-14:6 - Reti neurali e compressione immagine
2019-06-14:6 - Reti neurali e compressione immagine2019-06-14:6 - Reti neurali e compressione immagine
2019-06-14:6 - Reti neurali e compressione immagineuninfoit
 

Semelhante a Inverse problems in medical imaging (20)

Machine learning for Tomographic Imaging.pdf
Machine learning for Tomographic Imaging.pdfMachine learning for Tomographic Imaging.pdf
Machine learning for Tomographic Imaging.pdf
 
Machine learning for Tomographic Imaging.pptx
Machine learning for Tomographic Imaging.pptxMachine learning for Tomographic Imaging.pptx
Machine learning for Tomographic Imaging.pptx
 
Seminar_Thoracic EIT_UWO
Seminar_Thoracic EIT_UWOSeminar_Thoracic EIT_UWO
Seminar_Thoracic EIT_UWO
 
SPICE-MATEX @ DAC15
SPICE-MATEX @ DAC15SPICE-MATEX @ DAC15
SPICE-MATEX @ DAC15
 
Super resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooSuper resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun Yoo
 
Thesis presentation
Thesis presentationThesis presentation
Thesis presentation
 
Two Dimensional Image Reconstruction Algorithms
Two Dimensional Image Reconstruction AlgorithmsTwo Dimensional Image Reconstruction Algorithms
Two Dimensional Image Reconstruction Algorithms
 
CARI-2020, Application of LSTM architectures for next frame forecasting in Se...
CARI-2020, Application of LSTM architectures for next frame forecasting in Se...CARI-2020, Application of LSTM architectures for next frame forecasting in Se...
CARI-2020, Application of LSTM architectures for next frame forecasting in Se...
 
Image Reconstruction in Computed Tomography
Image Reconstruction in Computed TomographyImage Reconstruction in Computed Tomography
Image Reconstruction in Computed Tomography
 
SPIE 10059-36(Reheman Baikejiang)
SPIE 10059-36(Reheman Baikejiang)SPIE 10059-36(Reheman Baikejiang)
SPIE 10059-36(Reheman Baikejiang)
 
Sparse Sampling in Digital Image Processing
Sparse Sampling in Digital Image ProcessingSparse Sampling in Digital Image Processing
Sparse Sampling in Digital Image Processing
 
NeurIPS22.pptx
NeurIPS22.pptxNeurIPS22.pptx
NeurIPS22.pptx
 
Multi-class Classification on Riemannian Manifolds for Video Surveillance
Multi-class Classification on Riemannian Manifolds for Video SurveillanceMulti-class Classification on Riemannian Manifolds for Video Surveillance
Multi-class Classification on Riemannian Manifolds for Video Surveillance
 
ct_meeting_final_jcy (1).pdf
ct_meeting_final_jcy (1).pdfct_meeting_final_jcy (1).pdf
ct_meeting_final_jcy (1).pdf
 
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
 
various methods for image segmentation
various methods for image segmentationvarious methods for image segmentation
various methods for image segmentation
 
Unsupervised Learning for Compressed Sensing MRI Using CycleGAN
Unsupervised Learning for Compressed Sensing MRI Using CycleGANUnsupervised Learning for Compressed Sensing MRI Using CycleGAN
Unsupervised Learning for Compressed Sensing MRI Using CycleGAN
 
Deep Implicit Layers: Learning Structured Problems with Neural Networks
Deep Implicit Layers: Learning Structured Problems with Neural NetworksDeep Implicit Layers: Learning Structured Problems with Neural Networks
Deep Implicit Layers: Learning Structured Problems with Neural Networks
 
mid_presentation
mid_presentationmid_presentation
mid_presentation
 
2019-06-14:6 - Reti neurali e compressione immagine
2019-06-14:6 - Reti neurali e compressione immagine2019-06-14:6 - Reti neurali e compressione immagine
2019-06-14:6 - Reti neurali e compressione immagine
 

