Closing the Performance Gap Between AI and Radiologists in Chest X-Ray Reporting
MAIRA-X: longitudinal reporting, including lines and tubes, at near parity with radiologists on critical errors and sentence acceptability.
paper ↗Foundation models · Clinical AI · Somatic genomics
I build multimodal AI that reasons about biology — from radiology and radiotherapy models used in hospitals to AI for drug discovery.
Director of AI, Quotient Therapeutics · Cambridge, UK
I take AI out of the lab and into the places where it has to work — radiotherapy, radiology and, now, drug discovery.
I studied computer science at the Universidad de Oviedo and wrote my master’s thesis at the University of Cambridge. After engineering roles at Telefónica I+D, Redgate, Citrix and Featurespace, I joined Microsoft in 2012 and built Skype’s real-time telemetry pipeline, later scaled across Xbox, Bing and Office.
For 10 years at Microsoft Research I worked on AI for medicine. I led Project InnerEye — radiotherapy AI that cut contouring time by 36–67% in NHS use, open-sourced and adopted by 30+ organisations — and AI engineering for cancer treatment through FDA 510(k) clearance. As Senior Director in Health Futures I led a multidisciplinary team across continents building multimodal foundation models, with partners in three areas: radiology, deploying draft chest X-ray reports with Mayo Clinic; cancer screening with Cyted; and medical imaging in clinical trials with Novartis.
In 2026, as an advisor, I worked on autonomous chest X-ray reporting and built the knowledge-base layer of the open-source Firefly Agentic framework. Today I am Director of AI at Quotient Therapeutics, a Flagship Pioneering company using somatic genomics to discover medicines.
My team built image encoders and report-generation models for chest X-rays — Project MAIRA — and collaborated with Mayo Clinic to deploy draft reporting.
Draft report
MAIRA-X: longitudinal reporting, including lines and tubes, at near parity with radiologists on critical errors and sentence acceptability.
paper ↗Reports that localise every finding on the image, with RadFact to check each sentence.
paper ↗RAD-DINO: trained on images alone, it matches or beats language-supervised encoders and scales with data diversity.
paper ↗BioViL: better modelling of report text substantially improves vision-language learning. My most-cited paper.
paper ↗BioViL-T: learns how disease changes between studies from prior images and reports.
paper ↗GPT-4 matches or beats radiology-specific models on text-based tasks — and prompting matters.
paper ↗Clinicians spend an hour or more outlining organs on a CT scan before radiotherapy. Project InnerEye automates the routine part — and we took it into NHS use.
Organs at risk
A clinician then checks and edits every structure before the treatment plan.
Up to 13× faster segmentation with machine-learning assistance, within expert variability.
paper ↗InnerEye in hospital use: contouring 36% faster for prostate and 67% faster for head and neck.
paper ↗Open-sourced so hospitals and researchers can build their own imaging models; adopted by 30+ organisations.
project ↗The same ideas carry over to pathology, screening and biomarker discovery.
Screening
With Cyted: filtering clear negatives in oesophageal screening, cutting pathologist reviews by about half.
paper ↗An agent that turns scientific questions into executable histopathology analyses.
paper ↗Foundation models and AI agents across imaging, text and clinical data.
Agents that plan analyses, query what an organisation knows, and hand a case back to a human when unsure.
Analysis agent
A safety layer that reports a study as normal only when confident, and otherwise defers to a radiologist.
Hybrid-search ingestion, schema-aware parsing, an agentic SQL retriever and an MCP server on Azure — 20+ merged PRs.
pull requests ↗Frontier models can ace medical benchmarks without robust multimodal reasoning.
paper ↗Post-training frontier LLMs with reinforcement learning to improve instruction following, helpfulness and robustness.
Before medicine I built large systems: a model only matters if it runs reliably where people use it.
Millions of events per second, scaled across Xbox, Bing and Office as Microsoft’s first Azure-based telemetry platform.
A deep-learning dog-breed recogniser that reached 3 million users in three weeks.
Prioritises which labels experts should re-check, correcting up to 4× more effectively than random selection.
paper ↗Secure multi-party inference for medical imaging models, compiled automatically from TensorFlow.
paper ↗On leading teams, plus Microsoft Research blog posts written with colleagues, and interviews.
For roles, collaborations or speaking, email me or reach out on LinkedIn. I also mentor on MentorCruise.