Andrew Broad

Research Topic: Can Attention-Like Mechanisms Help in a Semantic Understanding of Imaging Data?

Supervisors: Dr Marc de Kamps, Dr Alex Wright, Professor Darren Treanor

About Andrew: Andrew graduated in Electronic Engineering at Leeds and later retrained as a software engineer. Most recently he worked at Leeds Teaching Hospitals NHS Trust, in the team developing the award-winning patient record system, PPM+.

Project Description: If a patient is suspected of having cancer, tissue samples may be taken for further investigation. These are mounted on slides and scanned to yield a high-resolution digital image, a valuable resource to pathologists. My PhD project explores how Artificial Intelligence can support the pathologist in analysing these images. The problem is that existing AI algorithms struggle to process such large images quickly and accurately. I am experimenting with neural networks that emulate visual attention processes in the human eye and brain, to identify regions of cancer cells and other tissue within the whole-slide image, to boost accuracy when classifying small patches, and to generate diagnostically useful measurements that are otherwise labour-intensive for the pathologist.