MIML 2022

Title: Image Quality Transfer and Applications in Diffusion MRI

Speaker: Daniel Alexander

Speaker Bio: Daniel is the Director of the Centre for Medical Image Computing (CMIC) and deputy head of the Computer Science Department at UCL. He leads the Microstructure Imaging Group and the Progression of Neurodegenerative Diseases initiative. He is theme lead for the UCLH Biomedical Research Centre Healthcare Engineering and Imaging theme. He coordinates the Horizon 2020 EuroPOND consortium. His core expertise is in computer science, computational modelling, machine learning, and imaging science.

Title: Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning

Speaker: Eleftherios Garyfallidis

Speaker Bio: Eleftherios holds the position of Assistant Professor of Intelligent Systems Engineering (ISE) of Indiana University (IU) School of Informatics, Computing and Engineering. He is also the founder and scientific lead of Diffusion Imaging in Python (DIPY), currently the largest open source project in the development of diffusion MRI methods.

Title: Distortion Correction of DW-MRI without Reverse Phase-encoding Scans or Field-maps

Speaker: Kurt G Schilling

Speaker Bio: Kurt got his PhD at Vanderbilt University in Biomedical Engineering. He then did a post-doc at Vanderbilt University in the Department of Computer Science. He is now a Research Assistant Professor of Radiology at Vanderbilt University Medical center. His research focuses on medical image analysis techniques with the aim to map tissue microstructure and connectivity in the central nervous system.

Title: Data-driven, Model-free, Deep Learning Approach for Quantitative MRI Protocol Design

Speaker: Francesco Grussu

Speaker Bio: Francesco is a biomedical engineer specialised in computational diffusion Magnetic Resonance Imaging (MRI), with almost 10 years of experience in MRI research. He obtained a PhD from University College London (UCL, UK) in Magnetic Resonance Physics (2016), with a thesis on spinal cord diffusion MRI. He worked as a post-doc at UCL from 2016 to 2020, where he investigated new ways of acquiring and processing spinal cord, brain and prostate diffusion MRI scans for application in multiple sclerosis and cancer. During his post-doc at UCL, he visited New York University (NY, USA) for two months in 2017 (Sept-Nov). From October 2020 he has been a post-doctoral researcher at the Vall d’Hebron Institute of Oncology (VHIO) in Barcelona (Spain). At VHIO he aims to advance diffusion MRI in the fight against cancer, as part of a Beatriu de Pinós postdoctoral Fellowship from the Catalan Government, awarded in 2021.

Title: Choice of Training Label Matters: Deep Learning for Quantitative MRI Parameter Estimation

Speaker: Sean Epstein

Speaker Bio: Sean is a PhD candidate at UCL’s Centre for Medical Image Computing, working with Gary Zhang, Timothy Bray, and Margaret Hall-Craggs. His current work involves fitting computational models to high-dimensional medical image data. Before this, he read Natural Sciences (Physics) at Christ’s College, Cambridge and worked in healthcare, sanitation, and private equity.

Title: Inverting Brain Grey Matter Models with Likelihood-free Inference

Speaker: Maëliss Jallais

Speaker Bio: Maëliss is research associate at the Cardiff University Brain Research Imaging Center (CUBRIC) and the School of Computer Science and Informatics at Cardiff University. She got her PhD at the Parietal team, Inria Saclay (France), under the supervision of Demian Wassermann with a research project focussing on microstructure imaging through diffusion MRI, with a particular interest in computational modelling and machine learning. During her thesis, Maëliss developed simulation-based inference methods to estimate brain grey matter microstructure with cell-specific sensitivity. These techniques allow for estimating a full posterior distribution, describing the ensemble of solutions and the confidence in the estimations.

Title: Fibre Orientation Estimation with Deep Learning

Speaker: Ting Gong

Speaker Bio: Ting is a research fellow in the Microstructure Imaging Group, within UCL Centre for Medical Imaging Computing. Before the current postdoctoral training, she started her study in the field of medical imaging in 2015 and completed PhD in Biomedical Engineering at Zhejiang University in 2020. Her research aims to develop and improve imaging biomarkers for non-invasive quantification of the microstructure of neuronal tissue with MRI and machine learning.

Title: Machine Learning Based White Matter Models with Permeability

Speaker: Ivana Drobnjak

Speaker Bio: Ivana is an Associate Professor and a Director of the Undergraduate Program at the Department of Computer Science, University College London. Her main research interests are in developing mathematical and computational methods with applications in medicine and healthcare. Her research career started at the University of Oxford where she completed her Masters (Oxford Centre for Industrial and Applied Mathematics), and DPhil (COMLAB & Centre for Functional MRI of the Brain). She has since worked on computational and AI modelling in medical imaging, microstructure imaging and digital health. Her goal is the translation of these methodologies for improving wellbeing and health.

Title: Tractography with Machine Learning

Speaker: Peter Neher

Speaker Bio: Peter is the lead of the Diffusion MRI analysis and fiber tractography group at the German Cancer Research Center (DKFZ). He works at the Division of Medical Image Computing and is a member of the Division board. He is the lead developer of the open-source research application MITK. He got his PhD in Medical Informatics from DKFZ in 2014.

Title: Detecting Microstructural Deviations in Individuals with Deep Diffusion MRI Tractometry

Speaker: Maxime Chamberland

Speaker Bio: Maxime has accumulated significant experience in the field of diffusion MRI (dMRI) tractography. Early on, Maxime contributed to a number of innovative methods in order to visualize dMRI data interactively using the Fibernavigator. After obtaining his PhD in 2017, he joined CUBRIC to extend tractography (which merely visualises pathways qualitatively) to tractometry, which also quantifies pathway properties. During this time, Maxime’s work tackled the curse of dimensionality often seen with tractometry analyses. His recent work focused on the development of deep normative models for anomaly detection in personalised-medicine. Maxime recently joined the Donders Institute for Brain, Cognition and Behavior (The Netherlands) after receiving the Radboud University Excellence Initiative Fellowship.