Último

Noida Sector 135 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few C...
Noida Sector 135 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few C...Noida Sector 135 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few C...
Noida Sector 135 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few C...rajnisinghkjn
 
call girls in munirka DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️
call girls in munirka  DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️call girls in munirka  DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️
call girls in munirka DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️saminamagar
 
Book Call Girls in Yelahanka - For 7001305949 Cheap & Best with original Photos
Book Call Girls in Yelahanka - For 7001305949 Cheap & Best with original PhotosBook Call Girls in Yelahanka - For 7001305949 Cheap & Best with original Photos
Book Call Girls in Yelahanka - For 7001305949 Cheap & Best with original Photosnarwatsonia7
 
Housewife Call Girls Hsr Layout - Call 7001305949 Rs-3500 with A/C Room Cash ...
Housewife Call Girls Hsr Layout - Call 7001305949 Rs-3500 with A/C Room Cash ...Housewife Call Girls Hsr Layout - Call 7001305949 Rs-3500 with A/C Room Cash ...
Housewife Call Girls Hsr Layout - Call 7001305949 Rs-3500 with A/C Room Cash ...narwatsonia7
 
9873777170 Full Enjoy @24/7 Call Girls In North Avenue Delhi Ncr
9873777170 Full Enjoy @24/7 Call Girls In North Avenue Delhi Ncr9873777170 Full Enjoy @24/7 Call Girls In North Avenue Delhi Ncr
9873777170 Full Enjoy @24/7 Call Girls In North Avenue Delhi NcrDelhi Call Girls
 
Call Girls Jayanagar Just Call 7001305949 Top Class Call Girl Service Available
Call Girls Jayanagar Just Call 7001305949 Top Class Call Girl Service AvailableCall Girls Jayanagar Just Call 7001305949 Top Class Call Girl Service Available
Call Girls Jayanagar Just Call 7001305949 Top Class Call Girl Service Availablenarwatsonia7
 
97111 47426 Call Girls In Delhi MUNIRKAA
97111 47426 Call Girls In Delhi MUNIRKAA97111 47426 Call Girls In Delhi MUNIRKAA
97111 47426 Call Girls In Delhi MUNIRKAAjennyeacort
 
Call Girls Kanakapura Road Just Call 7001305949 Top Class Call Girl Service A...
Call Girls Kanakapura Road Just Call 7001305949 Top Class Call Girl Service A...Call Girls Kanakapura Road Just Call 7001305949 Top Class Call Girl Service A...
Call Girls Kanakapura Road Just Call 7001305949 Top Class Call Girl Service A...narwatsonia7
 
Book Call Girls in Kasavanahalli - 7001305949 with real photos and phone numbers
Book Call Girls in Kasavanahalli - 7001305949 with real photos and phone numbersBook Call Girls in Kasavanahalli - 7001305949 with real photos and phone numbers
Book Call Girls in Kasavanahalli - 7001305949 with real photos and phone numbersnarwatsonia7
 
Call Girls Hosur Just Call 7001305949 Top Class Call Girl Service Available
Call Girls Hosur Just Call 7001305949 Top Class Call Girl Service AvailableCall Girls Hosur Just Call 7001305949 Top Class Call Girl Service Available
Call Girls Hosur Just Call 7001305949 Top Class Call Girl Service Availablenarwatsonia7
 
High Profile Call Girls Kodigehalli - 7001305949 Escorts Service with Real Ph...
High Profile Call Girls Kodigehalli - 7001305949 Escorts Service with Real Ph...High Profile Call Girls Kodigehalli - 7001305949 Escorts Service with Real Ph...
High Profile Call Girls Kodigehalli - 7001305949 Escorts Service with Real Ph...narwatsonia7
 
Report Back from SGO: What’s New in Uterine Cancer?.pptx
Report Back from SGO: What’s New in Uterine Cancer?.pptxReport Back from SGO: What’s New in Uterine Cancer?.pptx
Report Back from SGO: What’s New in Uterine Cancer?.pptxbkling
 
