Efficient Methods for
Computational Imaging and Radiology
Sean I. Young, PhD
Instructor, Harvard Medical School
Research Affiliate, CSAIL, MIT
Apr 25, 2023
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 2
Outline
• Previous and Current Research
• Computational imaging and radiology
• Future research directions and conclusion
• Teaching and outreach
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 3
About me...
Stanford, CASydney, NSW Boston, MA
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 4
About me...
Stanford, CASydney, NSW
—PhD, EE
Boston, MA
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 5
Efficient Algorithms for Imaging and Vision Problems Sean I. Young Bernd Girod Slide 8 of 9
Select publications
Young et al. Graph Laplacian regularization for optical flow estimation IEEE Trans. Image Process., 2019
Input image pair
Pixel-graph construction
Baseline flow
Our flow field
Optical flow estimation as a graduated non-convex graph-regularized optimization problem. (Work done
during PhD at UNSW.)
Sydney, NSW
—PhD, EE
—Video Compression
—Inverse Problems
About me...
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 6
About me...
Efficient Algorithms for Imaging and Vision Problems Sean I. Young Bernd Girod Slide 4 of 9
Select publications
Young et al. Fast optical flow extraction from compressed video IEEE Trans. Image Process., 2020
Decoded picture
Decoded motion parameters
Recovered motion
Ground-truth motion
Extraction of sub-pixel-accurate motion fields from coded motion parameters using weighted filtering. We
achieve a 100× speed-up over estimating the motion from scratch.
Sydney, NSW
—PhD, EE
—Video Compression
—Inverse Problems
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 7
About me...
Efficient Algorithms for Imaging and Vision Problems Sean I. Young Bernd Girod Slide 6 of 9
Select publications
Young et al. Gaussian lifting for fast bilateral and nonlocal means filtering IEEE Trans. Image Process., 2020
Original picture
Gaussian lifting
Filtered picture
Filter error (52.5dB)
Bilateral filtering posed as a pseudo-wavelet transform in the bilateral space. Up to a 5× speed-up over
other fast bilateral filter implementations.
Sydney, NSW
—PhD, EE
—Video Compression
—Inverse Problems
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 8
About me...
Stanford, CA
—Postdoc, EE
Sydney, NSW Boston, MA
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 9
Stanford, CA
—Postdoc, EE
—Compression
—Computational Imaging
About me...
Efficient Algorithms for Imaging and Vision Problems Sean I. Young Bernd Girod Slide 3 of 9
Select publications
Young et al. NLOS surface reconstruction using the Directional LCT CVPR (oral), 2020
Capture setup
Captured transients
Recovered surface
Ground-truth surface
Estimation of hidden surface normals posed as a vectorial deconvolution problem. We achieve a 1,000×
speed-up over previous methods.
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 10
About me...
Efficient Algorithms for Imaging and Vision Problems Sean I. Young Bernd Girod Slide 4 of 9
Select publications
Young et al. Fast optical flow extraction from compressed video IEEE Trans. Image Process., 2020
Decoded picture
Decoded motion parameters
Recovered motion
Ground-truth motion
Extraction of sub-pixel-accurate motion fields from coded motion parameters using weighted filtering. We
achieve a 100× speed-up over estimating the motion from scratch.
Stanford, CA
—Postdoc, EE
—Compression
—Computational Imaging
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 11
Stanford, CA
—Postdoc, EE
—Compression
—Computational Imaging
About me...
Efficient Algorithms for Imaging and Vision Problems Sean I. Young Bernd Girod Slide 5 of 9
Select publications
Young et al. Transform quantization for CNN compression IEEE Trans. Pattern Anal. Mach. Intell., 2020
Kernel quantization and pruning posed as a rate-distortion optimization problem. We achieve a 10×
inference speed-up over the default 8-bit quantization.
2021
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 12
About me...
Boston, MA
—Instructor, Radiology
Stanford, CASydney, NSW
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 13
Boston, MA
—Computational Radiology
—Computational Imaging
About me...
Young et al. Supervision by denoising. IEEE Tra n s. Pattern Anal Mach Intell, 2022
Semi-supervised medical image segmentation posed as a denoising problem. We achieve a 10x reduction in the
number of labeled examples required while significantly improving reconstruction accuracy.
FS reference nnU-Net Post-denoise Temporal ensembling SUD (ours)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 14
About me...
Young et al. Fully convolutional SVR for single-stack MRI. CVPR, 2024
Slice-to-volume reconstruction as a self-supervised image registration task. We enable 3D reconstruction from a
single stack of MR slices, which has not previously been done.
Monocular depth estimation [4–8] Single-stack slice-to-volume reconstruction (Ours)
Boston, MA
—Computational Radiology
—Computational Imaging
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 15
About me...
