Professor Michael Roberts

Mike Roberts is Research Professor at DAMTP and also at the Department of Medicine. He is a member of the Cambridge Image Analysis group (CIA), leads the BloodCounts! consortium (https://www.bloodcounts.org/) and led the algorithm development team for the global COVID-19 AIX-COVNET collaboration (https://covid19ai.maths.cam.ac.uk/).

Career

Positions:

October 2023 onwards: Research Professor at DAMTP and Department of Medicine, University of Cambridge, UK.

April 2021 to September 2023: Senior Research Associate at DAMTP, University of Cambridge, UK.

March 2020 to March 2021: Research Associate at DAMTP, University of Cambridge, UK.

April 2019 to July 2022: Postdoctoral Fellow at AstraZeneca, Cambridge, UK

Education:

July 2019: Doctor of Philosophy, University of Liverpool, UK

June 2015: Master’s degree in Mathematics with Honors, Durham University, UK

Research

Mike's research interests focus on variational methods for image processing (in particular image segmentation and registration), machine learning for image and data analysis, image processing and data analysis. More recently, he has been focussing on best practice and scientific integrity in machine learning and data science, in particular for understanding the crisis of reproducibility affecting these fields. He has active interdisciplinary collaborations with other applied mathematicians, computer scientists and clinicians focussing on medical imaging problems. He has vast experience in studying high-dimensional data and medical imaging problems for lung diseases including (but not limited to) lung cancer, idiopathic lung fibrosis, mesothelioma and drug induced interstitial lung disease.

Publications

On the caveats of AI autophagy

X Xing, F Shi, J Huang, Y Wu, Y Nan, S Zhang, Y Fang, M Roberts, C-B Schönlieb, J Del Ser, G Yang

– Nature Machine Intelligence

(2025)

172

(doi: 10.1038/s42256-025-00984-1)

A Pipeline for Automated Quality Control of Chest Radiographs

IA Selby, E González Solares, A Breger, M Roberts, L Escudero Sánchez, J Babar, JHF Rudd, NA Walton, E Sala, C-B Schönlieb, JR Weir-McCall, AIX-COVNET Collaboration

– Radiology Artificial Intelligence

(2025)

e240003

(doi: 10.1148/ryai.240003)

Review and Recommendations for using Artificial Intelligence in Intracoronary Optical Coherence Tomography Analysis

X Chen, Y Huang, B Jessney, J Sangha, S Gu, C-B Schönlieb, M Bennett, M Roberts

(2025)

(link to publication)

Improving the generalisation of radiographic AI using automated data curation to mitigate shortcut learning

I Selby, EG Solares, A Breger, M Roberts, LE Sánchez, J Rudd, N Walton, J Babar, C-B Schönlieb, E Sala, J Weir-McCall

– The Royal College of Radiologists Open

(2025)

100232

(doi: 10.1016/j.rcro.2024.100232)

A Study on the Adequacy of Common IQA Measures for Medical Images

A Breger, C Karner, I Selby, J Gröhl, S Dittmer, E Lilley, J Babar, J Beckford, TR Else, TJ Sadler, S Shahipasand, A Thavakumar, M Roberts, C-B Schönlieb

(2025)

1372,

451

(doi: 10.1007/978-981-96-3863-5_41)

SpeedyAnnotate: An Intuitive and Open-Source Tool for Efficient Image Annotation and Quality Comparison

I Selby, A Breger, M Roberts, LE Sánchez, J Babar, J Rudd, E Sala, C-B Schönlieb, J Weir-McCall

– The Royal College of Radiologists Open

(2025)

100233

(doi: 10.1016/j.rcro.2024.100233)

Parameter Choices in Haarpsi for IQA with Medical Images

C Karner, J Gröhl, I Selby, J Babar, J Beckford, TR Else, TJ Sadler, S Shahipasand, A Thavakumar, M Roberts, JHF Rudd, C-B Schönlieb, JR Weir-McCall, A Breger

– 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)

(2024)

00,

(doi: 10.1109/ISBI60581.2025.10981227)

Deep Generative Classification of Blood Cell Morphology.

S Deltadahl, J Gilbey, C Van Laer, N Boeckx, M Leers, T Freeman, L Aiken, T Farren, M Smith, M Zeina, B consortium, JH Rudd, C Piazzese, J Taylor, N Gleadall, C-B Schönlieb, S Sivapalaratnam, M Roberts, P Nachev

(2024)

(doi: 10.48550/arxiv.2408.08982)

Using machine learning to predict carotid artery symptoms from CT angiography: A radiomics and deep learning approach.

EPV Le, MYZ Wong, L Rundo, JM Tarkin, NR Evans, JR Weir-McCall, MM Chowdhury, PA Coughlin, H Pavey, F Zaccagna, C Wall, R Sriranjan, A Corovic, Y Huang, EA Warburton, E Sala, M Roberts, C-B Schönlieb, JHF Rudd

– Eur J Radiol Open

(2024)

13,

100594

(doi: 10.1016/j.ejro.2024.100594)

Correcting common OCT artifacts enhances plaque classification and identification of higher-risk plaque features.

B Jessney, X Chen, S Gu, A Brown, D Obaid, C Costopoulos, M Goddard, N Shah, H Garcia-Garcia, Y Onuma, P Serruys, SP Hoole, M Mahmoudi, M Roberts, M Bennett

– Cardiovascular revascularization medicine : including molecular interventions

(2024)

73,

(doi: 10.1016/j.carrev.2024.06.023)

Cambridge Image Analysis

Publications

Research Group

Email

Room

Study at Cambridge

About the University

Research at Cambridge