skip to content

Mike Roberts is Principal Research Associate (Reader / Professor Grade 11) 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 also leads the algorithm development team for the global COVID-19 AIX-COVNET collaboration (https://covid19ai.maths.cam.ac.uk/).

Career

Positions:

October 2023 onwards: Principal Research Associate 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

A study of why we need to reassess full reference image quality assessment with medical images
A Breger, A Biguri, MS Landman, I Selby, N Amberg, E Brunner, J Gröhl, S Hatamikia, C Karner, L Ning, S Dittmer, M Roberts, AIX-COVNET Collaboration, C-B Schönlieb
(2024)
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
(2024)
REFORMS: Consensus-based Recommendations for Machine-learning- based Science
S Kapoor, EM Cantrell, K Peng, TH Pham, CA Bail, OE Gundersen, JM Hofman, J Hullman, MA Lones, MM Malik, P Nanayakkara, RA Poldrack, ID Raji, M Roberts, MJ Salganik, M Serra-Garcia, BM Stewart, G Vandewiele, A Narayanan
– Sci Adv
(2024)
10,
eadk3452
Correction to: The curious case of the test set AUROC (Nature Machine Intelligence, (2024), 6, 4, (373-376), 10.1038/s42256-024-00817-7)
M Roberts, A Hazan, S Dittmer, JHF Rudd, CB Schönlieb
– Nature Machine Intelligence
(2024)
6,
494
Non-contact, portable and stand-off infrared thermal imager for security scanning applications
WL Khor, YK Chen, M Roberts, F Ciampa
– AIP Advances
(2024)
14,
045314
The curious case of the test set AUROC
M Roberts, A Hazan, S Dittmer, JHF Rudd, CB Schönlieb
– Nature Machine Intelligence
(2024)
6,
373
The curious case of the test set AUROC
M Roberts, A Hazan, S Dittmer, JHF Rudd, C-B Schönlieb
(2023)
The impact of imputation quality on machine learning classifiers for datasets with missing values.
T Shadbahr, M Roberts, J Stanczuk, J Gilbey, P Teare, S Dittmer, M Thorpe, RV Torné, E Sala, P Lió, M Patel, J Preller, AIX-COVNET Collaboration, JHF Rudd, T Mirtti, AS Rannikko, JAD Aston, J Tang, C-B Schönlieb
– Communications Medicine
(2023)
3,
139
Common methodological pitfalls in ICI pneumonitis risk prediction studies
YK Chen, S Welsh, AM Pillay, B Tannenwald, K Bliznashki, E Hutchison, JAD Aston, C-B Schönlieb, JHF Rudd, J Jones, M Roberts
– Frontiers in immunology
(2023)
14,
1228812
Shortcut Learning: Reduced But Not Resolved.
IA Selby, M Roberts, A Breger, JHF Rudd, JR Weir-McCall
– Radiology
(2023)
308,
e230379
  • 1 of 5
  • >

Research Group

Cambridge Image Analysis

Room

F1.13

Telephone

01223 760390