Young et al. Fully convolutional SVR for single-stack MRI. CVPR, 2024
Slice-to-volume reconstruction as a self-supervised image registration task. We enable 3D reconstruction from a
single stack of MR slices, which has not previously been done.
Monocular depth estimation [4–8] Single-stack slice-to-volume reconstruction (Ours)
Boston, MA
—Computational Radiology
—Computational Imaging
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 16
Outline
• Introduction to myself and my research
• Computational imaging and radiology
• Future research directions and conclusion
• Teaching and outreach
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 17
Computational Radiology
Inverse problems
3D Object
Reflections
on a wall
Non-line-of-sight surface reconstruction
(Young, 2020)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 18
Inverse problems
Computational Radiology
3D Volume
2D Acquisition
Slice-to-volume reconstruction (SVR)
(Young, 2024)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 19
Efficient methods
Computational Radiology
Linear algebra
and signal processing
Signal processing
and machine learning
Machine learning
and signal compression
Transform quantization for CNN compression
(Young, 2022)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 20
Ongoing Work
3D brain imaging using conventional cameras and machine learning
Dissection photography is routine in nearly every brain bank. Dissected into coronal slices and photographed
before further blocking and histological slices. Leverage existing data for 3D reconstruction.
(a) Slab preparation (b) Slab photographs (c) 3D reconstruction
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 21
Ongoing Work
Ultra-precision clinical imaging and detection of Alzheimer’s Disease (NIH K99AG081493)
Longitudinal image registration and change detection as a supervised learning problem. We achieve a 10-fold
improvement in registration accuracy compared to unsupervised (VoxelMorph) approaches.
Slice-to-Volume Reconstruction
for Single-Stack MRI
Based on “Fully convolutional slice-to-volume reconstruction for single-stack MRI”. CVPR 2024.
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 23
Introduction
Figure from https://answers.childrenshospital.org/neurodevelopment-congenital-heart-disease/
Slice-based MR acquisitions can freeze subject motion in-plane.
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 24
2D MR Acquisition
Axial
Stack
Axial view Axial view Axial view Coronal view Sagittal view
Figure adapted from Gholipour et al. (2010)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 25
2D MR Acquisition
Axial
Stack
Axial view
Figure adapted from Gholipour et al. (2010)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 26
2D MR Acquisition
Axial
Stack
Axial view
Figure adapted from Gholipour et al. (2010)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 27
2D MR Acquisition
Axial
Stack
Axial view
Figure adapted from Gholipour et al. (2010)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 28
2D MR Acquisition
Axial
Stack
Coronal view
Figure adapted from Gholipour et al. (2010)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 29
Axial
Stack
2D MR Acquisition
Sagittal view
Figure adapted from Gholipour et al. (2010)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 30
Slice-to-Volume Reconstruction
Axial
Stack
Coronal
Stack
Sagittal
Stack
Reconstructed
Volume
Figure adapted from Sobotka et al. (2022)
SVR aims to align a stack of acquired slices thereby
removing the remaining motion across slices.
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 31
Towards Fully Convolutional SVR
Figure adapted from Uus et al. (2020)
Classical iterative approaches
can be slow
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 32
Towards Fully Convolutional SVR
1 x 1 x 9
Anchor
points
(x1,y1,z1)
(x2,y2,z2)
(x3,y3,z3)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 33
Towards Fully Convolutional SVR
Figure adapted from Xu et al. (2022)
Bleeding-edge transformer
models!
(a)
(b)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 34
Towards Fully Convolutional SVR
Figure adapted from Xu et al. (2022)
Bleeding-edge transformer
models!
(a)
(b)
Unable to reconstruct accurately
from a single slice stack!
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 35
Towards Fully Convolutional SVR
Figure adapted from Xu et al. (2022)
Bleeding-edge transformer
models!
(a)
(b)
We can predict slice motion
instead of slice positions
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 36
Stereo Disparity Estimation
Szeliski and Golland (1999)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 37
Stereo Disparity Estimation
Szeliski and Golland (1999)
✓
✓
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 38
Stereo Disparity Estimation
Right view
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 39
Stereo Disparity Estimation
Left view
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 40
Stereo Disparity Estimation
Right view
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 41
Stereo Disparity Estimation
Disparity field
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 42
Monocular Disparity Estimation
U-Net
Deep learning allows disparity estimation from a SINGLE view!
✓
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 43
Monocular Disparity Estimation
Khan et al. Deep Learning-Based Monocular Depth Estimation Methods—A State-of-the-Art Review
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 44
Monocular Disparity Estimation
Khan et al. Deep Learning-Based Monocular Depth Estimation Methods—A State-of-the-Art Review
Single-stack MRI?
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 45
Towards Fully Convolutional SVR
• 3D representation: 3D scene (2D + depth).
• Reprojection: 2D view.
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 46
Towards Fully Convolutional SVR
• 3D representation: 3D volume (Splatting).
