Research
My research centres on explainable AI and applied machine learning — most directly in medical-image analysis, where an interpretable result matters as much as an accurate one.
Research areas
Making machine-learning predictions interpretable, so the reasoning behind a result can be reviewed, not just trusted.
Applying interpretable machine learning to medical imagery, where an explanation matters as much as an accurate prediction.
Moving machine-learning methods from a research setting into systems that are actually built and evaluated.
Designing AI systems whose outputs can be reviewed, questioned, and held to a standard of evidence.
Systems that support a human decision-maker with evidence and explanation, rather than replacing their judgement.
Featured publication
NMR in Biomedicine · 2025
Research exploring how explainable artificial intelligence can support interpretable brain-tumour detection from MRI imagery.
Explainable artificial intelligenceMedical image analysisApplied machine learningResponsible and interpretable AIIntelligent decision-support systemsComputer engineering
32 citations
As of August 2026
Source: Owner-supplied Google Scholar screenshot
Publications
NMR in Biomedicine
Explainable artificial intelligenceMedical image analysisApplied machine learningResponsible and interpretable AIIntelligent decision-support systemsComputer engineering
Research approach
Treat explainability as a design requirement, not an add-on applied after a model is built.
Judge a method by whether its explanation holds up against domain evidence, not only against a benchmark score.
Carry research questions through to a working technical implementation rather than stopping at a proof of concept.
Anchor research direction in a concrete applied problem — in this case, supporting medical-image review — rather than a purely theoretical one.
Areas of continued interest
Academic profiles
Research collaboration
