Lecturer: Joseph Jacob (UCL Respiratory Medicine and UCL CMIC)
In this talk, I will be describing the clinical reasons why image analysis of lung fibrosis is necessary. I will talk through methods that have been used to date. I will highlight challenges in implementing computer models and how we might inform radiologist visual interpretation of imaging features using computer models.
Lecturer: James Cole (UCL CMIC and Dementia Research Centre)
The brain changes as we age, and these changes are associated with cognitive decline and dementia risk. This motivates research using neuroimaging to measure the brain ageing process. I will present my work on the ‘brain-age’ paradigm, derived using machine learning analysis of MRI data. I will present results from brain-age studies of the general population and Down’s, HIV, traumatic brain injury, multiple sclerosis, and dementia, alongside my UK Biobank analysis on multiple MRI modality brain-age. Finally, I will talk about new developments, including voxelwise brain-age and clinical brain-age, as well as the ENIGMA Brain Age working group.
Lecturer: Rhodri Davies (Barts Heart Centre and UCL)
This talk will cover the three following topics:
– overview of cardiac imaging modalities and their clinical uses;
– the challenges associated with cardiac image interpretation;
– the challenges that can be tackled using machine learning techniques.
Lecturer: Andre Altmann (UCL CMIC)
In this talk I will speak about imaging genetics and its application to brain disorders. In imaging genetics measures derived from (neuro-)imaging are used as endpoints in statistical analyses of genetic data. This is in contrast to conducting such studies with dichotomous case-control labels. Replacing crisp diagnostic labels with imaging marker that are thought to better reflect the disease process are expected to lend increased statistical power to such analyses and also allow us to investigate different aspects of the underlying disease process such as disease progression speed or the emergence of distinct sub-types.
Lecturer: Jamie McClelland (UCL CMIC)
This talk will cover answers to the following questions:
– What is medical image registration?
– What is it used for / what can it do?
– How does it work?
– How do we know it’s worked?
Lecturer: Laura Panagiotaki (UCL CMIC)
This talk will focus on why and how we can image microstructure non-invasively with MRI. In particular we will focus on diffusion MRI and examine microstructural imaging techniques in the brain and cancer.
Lecturer: Catherine Scott (UCL and UCLH)
This talk will cover a brief introduction to Positron Emission Tomography (PET) imaging, covering the basics and current clinical practice, as well as active areas of research.
Lecturer: Claudia Wheeler-Kingshott (UCL Queen Square Institute Of Neurology)
In this lecture I will present how Magnetic Resonance Imaging (MRI) can be used for assessing health and disease of brain tissue by measuring properties of the brain in a magnetic field.
The learning objectives of the lecture will be to:
1) understand why MRI is clinically important and what makes MRI so powerful compared to other imaging techniques;
2) understand what do we mean by quantitative MRI and biophysically meaningful feature extraction from MRI scans;
3) to assess how we can use MRI for brain mictrostructure, function and physiology properties assessment;
4) to evaluate challenges to clinical translation and generatability and finally
5) to discuss new frontiers and limits of MRI.
In particular, I will explain how we can use sensitivity to water diffusion in tissue can help us assessing tissue microstructure integrity and properties. Exploiting the sensitivity of MRI to changes in magnetic susceptibility associated to blood oxygenation status during brain function, we can detect areas of functional activations and resting state networks. As example of using MRI to assess physiological properties of brain tissue I will present sodium imaging and sodium ion concentration quantification. This is really far from clinical adoption but could have great impact if technical challenges are met.
Examples of clinical applications will be presented to make the lecture more practical, including in multiple sclerosis (Toschi et al, Neuroscience, 2019), neurodegeneration (Castellazzi et al, Frontiers in Neuroscience, 2014) and stroke (Särkämö et al. Frontiers in Human Neuroscience 2014). Discussion of emerging areas of development go from the use of high field human scanners (e.g. 7T), to going beyond what we already know and find ways to challenge our approach to study design, to multi-modal applications for example to understand brain dynamics and obviously to big data analysis using artificial intelligence approaches.
Lecturer: Dave Cash (UCL DRC)
In the past few years, the amount of medical imaging data available across the whole spectrum of health and bioscience research has skyrocketed, enabled many new applications and discoveries. Larger sample sizes help characterize the clinical heterogeneity of the population and identify small but meaningful changes, particularly in individuals who are at-risk or showing the earliest signs of disease. In addition, they also are often needed to train and test machine learning and deep learning algorithms. However, the logistics of managing and analysing imaging data grow in complexity as the size of the data increases. Cloud-based and federated solutions can alleviate some of these issues but also bring new challenges. In addition to data management issues, funders are increasingly requiring researchers to share their data. While these open science mandates are crucial for the field, researchers must balance data sharing requirements with data protection law. Appropriate anonymisation strategies are important to remove all personal information from the image metadata, and in some cases the image themselves (e.g. the reconstruction of a face from a head MRI), whist not being so stringent that the data becomes unusable or affects reproducibility of the analysis. This talk will discuss considerations and strategies for data management and analysis of large-scale imaging studies, including considerations around multi-user access, multi-site studies, and public data sharing.
Lecturer: Yipeng Hu (UCL CMIC)
This is a lecture introducing the basic building blocks of deep learning algorithms. What will be discussed are several big ideas in both theoretical background of deep neural networks and their practical training strategies, with an overview of their applications in medical image computing and computer assisted intervention.