• Reprojection: 2D slices (Slicing).
• Registration of an unknown moving image to a fixed image.
?
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 47
Fully Convolutional SVR
• Suppose we have both a 3D volume and a slice stack.
• Reconstruct by registering the slice stack to the 3D volume.
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 48
Fully Convolutional SVR
• We do not assume the availability of a reference volume.
• Pairwise image registration between fixed (stack) and moving (volume).
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 49
Fully Convolutional SVR
• We do not assume the availability of a reference volume.
• Pairwise image registration between fixed (stack) and moving (volume).
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 50
Fully Convolutional SVR
• We do not assume the availability of a reference volume.
• Pairwise image registration between fixed (stack) and moving (volume).
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 51
Supervised Learning
• Train CNN on paired (slice stack, motion stack) examples
• Synthesize slice stacks with arbitrary but known motion
𝓛
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 52
Supervised Learning
• Training loss: L2 loss unduly forces all reconstructions to be aligned
precisely in a particular orientation.
andBut
Splat
✓ ✗ ✗
𝓛
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 53
Supervised Learning
• Training loss: L2 loss unduly forces all reconstructions to be aligned
precisely in a particular orientation.
andBut
Splat
✓ ✗ ✗
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 54
Supervised Learning
• Training loss: L2 loss unduly forces all reconstructions to be aligned
precisely in a particular orientation.
andand
Splat
✓ ✓ ✓
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 55
Supervised Learning
• Uncompensated loss penalizes
global rotations and translations.
• Translation-compensation
improves prediction.
• Rigid compensation
improves prediction further.
Motion MSE (voxels)
Epochs
Uncompensated
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 56
Supervised Learning
• Uncompensated loss penalizes
global rotations and translations.
• Translation-compensation
improves prediction.
• Rigid compensation
improves prediction further.
Motion MSE (voxels)
Epochs
Uncompensated
Trans-comp
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 57
Supervised Learning
• Uncompensated loss penalizes
global rotations and translations.
• Translation-compensation
improves prediction.
• Rigid compensation
improves prediction further.
Motion MSE (voxels)
Epochs
Uncompensated
Trans-comp
Rigid-comp
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 58
Supervised Learning
• Splatted volume has regions of missing intensities.
• Interpolate missing data to produce 3D reconstruction.
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 59
Supervised Learning
• Splatted volume has regions of missing intensities.
• Interpolate missing data to produce 3D reconstruction.
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 60
Results
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 61
Results
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 62
Results
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 63
Results
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 64
Results
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 65
Results
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 66
Results
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 67
Results
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 68
Results
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 69
Results
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 70
Results
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 71
Results
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 72
Results
Non-line-of-sight surface reconstruction
Based on “NLOS Surface Reconstruction Using the D-LCT”. CVPR 2020 (oral)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 74
Non-line-of-sight Imaging
Wall
Hidden
Object
Occluder
• Suppose we want to image a hidden
object around the corner.
Laser and
Detector
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 75
Non-line-of-sight Imaging
Wall
Hidden
Object
Occluder
• Suppose we want to image a hidden
object around the corner.
Laser and
Detector
Time (seconds)
Photons Detected
0
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 76
Non-line-of-sight Imaging
Wall
Hidden
Object
Occluder
• At t
1
, we have photon contributions
from points on the hidden object that
are t
1
light-seconds away from the wall.
Laser and
Detector
Time (seconds)
Photons Detected
0
t
1
t
1
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 77
Non-line-of-sight Imaging
Wall
Hidden
Object
Occluder
• At t
2
, we have photon contributions
from points on the hidden object that
are t
2
light-seconds away from the wall.
Laser and
Detector
Time (seconds)
Photons Detected
0
t
2
t
2
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 78
Non-line-of-sight Imaging
Wall
Hidden
Object
Occluder
• Forward model relates time-varying
photon count at a wall points to the
surface of the hidden object.
Laser and
Detector
t
𝑦
𝑥
𝑧
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 79
Non-line-of-sight Imaging
Wall
Hidden
Object
Occluder
• By scanning multiple known locations
on the wall, we can collect indirect
observations of the hidden scene.
Laser and
Detector
Time (seconds)
Photons Detected
0
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 80
Non-line-of-sight Imaging
Wall
Hidden
Object
Occluder
• By scanning multiple known locations
on the wall, we can collect indirect
observations of the hidden scene.
Laser and
Detector
Time (seconds)
Photons Detected
0
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 81
Non-line-of-sight Imaging
Wall
Hidden
Object
Occluder
• By scanning multiple known locations
on the wall, we can collect indirect
observations of the hidden scene.
Laser and
Detector
Time (seconds)
Photons Detected
0
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 82
Non-line-of-sight Imaging
Photons Detected
Hidden
Object Surface
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 83
Non-line-of-sight Imaging
Photons Detected
Hidden
Object Surface
Unable to accurately resolve
surface normals!
