Welcome to the MANIFOLD Lab

About the lab

Welcome to the website of the Machine-learning Artificial Intelligence Neuro Imaging Focusing on Longevity & Dementia (MANIFOLD) Laboratory. We are based at University College London, part of the Centre for Medical Image Computing (CMIC) and the Dementia Research Centre (DRC) at the Queen Square Institute of Neurology.

Mission Statement

Our goal is to further our understanding of how the brain ages and how this affects risk of cognitive decline, neurodegenerative diseases and dementia. We do this using advanced statistics, machine learning and AI methods to analyse neuroimaging data, alongside genetic, cognitive, clinical, biological and behavioural information – taking a big-data science approach to help translate computational methods into the clinic for people with age-associated cognitive decline, dementia and related conditions.

Lab beliefs

UCL CMIC DRC logos

Meet the Team

Researchers

Francesca Biondo

Senior Research Fellow

Neuroscience, Neuroimaging, Ageing & Dementia, Machine Learning & Artificial Intelligence, Neuropsychology, Developmental & Cognitive psychology

James H Cole

Professor of Neuroimage Computing

Neuroscience, Neuroimaging, Ageing, Dementia, Neurodegenerative diseases, Artificial Intelligence, Machine Learning, Information Processing

Maitrei Kohli

Research Fellow

Neuroimaging, Neurodegenrative diseases, Machine Learning & Artificial Intelligence, Computational Modelling, Behavioual Genetics

Mariam Zabihi

Research Fellow

Normative Modeling, Machine Learning, Neuroimaging, Ageing, Neurodegenerative diseases

Serena Verdi

Research Fellow

Neuroimaging, Ageing, Dementia, Neuroscience, Public engagement of science, Translational research

PhD Students

Ayodeji Ijishakin

PhD Student

Neuroimaging, Deep learning, Motor Neurone Disease, Computational neuroscience

Douglas Wyllie

PhD Student

Multi-modal data fusion, Neuroimaging, Deep learning, Dementia

Florence Townend

PhD Student

Multi-modal data fusion, Neuroimaging, Motor neurone disease

Jen Cox

PhD student

Neuroimaging, Autoimmune diseases, Systemic inflammation, Imaging biomarkers, Translational imaging

Jiongqi Qu

PhD student

Neuroimaging, Dementia

Rohan Bhome

PhD Student

Neuroimaging, Neuroscience, Dementia, Neurodegeneration, Dementia with Lewy Bodies, Neuropsychiatry

Sophie Martin

PhD Student

Deep Learning, Interpretability, Neuroimaging, Dementia, Computational Modelling, Physics

Alumni & Affiliates

Melis Anatürk

Honorary Research Fellow

Multimodal MRI, Ageing, Dementia, Machine Learning, Epidemiology, Public Engagement, Open Science

Lab expertise

Statistics

Machine Learning

Artificial Intelligence

Dementia

Ageing

Imaging

Projects

BARCODE

Predicting risk of dementia in adults with subjective or mild cognitive impairment using the brain-age paradigm.

ENIGMA Brain Age

James Cole chairs the ENIGMA Brain Age working group.

Interpretable Dementia Prediction

Developing a generalisable and interpretable framework for dementia prediction.

Motor Neurone Disease

Predicting disease progression in motor neurone disease

Multimodality MRI brain age prediction

Using the UK Biobank to predict brain age from multiple modalities of MRI data, including structural, diffusion and functional scans.

Neurodevelopment

Predicting risk of poor educational outcomes from MRI measurements of the brain during infancy and early childhood

Normative Modelling

Mapping individual differences in the neuroanatomy of dementia

Recent Publications

Brain Matters: Exploring Bias in AI for Neuroimaging Research

Developing fair and unbiased models is important for good scientific practice and clinical utility. This paper delves into the specific …

Sophie Martin, Francesca Biondo, James H Cole

Revealing Individual Neuroanatomical Heterogeneity in Alzheimer Disease Using Neuroanatomical Normative Modeling

Here we employ a novel neuroanatomical normative modelling approach to index individual patterns of brain structure in patients with Alzheimer’s disease or mild cognitive impairment. By comparing patients to a large independent dataset (n>33,000), our analysis provides evidence that i) patterns of cortical thickness differ markedly between individual patients with Alzheimer’s disease, ii) these individual cortical ‘outlier’ patterns are associated with cognitive performance and CSF measures, and iii) individualised cortical atrophy measures can predict conversion from the MCI stage to diagnosed Alzheimer’s disease.

Serena Verdi, James H Cole

Interpretable deep learning for dementia: a systematic review

Introduction. Machine learning research into automated dementia diagnosis is becoming increasingly popular but so far has had limited …

Sophie Martin, James H Cole

PDF Project DOI

Brain-age is associated with progression to dementia in memory clinic patients

Background: Biomarkers for the early detection of dementia risk hold promise for better disease monitoring and targeted interventions. …

Francesca Biondo, James H Cole

Thalamic white matter macrostructure and subnuclei volumes in Parkinson’s disease depression

Thalamic changes in Parkinson’s disease depression

Rohan Bhome, James H Cole

See all publications