AI: From High Energy Physics to Medical Applications"

Lead Research Organisation: University of Liverpool
Department Name: Physics

Abstract

Artificial Intelligence (AI) is becoming more commonplace in many fields. The team at the University
of Liverpool for the ATLAS experiment at the Large Hadron Collider (LHC), have been using such
techniques for many years to be applied to High Energy Physics (HEP) data analyses. A local company
to the city, AIMES, provides cloud solutions and services for its clients, and has been developing
extensive expertise on data research in the medical field, using AI techniques for healthcare
applications.[1]
The ATLAS aspect of this PhD involves the commissioning of and improvements to Machine Learning
(ML) algorithms used for efficient identification of objects relevant for the analysis, including taulepton
and heavy-flavour jets. These techniques will be then applied in the future Higgs-pair analysis
to improve their sensitivity.
The AIMES project of this PhD is to evaluate the performance of convolutional neural networks to
Magnetic Resonance Imaging (MRI) data. AIMES, in collaboration with Barts Hospital in London, have
access to a large database of MR images and have already developed Fully Convolutional Networks
(FCNs) that can analyse them. The project work is to ultimately target the development of a validation
methodology for these networks and the reduction of the time needed by physicians to provide
consultation to patients.
References
[1] University of Liverpool, "Centre for Doctoral Training in Data Intensive Science: Research Projects
- Artificial Intelligence and Machine Learning: Project 8": Available from:
https://www.liverpool.ac.uk/centre-for-doctoral-training-for-innovation-in-data-intensivescience/
research-projects/artificial-intelligence-and-machine-learning/project-8/ [Accessed on:
28/11/22]

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
ST/W006766/1 01/10/2022 30/09/2028
2760511 Studentship ST/W006766/1 01/10/2022 30/09/2026 Robert McNulty