Programme
MICCAI 2023 Workshop on Computational Diffusion MRI
Full programme below! Keep scrolling for an overview of our keynote speakers.
CDMRI Workshop including the QuantConn Challenge
ALL TIMES ARE GIVEN IN GMT-7 (Vancouver time)
Welcome (13:30 – 13:35)
13:30 – 13:35
Welcome and Introduction
Keynote Lecture 1 (13:35 – 13:55)
13:35 – 13:55
Demian Wassermann
Inria, CEA, Université Paris-Saclay, Palaiseau, France
How do we link diffusion MRI with brain structure and cognition? Breaching the gap between classical neuroanatomy and machine learning.
Oral Session 1 (13:55 – 14:25)
13:55 – 14:05
Subnet communicability: Diffusive communication across the brain through a backbone subnetwork
Speaker: Yusuf Osmanlioglu
14:05 – 14:15
ReTrace: Topological evaluation of white matter tractography algorithms using Reeb graphs
Speaker: S. Shailja
14:15 – 14:25
Advanced diffusion MRI modeling sheds light on FLAIR white matter hyperintensities in an aging cohort
Speaker: Kelly Chang
Oral Session 2 (14:25 – 14:55)
14:25 – 14:35
Anisotropic fanning aware low-rank tensor approximation based tractography
Speaker: Johanes Grün
14:35 – 14:45
Diffusion phantom study of fiber crossings at varied angles reconstructed with ODF-fingerprinting
Speaker: Patryk Filipiak
14:45 – 14:55
A unified single-stage learning model for estimating fiber orientation distribution functions on heterogeneous multi-shell diffusion-weighted MRI
Speaker: Yuankai Huo
Keynote Lecture 2 (14:55 – 15:15)
14:55 – 15:15
Jennifer A. McNab
Stanford University, California, USA
Multimodal integration of diffusion MRI
Power-pitch Session 1 (15:15 – 15:35)
Voxlines: streamline transparency through voxelization and view-dependent line orders
Speaker: Besm Osman
FASSt: Filtering via symmetric Autoencoder for Spherical Superficial white matter Tractography
Speaker: Yuan Li
BundleCleaner: unsupervised denoising and subsampling of diffusion MRI-derived tractography data
Speaker: Yixue Feng
Improving multi-tensor fitting with global information from track orientation density imaging
Speaker: Erick Hernandez Gutierrez
Automatic fast and reliable recognition of a small brain white matter bundle
Speaker: John Kruper
BundleSeg: A versatile, reliable and reproducible approach to white matter bundle segmentation
Speaker: Etienne St-Onge
Coffee break (15:35 – 16:00)
Power-pitch Session 2 (16:00 – 16:20)
Automated mapping of residual distortion severity in diffusion MRI
Speaker: Yonggang Shi
Neural spherical harmonics for structurally coherent continuous representation of diffusion MRI signal
Speaker: Tom Hendriks
Fast acquisition for diffusion tensor tractography
Speaker: Omri Leshem
Self supervised denoising diffusion probabilistic models for abdominal DW-MRI
Speaker: Serge Vasylechko
A deep network for explainable prediction of non-imaging phenotypes using anatomical multi-view data
Speaker: Yuxiang Wei
Question time (all power pitch speakers)
Keynote Lecture 3 (16:20 – 16:40)
16:20 – 16:40
Chun-Hung J. Yeh
Chang Gung University, Taoyuan, Taiwan
Analysis of longitudinal diffusion MRI data: research on autism and bipolar disorder
QuantConn Challenge (16:40 - 17:20)
16:40 – 17:10
Challenge overview: Quantitative Connectivity through harmonized preprocessing of diffusion MRI (QuantConn)
Challenge organiser: Nancy Newlin
17:10 – 17:20
Submissions and winners
Challenge organiser: Nancy Newlin
Concluding Remarks (17:20 – 17:25)
| 13:30 – 13:35 | Welcome and Introduction |
| 13:35 – 13:55 |
|
Demian WassermannInria, CEA, Université Paris-Saclay, Palaiseau, FranceHow do we link diffusion MRI with brain structure and cognition? Breaching the gap between classical neuroanatomy and machine learning. |
| 13:55 – 14:05 | Subnet communicability: Diffusive communication across the brain through a backbone subnetwork
Speaker: Yusuf Osmanlioglu |
| 14:05 – 14:15 | ReTrace: Topological evaluation of white matter tractography algorithms using Reeb graphs
Speaker: S. Shailja |
| 14:15 – 14:25 | Advanced diffusion MRI modeling sheds light on FLAIR white matter hyperintensities in an aging cohort
Speaker: Kelly Chang |
| 14:25 – 14:35 | Anisotropic fanning aware low-rank tensor approximation based tractography
