About
Principal Scientist, Imaging Biomarkers at Boehringer Ingelheim — a decade of imaging analysis, pipeline engineering and machine learning research, across academia, medical devices and pharmaceutical R&D.
Research focus
I work on quantitative imaging biomarkers, and my day-to-day sits in the engineering of the analysis itself: designing and building end-to-end pipelines that take imaging data from raw acquisition through processing to the measures a study actually reports. Neuroimaging remains the centre of gravity — multimodal MRI, fMRI, PET and DTI — and the same approach now extends across organ systems, including retinal imaging and abdominal MR.
These pipelines often integrate imaging with other modalities — EEG, movement and speech — to support diagnosis and therapeutic target identification in Alzheimer’s disease, Parkinson’s disease, autism and depression. The emphasis is on getting the analysis right and making it reproducible: validated against clinical endpoints, and engineered so other teams can run it consistently at scale.
Earlier in my career the work was more squarely in machine learning and deep learning — evolutionary-algorithm classifiers for resting-state fMRI in my PhD, white-box models for depression in UK Biobank data, deep learning for A/T/N staging from tau-PET, and the ML behind diagnostic devices at ClearSky. That background still shapes how I build and evaluate analyses, and I draw on it when a problem calls for it. My proficiency spans Python, MATLAB, R and Shell, alongside scalable data engineering and high-performance computing.
Professional experience
2025 — present · Principal Scientist, Imaging Biomarkers Boehringer Ingelheim, Germany
Building end-to-end pipelines for the processing and analysis of imaging data, and the quantitative biomarkers derived from them, to support disease diagnosis, therapeutic target identification and drug development. Neuroimaging is the primary focus, with the remit extending across organ systems including retinal imaging and abdominal MR.
2022 — 2025 · Postdoctoral Researcher Institute for Stroke and Dementia Research (ISD), Ludwig-Maximilians-Universität München, Germany
- Developed ADPrep, an automated neuroimaging preprocessing pipeline (Python, MATLAB, R, Shell) covering MRI, fMRI, PET and DTI, and adopted as standard preprocessing for the group’s multimodal imaging studies. It is set for integration into the GRIP platform, a Gates Ventures initiative.
- Developed, validated and deployed a deep learning model that infers full Alzheimer’s disease A/T/N classification from a single tau-PET scan, reaching high predictive accuracy for amyloid-PET (r = 0.80) and MRI grey-matter density (r = 0.76).
- Managed the institute’s high-performance computing resources and supported research labs with their data analysis, alongside serving as an IT assistant for the LMU Hospital.
2018 — 2025 · Chief Technology Officer ClearSky Medical Diagnostics Ltd., York, UK
- Contributed to the development of machine learning–based medical devices for diagnosing and monitoring neurodegenerative conditions, including PD-Monitor, LID-Monitor and MCI-Monitor.
- Optimised machine learning for movement disorder analysis, improving diagnostic precision.
- Collaborated with multidisciplinary teams of clinicians and engineers to integrate AI-driven solutions into clinical applications.
2021 — 2022 · Postdoctoral Research Associate University of York, UK
Applied white-box machine learning to resting-state fMRI to differentiate depression from healthy controls in large-scale UK Biobank data.
2021 · Machine Learning and Image Processing Engineer smartR.ai, Edinburgh, UK
Created deep learning pipelines to normalise and match colour profiles between FIBI and H&E histological images.
2020 — 2021 · Research Fellow University of Aberdeen, UK
Used neuroimaging to define a fatigue-related brain network in rheumatoid arthritis, exploring how therapies affect it and which mediators might feasibly be targeted.
2019 · Postdoctoral Researcher in Neuroimaging Trinity College Dublin, Ireland
Linked speech patterns to brain volume change in MCI and Alzheimer’s disease, exploring speech as an early marker of cognitive decline.
2016 — 2017 · Professional Engineer My Therapy Tools Ltd., UK
Provided engineering support to a Horizon 2020 telerehabilitation platform for patients with acquired brain injury.
Education
2014 — 2018 · PhD, Electronic Engineering — University of York, UK Supervised by Professor Stephen Smith. Thesis: Cartesian Genetic Programming Classification of Resting-State fMRI: Towards a Brain Imaging Biomarker for Parkinson’s Disease.
2013 · MSc, Digital Signal Processing — University of York, UK
2010 · BSc, Applied Science Electronics — University of Science and Arts of Yazd, Iran
Collaborations
I have had the pleasure and honour of working with researchers such as Dr Franzmeier, Professor Smith, Dr Waiter, Professor Basu and Professor Reilly on multiple projects. These collaborations have focused on advanced automated neuroimaging preprocessing pipelines, objective assessment of depression from resting-state fMRI, the mechanisms of rheumatoid arthritis–related fatigue in the brain, and the analysis of speech and imaging features for classifying Alzheimer’s disease and mild cognitive impairment.
By its nature this work is highly interdisciplinary, and I have been fortunate to collaborate closely with clinicians and clinical scientists as well as researchers across engineering, computer science and the basic sciences — translating between these perspectives is one of the parts of the work I enjoy most.