AI powered tools tackling oesophageal cancer
Dr Felix Zhou is working closely with collaborators in the Oxford Big Data Institute and John Radcliffe Hospital to develop AI-powered augmented reality tools to assist clinicians in accurately detecting and mapping the location of oesophageal tumours during an endoscopy.
An endoscopy is a procedure where a thin, flexible tube with a light and camera at one end is passed into the oesophagus, allowing doctors to see the lining of the food pipe and look for signs of cancer.
Dr Zhou and his colleagues established the Endoscopy Artefact Detection Challenge, an initiative aiming to improve the computerised analysis of endoscopy images to help us to more effectively detect and treat cancer.
They are also developing personalised treatments to overcome treatment resistance, a common problem with current standard treatments such as chemotherapy. This involves running drug screens using miniature organs grown from patient biopsies, called organoids. The team use time-lapse imaging to monitor growth of these organoids with different drugs applied.
Dr Zhou develops computational analyses to characterize a tumour’s sensitivity to existing and new drugs. This builds upon a comprehensive framework that Felix recently developed that analyses the way cells move to enable researchers to detect changes in movements that might indicate cancer. The framework, called Motion Sensing Superpixels (MOSES), has already been shown to capture subtle interaction changes between oesophageal cells in the laboratory.
It’s hoped that harnessing the power of AI and computational modelling will help clinicians to better diagnose and treat this hard-to-treat cancer in the future.