Christopher P. Bridge

Researcher in Machine Learning for Biomedical Image Analysis

I grew up South East England and pursued my ungraduate studies in Engineering at Pembroke College, University of Cambridge. I specialised in Information and Computer Engineering and developed particular interests in the areas of control theory, signal processing, image analysis, and machine learning. In my final year, my research project involved registering human femur surfaces extracted from CT scans as part of a pipeline to improve our understanding of hip fracture. This project was my gateway to the field of medical image analysis, where I have worked ever since.

I graduated from Cambridge in 2013, with the B.A. and M.Eng. degrees awarded with Distinction and the AT&T Prize for achieving the best overall final-year performance of students in the Electrical and Information Engineering areas.

I began my DPhil (PhD) at the University of Oxford’s Institute of Biomedical Engineering as a student of Balliol College, Oxford. I was supervised by the Institute’s director, Professor Alison Noble, and worked on the application of machine learning techniques to medical ultrasound. In particular I was working to develop software that can develop an understanding of video streams of 2D ultrasound data of the fetal heart. I successfully defended my DPhil thesis in July 2017.

In August 2017 I relocated to the US, and I began working as an Innovation Fellow, and then more recently as a Machine Learning Scientist and Senior Machine Learning Scientist, at Mass General Brigham AI (formerly Data Science Office and Center for Clinical Data Science) in Boston. During this time I developed a number of machine learning models for commercialisation through industry partners, and worked on problems across a range of medical disciplines and image modalities. Later, as the group’s Director of Machine Learning, I led the Translational Data Science team and focused on the development of AI models into clinical radiology workflows and overseeing standards and best practices across multiple groups developing AI models with commercial partners.

In October 2022, I moved into a full-time research role as in the Quantitative Translational Imaging in Medicine Laboratory at the Athinoula A. Martinos Center for Biomedical Imaging and Harvard Medical School, where I am now an Assistant Professor of Radiology. I have recently been focusing on machine learning for cancer imaging biomarkers in radiology and pathology, and open-source tooling for medical image computing including initiatives such as the highdicom library and the Imaging Data Commons. See my research page for more information on my recent research interests.

Outside of work, I enjoy badminton, running, skiing, and climbing.

You can find my short form CV here.