Principal Scientist, Imaging Biomarkers at Boehringer Ingelheim
I build machine learning and deep learning systems that turn medical images into quantitative biomarkers — neuroimaging above all, and increasingly retinal imaging and abdominal MR — as evidence for diagnosis, target identification and drug development.
My work sits between the lab and the clinic: methods that hold up to peer review, delivered as systems that teams can run, trust and act on.
Deep learning across MRI, fMRI, PET and DTI to detect disease earlier, stage it more precisely and surface therapeutic targets. Neurodegeneration remains the core; the same methods now extend to retinal imaging and abdominal MR.
Taking models from prototype to validated, deployable tools: regulated medical-device programmes, clinical trial data pipelines, and models clinicians can actually act on.
Automated, reproducible preprocessing and data engineering on HPC infrastructure, so multi-site imaging studies run consistently and research teams move faster.
A few pieces of work that other people now depend on — pipelines, models and devices rather than papers alone.
An end-to-end pipeline that standardises multimodal imaging data (MRI, fMRI, PET, DTI) for large multi-site studies. Used in more than 25 peer-reviewed publications since 2023 and set for integration into the GRIP platform, a Gates Ventures initiative.
A deep learning model that infers full Alzheimer's A/T/N classification from one tau-PET acquisition, reaching r = 0.80 against amyloid-PET and r = 0.76 against MRI grey-matter density — reducing the scans a patient needs.
Seven years leading technology for ML-based medical devices for diagnosing and monitoring neurodegenerative conditions — PD-Monitor, LID-Monitor and MCI-Monitor — working alongside clinicians and engineers to move AI into clinical use.
Within the multicentre LIFT trial, multimodal MRI/fMRI and machine learning were used to define a fatigue-related brain network in rheumatoid arthritis and characterise the mediators most plausibly open to future intervention.
A decade spanning academic research, a medical-device company and now pharmaceutical R&D — across the UK, Ireland and Germany.
Developing quantitative imaging biomarkers for diagnosis and drug development — neuroimaging at the core, extending across organ systems including the retina and abdominal MR.
Built ADPrep and the tau-PET A/T/N model; managed HPC resources and supported labs across the institute.
Led development of ML-based medical devices for neurodegenerative diagnosis and monitoring.
White-box machine learning on resting-state fMRI to separate depression from healthy controls in UK Biobank data.
Deep learning pipelines to normalise and match colour profiles between FIBI and H&E histological images.
Defined a fatigue-related brain network in rheumatoid arthritis and explored how therapies affect it.
Linked speech patterns to brain volume change in MCI and Alzheimer's disease as an early marker of decline.
Cartesian Genetic Programming classification of resting-state fMRI: towards a brain imaging biomarker for Parkinson's disease.
29 peer-reviewed papers to date, largely on imaging biomarkers of neurodegeneration.
This study demonstrates that the ApoE4 risk allele lowers the threshold of plasma phosphorylated tau 217 (ptau217) required to drive fibrillar tau aggregation and spread in Alzheimer’s disease in a dose-dependent manner.
This study establishes patient-centered amyloid PET thresholds for the onset of tauopathy, demonstrating that age and sex significantly influence the amyloid-to-tauopathy transition in Alzheimer’s disease.
This systematic study compares longitudinal changes in A/T/N biomarkers (amyloid-PET, tau-PET, plasma p-tau217, and MRI) for tracking cognitive changes in Alzheimer's disease, finding plasma p-tau217 to be a robust, cost-effective alternative to tau-PET.
This study demonstrates that cortical tau accumulation promotes atrophy in connected white matter regions in Alzheimer's disease, highlighting the role of tau-induced axonal degeneration.
I work across imaging, machine learning and clinical science. If you are working on biomarkers, trial imaging or translating models into practice, I would be glad to hear from you.