CV

Education

B.Sc. (Hons) Statistics, University of Cape Town, 2018 (First class honors 75%)
M.Sc. Artificial Intelligence, University of Southampton, 2020 (Distinction 89%)
Ph.D. Artificial Intelligence for Cancer Biology, Institute of Cancer Research and Imperial College London, 2024 (expected)

Work experience

Oct 2020 – Present: PhD Researcher
- Joined between Institute of Cancer Research and Imperial College London
- Thesis title: Tumour evolution in super-resolution: Developing new Artificial Intelligence-based methods to analyse 4D imaging data of tumours.
- Duties included:
  - Developed graph-based deep learning-based 3D shape analysis tools to profile melanoma cancer cells.
  - Developed method to learn feature representations from 3D+t mcroscopy images of melanoma spheroids.
  - Involved in recruiting and interviewing Senior Software Engineers.
  - Involved in starting a spin-off company based on the results from my project and attended Accerlerator for this start-up.
  - Published peer-reviewed articles.
- Tools: Python, PyTorch, GitHub
- Supervisors:
  - Prof. Chris Bakal (ICR)
  - Prof. Christopher Dunsby (Imperial)
Nov 2019 – Oct 2020: Research Assistant
- University of Southampton, Centre for Machnie Intelligence, Southampton, UK
- Duties included:
  - Research in prediction of early recurrence after esophageal cancer surgery using gene sequencing data, as well as high resolution digital pathology scans.
  - Worked closely with Cancer Research UK.
  - Developed novel AI methodologies for integrating imaging data with patient demographic information and gene data.
  - Competed in kaggle competitions.
- Tools: Python, PyTorch, Azure, GitHub
Apr 2019 – Sept 2019: Data Scientist
- Advanced Data Science, Cape Town, RSA
- Duties included:
  - Performed cluster analysis to identify customer groups of a large telecommunication company in order to identify customers which needed targeting.
  - Cleaned and assimilated sales data as inputs to sales regression models.
  - Built statistical learning models including GAMs, MARS, splines and logistic regression models.
  - Data visualisation.
  - Used MCA and PCA for dimension reduction.
  - Explored marginal effects of regression models.
- Tools: Python, R, GitHub
Jan 2019 - Apr 2019: Data Scientist
- Barrows Global, Durban, RSA
- Duties included:
  - Customer analytics for large supermarket chain.
  - Business intelligence.
  - Research and design of statistical methods used to analyse whether a marketing campaign was successful or not.
- Tools: Python, R, GitHub

Skills

Deep learning
Computer vision
Mathematics
Statistical learning
Python
Medical Image Analysis

Publications

Predicting response to neoadjuvant therapy using image capture from diagnostic biopsies of oesophageal adenocarcinoma

Saqib Rahman, Joe Early, Matt De Vries, Megan Lloyd, Ben Grace, Gopal Ramchurn, and Timothy Underwood. Predicting response to neoadjuvant therapy using image capture from diagnostic biopsies of oesophageal adenocarcinoma. European Journal of Surgical Oncology, 47(1):e4, 2021

What do machines see? Utilizing artificial intelligence to explore cell biology

Matt De Vries, Chris Bakal; What do machines see? Utilizing artificial intelligence to explore cell biology. Biochem (Lond) 1 October 2021; 43 (5): 48–52. doi: https://doi.org/10.1042/bio_2021_168

Predicting survival and response to therapy using diagnostic biopsies: A machine learning approach to facilitate treatment decisions for oesophageal adenocarcinoma

Saqib Rahman, Joseph Early, Ben Sharpe, Megan Lloyd, Matt De Vries, Ben Grace, Sarvapali Ramchurn, and Timothy Underwood. P-OGC57 Predicting survival and response to therapy using diagnostic biopsies: A machine learning approach to facilitate treatment decisions for oesophageal adenocarcinoma. British Journal of Surgery, 108

3D single-cell shape analysis of cancer cells using geometric deep learning

Matt De Vries, Lucas Dent, Nathan Curry, Leo Rowe-Brown, Adam Tyson, Christopher Dunsby, and Chris Bakal. 3D single-cell shape analysis of cancer cells using geometric deep learning. 17 June 2022; bioRxiv 2022.06.17.496550; doi: https://doi.org/10.1101/2022.06.17.496550