Pearse Keane & Siegfried Wagner - CMIC/WEISS joint seminar series

Speaker: Pearse Keane

Title: Building a Cloud-based Pipeline for Ophthalmic Imaging at Moorfields

Abstract: 

In 2016, Moorfields Eye Hospital established a research collaboration agreement with DeepMind which involved the development of a deep learning system for ophthalmic image classification. As a result of this Moorfields, began to develop the technical infrastructure to aggregate and curate its data. In 2019, Moorfields (plus other partners) received funding from Health Data Research (HDR) UK to greatly expand this data pipeline and to move it to the Cloud. With this support, we have build (by far) the world’s large ophthalmic imaging bio resource, a continuously updating pipeline with >18 million ophthalmic image. In my presentation, I will give an introduction to this structure, describing our capabilities for analytics and machine learning, and how we have leveraged these to facilitate the AlzEye study. In doing so, I hope to both share learnings and stimulate further collaborations within UCL.

Bio:

Pearse Keane is Professor of Artificial Medical Intelligence at UCL Institute of Ophthalmology, and a consultant ophthalmologist at Moorfields Eye Hospital, London. He is originally from Ireland and received his medical degree from University College Dublin (UCD), graduating in 2002.  In 2016, he initiated a formal collaboration between Moorfields Eye Hospital and Google DeepMind, with the aim of developing artificial intelligence (AI) algorithms for the earlier detection and treatment of retinal disease. In August 2018, the first results of this collaboration were published in the journal, Nature Medicine. In May 2020, he jointly led work, again published in Nature Medicine, to develop an early warning system for age-related macular degeneration (AMD), by far the commonest cause of blindness in many countries.

In October 2019, he was included on the Evening Standard Progress1000 list of most influential Londoners (https://www.standard.co.uk/news/the1000) and in June 2020, he was profiled in The Economist (https://www.economist.com/technology-quarterly/2020/06/11/the-potential-and-the-pitfalls-of-medical-ai). In 2020, he was listed on the “The Power List” by The Ophthalmologist magazine, a ranking of the Top 100 most influential people in the world of ophthalmology (https://theophthalmologist.com/power-list/2020).

Speaker: Siegfried Wagner

Title: AlzEye: Insights into systemic disease through retinal imaging

Abstract: 

Retinal signatures of systemic disease (‘oculomics’) are increasingly being revealed through a combination of high resolution ophthalmic imaging and sophisticated modelling strategies, such as deep learning. Yet the availability of large datasets, a sine qua non for deep learning, has traditionally been limited restricted to prospective epidemiological cohort studies where retinal imaging is typically unimodal, cross-sectional, of limited number, and often pertains to a cohort of relative sociodemographic homogeneity and few systemic disease cases. We therefore established AlzEye, a large curated dataset linking longitudinal multimodal retinal imaging from routinely collected National Health Service (NHS) data with systemic disease data from hospital admissions using a privacy-by-design third party linkage approach at University College London. A total of 6,261,931 retinal images of seven different modalities and across three manufacturers were acquired from 154,830 patients.

Bio:

Siegfried is a PhD student at UCL funded by the Medical Research Council and an ophthalmology trainee in London by background. He completed his medical training at the University of Oxford and subsequently a PG Diploma in Epidemiology and Biostatistics at the London School of Hygiene and Tropical Medicine. Siegfried’s research seeks to further our understanding on the intersect between the eye and systemic disease with a focus on clinical prediction model development using retinal imaging-based biomarkers for cardiovascular disease and dementia.

Chair: Andre Altmann