Speaker: Johanes Grün |
| 14:35 – 14:45 | Diffusion phantom study of fiber crossings at varied angles reconstructed with ODF-fingerprinting
Speaker: Patryk Filipiak |
| 14:45 – 14:55 | A unified single-stage learning model for estimating fiber orientation distribution functions on heterogeneous multi-shell diffusion-weighted MRI
Speaker: Yuankai Huo |
| 14:55 – 15:15 |
|
Jennifer A. McNabStanford University, California, USAMultimodal integration of diffusion MRI |
| Voxlines: streamline transparency through voxelization and view-dependent line orders
Speaker: Besm Osman |
| FASSt: Filtering via symmetric Autoencoder for Spherical Superficial white matter Tractography
Speaker: Yuan Li |
| BundleCleaner: unsupervised denoising and subsampling of diffusion MRI-derived tractography data
Speaker: Yixue Feng |
| Improving multi-tensor fitting with global information from track orientation density imaging
Speaker: Erick Hernandez Gutierrez |
| Automatic fast and reliable recognition of a small brain white matter bundle
Speaker: John Kruper |
| BundleSeg: A versatile, reliable and reproducible approach to white matter bundle segmentation
Speaker: Etienne St-Onge |
| Automated mapping of residual distortion severity in diffusion MRI
Speaker: Yonggang Shi |
| Neural spherical harmonics for structurally coherent continuous representation of diffusion MRI signal
Speaker: Tom Hendriks |
| Fast acquisition for diffusion tensor tractography
Speaker: Omri Leshem |
| Self supervised denoising diffusion probabilistic models for abdominal DW-MRI
Speaker: Serge Vasylechko |
| A deep network for explainable prediction of non-imaging phenotypes using anatomical multi-view data
Speaker: Yuxiang Wei |
| Question time (all power pitch speakers) |
| 16:20 – 16:40 |
|
Chun-Hung J. YehChang Gung University, Taoyuan, TaiwanAnalysis of longitudinal diffusion MRI data: research on autism and bipolar disorder |
| 16:40 – 17:10 | Challenge overview: Quantitative Connectivity through harmonized preprocessing of diffusion MRI (QuantConn)
Challenge organiser: Nancy Newlin |
| 17:10 – 17:20 | Submissions and winners
Challenge organiser: Nancy Newlin |
Keynote Speaker Bios
Jennifer A. McNab
Stanford University, California, USA
Jennifer McNab is an MRI physicist by training and an Associate Professor at Stanford University, where her research program is focused on the development of MRI acquisition, image reconstruction and analysis strategies that yield new and/or improved images of the human brain. Over the past decade, she has developed numerous MRI methods, with her primary contributions being in the field of diffusion MRI. Applications of Jennifer’s work include neurosurgical targeting, neuronavigation, lesion detection, assessment of neurodevelopment, neuroplasticity and aging, as well as basic neuroscience investigation. She also has extensive experience in state-of-the-art MRI technology, including high-field (7T) and strong gradient (300 mT/m) MR systems, as well as highly parallelised phased-array RF coils (64 channels).
Google Scholar link here.
Demian Wassermann
Inria, CEA, Université Paris-Saclay, Palaiseau, France
Demian Wassermann is a Research Professor in the Mind team - part of the Inria National Institute for Research in Digital Science and Technology, Saclay, France - that develops statistics and machine learning techniques for brain imaging. Demian started working in diffusion MRI in 2006; currently, he works on probabilistic knowledge representation in neuroimaging as well as in diffusion MRI, contributing both methodological advancements as well as software. In the past 5 years, Demian has been organizer and program chair of several of the top conferences in the neuroimaging community (ISMRM, MICCAI, IPMI). Since 2018, Demian Wassermann leads an ERC-funded project called NeuroLang with the objective of harnessing probabilistic knowledge representation approaches to facilitate neuroimaging analyses. Demian’s research has been featured in top venues in machine learning and machine learning in medical imaging (ICLR, NeurIPS, AAAI, IPMI, MICCAI) as well as in top venues in life and general sciences (eLife, Nature Communications).