Radiation Dosimetry Parameters and Isodose Curves.pptx
Radiation Dosimetry Parameters and Isodose Curves.pptxRadiation Dosimetry Parameters and Isodose Curves.pptx
Radiation Dosimetry Parameters and Isodose Curves.pptxDr. Dheeraj Kumar
 
call girls in green park DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️
call girls in green park  DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️call girls in green park  DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️
call girls in green park DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️saminamagar
 
Glomerular Filtration and determinants of glomerular filtration .pptx
Glomerular Filtration and  determinants of glomerular filtration .pptxGlomerular Filtration and  determinants of glomerular filtration .pptx
Glomerular Filtration and determinants of glomerular filtration .pptxDr.Nusrat Tariq
 
Housewife Call Girls Bangalore - Call 7001305949 Rs-3500 with A/C Room Cash o...
Housewife Call Girls Bangalore - Call 7001305949 Rs-3500 with A/C Room Cash o...Housewife Call Girls Bangalore - Call 7001305949 Rs-3500 with A/C Room Cash o...
Housewife Call Girls Bangalore - Call 7001305949 Rs-3500 with A/C Room Cash o...narwatsonia7
 
Call Girls Electronic City Just Call 7001305949 Top Class Call Girl Service A...
Call Girls Electronic City Just Call 7001305949 Top Class Call Girl Service A...Call Girls Electronic City Just Call 7001305949 Top Class Call Girl Service A...
Call Girls Electronic City Just Call 7001305949 Top Class Call Girl Service A...narwatsonia7
 
Pharmaceutical Marketting: Unit-5, Pricing
Pharmaceutical Marketting: Unit-5, PricingPharmaceutical Marketting: Unit-5, Pricing
Pharmaceutical Marketting: Unit-5, PricingArunagarwal328757
 
Dwarka Sector 6 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few Cl...
Dwarka Sector 6 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few Cl...Dwarka Sector 6 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few Cl...
Dwarka Sector 6 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few Cl...rajnisinghkjn
 
Mumbai Call Girls Service 9910780858 Real Russian Girls Looking Models
Mumbai Call Girls Service 9910780858 Real Russian Girls Looking ModelsMumbai Call Girls Service 9910780858 Real Russian Girls Looking Models
Mumbai Call Girls Service 9910780858 Real Russian Girls Looking Modelssonalikaur4
 

Último (20)

Noida Sector 135 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few C...
Noida Sector 135 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few C...Noida Sector 135 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few C...
Noida Sector 135 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few C...
 
call girls in munirka DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️
call girls in munirka  DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️call girls in munirka  DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️
call girls in munirka DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️
 
Book Call Girls in Yelahanka - For 7001305949 Cheap & Best with original Photos
Book Call Girls in Yelahanka - For 7001305949 Cheap & Best with original PhotosBook Call Girls in Yelahanka - For 7001305949 Cheap & Best with original Photos
Book Call Girls in Yelahanka - For 7001305949 Cheap & Best with original Photos
 
Housewife Call Girls Hsr Layout - Call 7001305949 Rs-3500 with A/C Room Cash ...
Housewife Call Girls Hsr Layout - Call 7001305949 Rs-3500 with A/C Room Cash ...Housewife Call Girls Hsr Layout - Call 7001305949 Rs-3500 with A/C Room Cash ...
Housewife Call Girls Hsr Layout - Call 7001305949 Rs-3500 with A/C Room Cash ...
 
9873777170 Full Enjoy @24/7 Call Girls In North Avenue Delhi Ncr
9873777170 Full Enjoy @24/7 Call Girls In North Avenue Delhi Ncr9873777170 Full Enjoy @24/7 Call Girls In North Avenue Delhi Ncr
9873777170 Full Enjoy @24/7 Call Girls In North Avenue Delhi Ncr
 
Call Girls Jayanagar Just Call 7001305949 Top Class Call Girl Service Available
Call Girls Jayanagar Just Call 7001305949 Top Class Call Girl Service AvailableCall Girls Jayanagar Just Call 7001305949 Top Class Call Girl Service Available
Call Girls Jayanagar Just Call 7001305949 Top Class Call Girl Service Available
 
