Friday 5 January 2024

Student Research: From Research Breakthrough to £1 Million Collaboration

Keble celebrates the achievements of Aleksander Zagajewski (DPhil Biomedical Imaging, 2018). As a doctoral student with the University’s Department of Physics, Aleksander has worked on a research breakthrough that has evolved into a £1 million collaboration between three university departments.

The study, conducted under Oxford Martin Programme on Antimicrobial Resistance Testing, focuses on developing a novel and rapid antimicrobial susceptibility test. Researchers displayed a method capable of detecting antibiotic resistance in as little as 30 minutes—a significant leap forward from current gold-standard approaches.

The heart of this research lies in the intersection of fluorescence microscopy and artificial intelligence (AI). Aleksander and his team utilized deep-learning models to analyse bacterial cell images, identifying structural changes induced by antibiotic treatment. This innovative approach demonstrated a remarkable 80% accuracy on a per-cell basis across multiple antibiotics, showing its potential to revolutionize the field of infectious disease treatment.

Co-author Achillefs Kapanidis, Professor of Biological Physics and Director of the Oxford Martin Programme on Antimicrobial Resistance Testing, explained the significance of this, stating, ‘Our AI-based approach detects such changes reliably and rapidly. Equally, if a cell is resistant, the changes we selected are absent, and this forms the basis for detecting antibiotic resistance.’

The potential applications of this research are vast. Current testing methods, relying on growing bacterial colonies in the presence of antibiotics, are slow and often take several days. In critical cases such as sepsis, where urgent treatment is vital, this delay can be life-threatening. Aleksander envisions their rapid method facilitating targeted antibiotic treatments, decreasing treatment times, minimizing side effects, and ultimately contributing to the slowing down of the rise of AMR.

Speaking about the urgency of their work, Aleksander Zagajewski said, ‘Time is beginning to run out for our antibiotic arsenal; we are hoping our novel diagnostics will pave the way for a new generation of precision treatments for the most sick patients.’

The study, titled ‘Deep learning and single-cell phenotyping for rapid antimicrobial susceptibility detection in Escherichia coli,’ has been officially published in Communications Biology.

You can read more about this research here: https://www.ox.ac.uk/news/2023-11-21-oxford-led-study-shows-how-ai-can-detect-antibiotic-resistance-little-30-minutes