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 84
Non-line-of-sight Imaging
Wall
Hidden
Object
Occluder
• Forward model relates time-varying
photon count at a wall points to the
surface of the hidden object.
Laser and
Detector
t
𝑦
𝑥
𝑧
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 85
Non-line-of-sight Imaging
Wall
Hidden
Object
Occluder
• Photon contributions proportional
to the cosine of the angle
θ
between
surface normal and incident ray.
Laser and
Detector
θ
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 86
Non-line-of-sight Imaging
Wall
Hidden
Object
Occluder
• Photon contributions proportional
to the cosine of the angle
θ
between
surface normal and incident ray.
Laser and
Detector
θ
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 87
Non-line-of-sight Imaging
Wall
Hidden
Object
Occluder
• Photon contributions proportional
to the cosine of the angle
θ
between
surface normal and incident ray.
Laser and
Detector
θ
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 88
Non-line-of-sight Imaging
Photons Detected
Hidden
Object Surface
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 89
Non-line-of-sight Imaging
Photons Detected
Hidden Object
Surface Normals
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 90
Non-line-of-sight Imaging
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 91
Non-line-of-sight Imaging
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 92
Non-line-of-sight Imaging
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 93
Non-line-of-sight Imaging
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 94
Non-line-of-sight Imaging
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 95
Non-line-of-sight Imaging
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 96
Non-line-of-sight Imaging
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 97
Non-line-of-sight Imaging
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 98
Outline
• Introduction to myself and my research
• Computational imaging and radiology
• Future research directions and conclusion
• Teaching and outreach
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 99
Going forward…
• Temporal view (or view from “above”)
https://openaccess.thecvf.com/content_CVPR_2019/papers/Choy_4D_Spatio-Temporal_ConvNets_Minkowski_Convolutional_Neural_Networks_CVPR_2019_paper.pdf
Acquired timepoints
Segmentation targets
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 100
Going forward…
Foundations of large network model quantization (IEEE Trans Pattern Anal Mach Intell)
Longitudinal image registration and change detection as a supervised learning problem. We achieve a 10-fold
improvement in registration accuracy compared to unsupervised (VoxelMorph) approaches.
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 101
Going forward…
• Detect neuroanatomical change predictive of AD
• Compensate for the motion and take the difference
0m
12m
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 102
Going forward…
• Detect neuroanatomical change predictive of AD
• Compensate for the motion and take the difference
0m
12m
0m – 12m
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 103
Roadmap
PI’s sub-aims and *other tasks across K99/R00, with definite (YES), potential (MAYBE), and unlikely (NO) effort in these years.
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 104
Outline
• Introduction to myself and my research
• Computational imaging and radiology
• Future research directions and conclusion
• Teaching and outreach
Teaching and Outreach
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 111
Computational Radiology Lab
Computational
Radiology
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 112
Computational Radiology Lab
Computational
Radiology
Recruit
Diversely
Reach Out
Individually
Respect
Personal Space
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 113
Computational Radiology Lab
Computational
Methods
Recruit
Diversely
Reach Out
Individually
Respect
Personal Space
Not only graduate students but
also high school students
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 114
Computational Radiology Lab
Computational
Methods
Recruit
Diversely
Reach Out
Individually
Respect
Personal Space
Not only graduate students but
also high school students
Crunch culture can be toxic and
put undue pressure on students
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 115
Computational Radiology Lab
Computational
Radiology
Recruit
Diversely
Reach Out
Individually
Respect
Personal Space
Not only graduate students but
also high school students
Crunch culture can be toxic and
put undue pressure on students
Ensure students have what they
need. Mental well-being.
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 116
Computational Radiology Lab
Computational
Radiology
Recruit
Diversely
Reach Out
Individually
Respect
Personal Space
Not only graduate students but
also high school students
Crunch culture can be toxic and
put undue pressure on students
Ensure students have what they
need. Mental well-being.
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 117
Teaching
• Artificial Intelligence and Machine Learning (4 trimesters)
• Kaplan Australia and New Zealand (Online, 2022–2024)
• Advanced Digital Signal Processing (1 semester)
• University of New South Wales, Sydney, Australia (2018)
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 118
Teaching
• 344. Introduction to Digital Signal Processing.
• 385. Signals, Systems, & Learning.
• 447. Information Theory.
• 412. Machine Learning for Signal Processing.
• 414–5. Image Processing & Analysis.
• 432. Medical Imaging Systems.
• 433. Medical Image Analysis.
Efficient algorithms for computational radiology and imaging Sean I. Young Slide 119
Acknowledgments
Sean I. Young Yaël Balbastre Margherita Firenze David Taubman
Bernd Girod Polina Golland Bruce Fischl J Eugenio Iglesias