97111 47426 Call Girls In Delhi MUNIRKAA
97111 47426 Call Girls In Delhi MUNIRKAA97111 47426 Call Girls In Delhi MUNIRKAA
97111 47426 Call Girls In Delhi MUNIRKAA
 
Call Girls Kanakapura Road Just Call 7001305949 Top Class Call Girl Service A...
Call Girls Kanakapura Road Just Call 7001305949 Top Class Call Girl Service A...Call Girls Kanakapura Road Just Call 7001305949 Top Class Call Girl Service A...
Call Girls Kanakapura Road Just Call 7001305949 Top Class Call Girl Service A...
 
Book Call Girls in Kasavanahalli - 7001305949 with real photos and phone numbers
Book Call Girls in Kasavanahalli - 7001305949 with real photos and phone numbersBook Call Girls in Kasavanahalli - 7001305949 with real photos and phone numbers
Book Call Girls in Kasavanahalli - 7001305949 with real photos and phone numbers
 
Call Girls Hosur Just Call 7001305949 Top Class Call Girl Service Available
Call Girls Hosur Just Call 7001305949 Top Class Call Girl Service AvailableCall Girls Hosur Just Call 7001305949 Top Class Call Girl Service Available
Call Girls Hosur Just Call 7001305949 Top Class Call Girl Service Available
 
High Profile Call Girls Kodigehalli - 7001305949 Escorts Service with Real Ph...
High Profile Call Girls Kodigehalli - 7001305949 Escorts Service with Real Ph...High Profile Call Girls Kodigehalli - 7001305949 Escorts Service with Real Ph...
High Profile Call Girls Kodigehalli - 7001305949 Escorts Service with Real Ph...
 
Report Back from SGO: What’s New in Uterine Cancer?.pptx
Report Back from SGO: What’s New in Uterine Cancer?.pptxReport Back from SGO: What’s New in Uterine Cancer?.pptx
Report Back from SGO: What’s New in Uterine Cancer?.pptx
 
Radiation Dosimetry Parameters and Isodose Curves.pptx
Radiation Dosimetry Parameters and Isodose Curves.pptxRadiation Dosimetry Parameters and Isodose Curves.pptx
Radiation Dosimetry Parameters and Isodose Curves.pptx
 
call girls in green park DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️
call girls in green park  DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️call girls in green park  DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️
call girls in green park DELHI 🔝 >༒9540349809 🔝 genuine Escort Service 🔝✔️✔️
 
Glomerular Filtration and determinants of glomerular filtration .pptx
Glomerular Filtration and  determinants of glomerular filtration .pptxGlomerular Filtration and  determinants of glomerular filtration .pptx
Glomerular Filtration and determinants of glomerular filtration .pptx
 
Housewife Call Girls Bangalore - Call 7001305949 Rs-3500 with A/C Room Cash o...
Housewife Call Girls Bangalore - Call 7001305949 Rs-3500 with A/C Room Cash o...Housewife Call Girls Bangalore - Call 7001305949 Rs-3500 with A/C Room Cash o...
Housewife Call Girls Bangalore - Call 7001305949 Rs-3500 with A/C Room Cash o...
 
Call Girls Electronic City Just Call 7001305949 Top Class Call Girl Service A...
Call Girls Electronic City Just Call 7001305949 Top Class Call Girl Service A...Call Girls Electronic City Just Call 7001305949 Top Class Call Girl Service A...
Call Girls Electronic City Just Call 7001305949 Top Class Call Girl Service A...
 
Pharmaceutical Marketting: Unit-5, Pricing
Pharmaceutical Marketting: Unit-5, PricingPharmaceutical Marketting: Unit-5, Pricing
Pharmaceutical Marketting: Unit-5, Pricing
 
Dwarka Sector 6 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few Cl...
Dwarka Sector 6 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few Cl...Dwarka Sector 6 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few Cl...
Dwarka Sector 6 Call Girls ( 9873940964 ) Book Hot And Sexy Girls In A Few Cl...
 