Google Scholar link here.
Chun-Hung J. Yeh
Chang Gung University, Taoyuan, Taiwan
Chun-Hung Yeh is an Assistant Professor in the Department of Medical Imaging and Radiological Sciences at Chang Gung University (CGU), Taiwan. He joined CGU in 2020 as an Assistant Research Fellow at the Institute for Radiological Research, following his appointment as a Senior Research Officer at the Imaging Division of the Florey Institute of Neuroscience and Mental Health in Melbourne, Australia (2014-2019). He received dual PhD degrees in the frame of the Joseph Fourier Scholarship awarded by the French Institute in Taipei: one in Physics at Paris-Sud XI University (now Paris-Saclay University) in France and the other in Biomedical Imaging and Radiological Sciences at National Yang Ming University in Taiwan. He has a long-standing interest in the application of novel diffusion imaging method developments to significant clinical neuroscience challenges. He is currently leading and supporting multiple local and trans-national projects, mainly focusing on mental disorders (including autism spectrum disorder, bipolar disorder and Alzheimer's disease) with multi-modality approach, including curing psychiatric symptoms with the development of transcranial brain stimulation protocol.
Google Scholar link here.
|
|
Jennifer A. McNabStanford University, California, USAJennifer McNab is an MRI physicist by training and an Associate Professor at Stanford University, where her research program is focused on the development of MRI acquisition, image reconstruction and analysis strategies that yield new and/or improved images of the human brain. Over the past decade, she has developed numerous MRI methods, with her primary contributions being in the field of diffusion MRI. Applications of Jennifer’s work include neurosurgical targeting, neuronavigation, lesion detection, assessment of neurodevelopment, neuroplasticity and aging, as well as basic neuroscience investigation. She also has extensive experience in state-of-the-art MRI technology, including high-field (7T) and strong gradient (300 mT/m) MR systems, as well as highly parallelised phased-array RF coils (64 channels). Google Scholar link here. |
|
|
Demian WassermannInria, CEA, Université Paris-Saclay, Palaiseau, FranceDemian Wassermann is a Research Professor in the Mind team - part of the Inria National Institute for Research in Digital Science and Technology, Saclay, France - that develops statistics and machine learning techniques for brain imaging. Demian started working in diffusion MRI in 2006; currently, he works on probabilistic knowledge representation in neuroimaging as well as in diffusion MRI, contributing both methodological advancements as well as software. In the past 5 years, Demian has been organizer and program chair of several of the top conferences in the neuroimaging community (ISMRM, MICCAI, IPMI). Since 2018, Demian Wassermann leads an ERC-funded project called NeuroLang with the objective of harnessing probabilistic knowledge representation approaches to facilitate neuroimaging analyses. Demian’s research has been featured in top venues in machine learning and machine learning in medical imaging (ICLR, NeurIPS, AAAI, IPMI, MICCAI) as well as in top venues in life and general sciences (eLife, Nature Communications). Google Scholar link here. |
|
|
Chun-Hung J. YehChang Gung University, Taoyuan, TaiwanChun-Hung Yeh is an Assistant Professor in the Department of Medical Imaging and Radiological Sciences at Chang Gung University (CGU), Taiwan. He joined CGU in 2020 as an Assistant Research Fellow at the Institute for Radiological Research, following his appointment as a Senior Research Officer at the Imaging Division of the Florey Institute of Neuroscience and Mental Health in Melbourne, Australia (2014-2019). He received dual PhD degrees in the frame of the Joseph Fourier Scholarship awarded by the French Institute in Taipei: one in Physics at Paris-Sud XI University (now Paris-Saclay University) in France and the other in Biomedical Imaging and Radiological Sciences at National Yang Ming University in Taiwan. He has a long-standing interest in the application of novel diffusion imaging method developments to significant clinical neuroscience challenges. He is currently leading and supporting multiple local and trans-national projects, mainly focusing on mental disorders (including autism spectrum disorder, bipolar disorder and Alzheimer's disease) with multi-modality approach, including curing psychiatric symptoms with the development of transcranial brain stimulation protocol. Google Scholar link here. |