Oxford study on Optellum software published in European Radiology

Post author:Rhiannon Lassiter
Post published:March 21, 2022
Post category:Clinical / Publications

Researchers from the University of Oxford and Oxford University Hospitals NHS Foundation Trust (OUH) have published the results of an academic study in European Radiology which takes a closer look at the Optellum Lung Cancer Prediction (LCP) model.

The study’s lead author Madhurima Chetan MBBChir MA FRCR is a Cambridge graduate and an academic clinical fellow at the Churchill Hospital at OUH whose past papers include the use of radiomics to predict treatment response.

Co-author Professor Fergus Gleeson MD FRCP FRCR is a Consultant Radiologist and Professor of Radiology in Oxford where he holds roles as head of academic radiology, the director of the Oxford Imaging Trials Unit, and a Divisional Director for OUH.

The European Radiology study assesses the efficacy of the Brock model for assessing the malignancy of potentially cancerous cells and compares it to the Optellum Lung Cancer Prediction tool.

10,485 lung nodules in 4,660 participants were analysed. Both manual and automated nodule measurements were inputted into the Brock model, and compared to the performance of the Lung Cancer Prediction model.

In addition to findings about automated measurements improving on manual measurement, the study found that: ‘Predictive accuracy was further improved by using the Lung Cancer Prediction convolutional neural network, an artificial intelligence-based model which obviates the requirement for nodule measurement.’

Dr Chetan commented on the results:

“This result takes a closer look under the hood at the LCP convolutional neural network and how it achieves its results. The tool’s performance was previously covered by a study Thorax and the Vanderbilt study in the USA. This study covers what aspects of a lung nodule are most informative as predictors of malignancy. It also shows the importance of automating processes and using AI technologies like these to improve on the standard of patient care.”

The Optellum Virtual Nodule Clinic platform is currently being trialed at ten NHS hospitals as part of DOLCE: a landmark research project which part of the NHS AI Lab’s £140million AI in Health and Care Award to accelerate the testing and evaluation of AI in the NHS so patients can benefit from faster and more personalised diagnosis and greater efficiency in screening services. Dr Gleeson is the Research Lead for OUH’s contribution to the trial.

Speaking recently about the Optellum software, Professor Gleeson commented:

“I believe every physician involved in the care of patients with lung nodules would benefit from having access to the Optellum technology. Their software has been validated to improve CT interpretation and diagnosis for nodules that will lead to improved patient outcomes.”