Mumbai Call Girls Service 9910780858 Real Russian Girls Looking Models
Mumbai Call Girls Service 9910780858 Real Russian Girls Looking ModelsMumbai Call Girls Service 9910780858 Real Russian Girls Looking Models
Mumbai Call Girls Service 9910780858 Real Russian Girls Looking Models
 

Inverse problems in medical imaging

  • 1. Inverse problems in medical imaging Nikita Moriakov Diagnostic Image Analysis Group Department of Radiology and Nuclear Medicine Radboud University Medical Center, Nijmegen
  • 2. Plan • Inverse problems • Deep Learning in Inverse Problems: Fully learned inversion vs. Learned iterative schemes • Results and future work
  • 4. What is inverse problem? • 𝑓𝑡𝑟𝑢𝑒 ∈ 𝑋 is an unknown true model parameter, 𝑔 ∈ 𝑌 is data, 𝑒 is sample from measurement noise and 𝐴: 𝑋 → 𝑌 is a continuous operator mapping model parameter to data (in the absence of noise) • Examples: CT & MR reconstruction, denoising, inpainting.
  • 5. Examples: Radon Transform • Let 𝑓 ∈ 𝐿1 ℝ2 be a function such that 𝑓(𝑥, 𝑦) is the attenuation coefficient of scanned object at point (𝑥, 𝑦) • If X-ray going along the line 𝐿 has incident intensity 𝐼0, the outcoming intensity equals 𝐼0 𝑒 − 𝑥,𝑦 ∈𝐿 𝑓 𝑥,𝑦 𝑑𝐿
  • 6. Examples: Radon Transform • Parametrize all lines by the angle 𝜃 and the distance 𝑠 to the origin • The Radon transform of 𝑓 is a function of 𝑠 ∈ ℝ, 𝜃 ∈ [0, 2 𝜋) given by
  • 8. Back projection (key for inversion)
  • 9. Examples: Radon Transform • This direct analytic inversion is called Filtered Back Projection today. • Radon transform is invertible (when we know projections from all directions and all rays intersecting the object).
  • 10. Examples: DBT • Available since late 2000s. • Rapidly replacing Digital Mammography • Can have resolution as high as DM standards.
  • 11. Examples: DBT • The x-ray tube moves in an arc over the compressed breast capturing multiple images of each breast from different angles in a continuous or step-and-shoot fashion.
  • 12. Examples: MR • Fourier transform ℱ maps images to frequency domain. • Some measurements in this domain are taken, giving subsampling mask 𝑃. • Inverse Fourier transform maps back to the image domain. • Reconstructed image can deviate from target if k-space is undersampled.
  • 13. Problems with inverse problems? • 𝐴 can have non-trivial kernel. E.g., for CT with limited number of view angles the following holds: • 𝐴 can have discontinuous inverse, thus variations in noise can have strong effect on reconstruction.
  • 14. Bayesian view and regularization, MAP • Finding most likely reconstruction given measurements amounts to finding 𝑎𝑟𝑔𝑚𝑎𝑥𝑖𝑚𝑎𝑔𝑒 𝑃 𝐼𝑚𝑎𝑔𝑒 𝑀𝑒𝑎𝑠). • 𝑎𝑟𝑔𝑚𝑎𝑥𝑖𝑚𝑎𝑔𝑒 𝑃 𝐼𝑚𝑎𝑔𝑒 𝑀𝑒𝑎𝑠) = 𝑎𝑟𝑔𝑚𝑎𝑥𝑖𝑚𝑎𝑔𝑒 𝑃 𝑀𝑒𝑎𝑠 𝐼𝑚𝑎𝑔𝑒)⋅𝑃 𝐼𝑚𝑎𝑔𝑒 𝑃(𝑀𝑒𝑎𝑠) = 𝑎𝑟𝑔𝑚𝑎𝑥𝑖𝑚𝑎𝑔𝑒 (log 𝑃 𝑀𝑒𝑎𝑠 𝐼𝑚𝑎𝑔𝑒 + log 𝑃(𝐼𝑚𝑎𝑔𝑒)) • log 𝑃(𝑀𝑒𝑎𝑠|𝐼𝑚𝑎𝑔𝑒) is the log-likelihood of observed data, log 𝑃(𝐼𝑚𝑎𝑔𝑒) is the prior term. • Prior term is used for regularization such as TV regularization.
  • 15. Deep Learning for Inverse Problems
  • 16. Inverse problems with DL Fully learned data driven reconstruction • Generic parametrization by a neural network to find an inverse mapping 𝑅 𝜃: 𝑌 → 𝑋 with 𝜃 being the neural network weights • No need to have explicit forward operator or data likelihood • Need to use fully connected layers and hence requires a lot of parameters. Learned iterative schemes • Contains explicit knowledge of forward operator built in the architecture of 𝑅 𝜃: 𝑌 → 𝑋 • Architecture motivated by existing optimization algorithms
  • 17. Inverse problems with DL Learned regularizers • Train a regularizer 𝑆 𝜃: 𝑋 → ℝ separately, which is parametrized by a neural network, and is ideally proportional to the image prior (Bayesian view). • Can be trained adversarily.
  • 18. Fully learned inference • Zhu, Liu, Rosen, Rosen “Image reconstruction by domain transform manifold learning” 2018
  • 19. Learned Iterative Schemes: LPD • Learned Primal-Dual (LPD) is an example of learned iterative schemes. • Architecture motivated by Primal-Dual Hybrid Gradient Method.
  • 20. Learned Primal-Dual • A deep neural network • Iterative procedure inspired by Primal-Dual Hybrid Gradient algorithm • Consists of a primal/dual reconstruction blocks which performs small “steps” in image and projection space respectively.
  • 22. Results (Adler & Öktem)
  • 23. Learned Iterative Schemes: RIM • The goal in MAP estimate is finding • This is often done in via an iterative scheme • To avoid the need to learn prior, we can “generalize” this to the form • So can optimize this as a recurrent neural network.
  • 24. Recurrent Inference Machines for MR Lonning, Putzky, Caan, Welling Recurrent Inference Machines for Accelerated MRI Reconstruction 2018
  • 25. RIM for MRI Reconstruction Lonning, Putzky, Caan, Welling Recurrent Inference Machines for Accelerated MRI Reconstruction 2018
  • 27. SPIE 2019 Medical Imaging
  • 28. Data for the experiment • Synthetic breast images generated by realistic digital breast phantom (from I. Sechopoulos et al.) • 25 view angles: [-24, -22, … , 22, 24] deg
  • 31. LPD for DBT architecture (DBToR) 𝑚 𝑇(𝑚)
  • 33. Results (end of training)
  • 36. Compressed breast phantom Classification Image Segmentation: Skin – Adipose – Glandular Caballo M. et al . 2018 “An Unsupervised Automatic Segmentation algorithm for breast tissue” – Med. Phys. Finite Element Compression BCT images acquired from patients at Radboudumc
  • 37. Finite Element Compression Breast Density Map • Create a mesh of the breast • Simulate the compression of soft tissue (adipose, glandular & skin) using the high-performance explicit finite element solver, developed for medical application
  • 38. Compression Compression The breast support is move up by 20 mm (to make the bottom flat); the compression is performed by moving down the compression paddle Voxel Resolution of (0.273 mm)3
  • 40. Sources • Arridge, Maass, Öktem, Schönlieb “Solving Inverse Problems Using Data Driven Models”, Acta Numerica 2019. • Adler, Öktem “Learned Primal-dual Reconstruction” • Markoe, “Analytic Tomography” • Zhu, Liu, Rosen, Rosen “Image reconstruction by domain transform manifold learning”, Nature 2018 • Lønning, Putzky, Caan, Welling “Recurrent Inference Machines for Accelerated MRI Reconstruction”, Medical Image Analysis, 2018