Cookies on this website
We use cookies to ensure that we give you the best experience on our website. If you click 'Continue' we'll assume that you are happy to receive all cookies and you won't see this message again. Click 'Find out more' for information on how to change your cookie settings.

The contribution of individual features on clinical imaging scans to the performance of the LCP-CNN cancer risk prediction model developed in Oxford was investigated.

Monitor screen in radiology

Pulmonary nodules are small growths in the lung and a common incidental finding on computed tomography (CT) scans. They are mostly benign but in some cases are early lung cancers. The earlier that a lung cancer is identified and treated, the more likely the outcome will be successful. However, currently, lung nodules may need to be observed with repeat CT scans for up to two years to be able distinguish between benign and malignant nodules. A key clinical challenge is to improve the ability to predict malignancy using the initial CT scan, which would remove the diagnostic delay introduced by the need for repeat scans.

There are two types of lung cancer risk prediction models, which use either statistical approaches, such as the Brock model, or machine learning approaches such as the Lung Cancer Prediction Convolutional Neural Network, LCP-CNN developed by Oxford spin-out Optellum Ltd. The Brock model is currently recommended in clinical practice by the British Thoracic Society and incorporates patient clinical information and nodule characteristics to predict which nodules are likely to be malignant.

LCP-CNN is an externally validated artificial intelligence model that performs better than the Brock model at predicting malignancy. However, because of its AI-based nature, LCP-CNN is not fully interpretable and therefore the importance of individual parameters on the model performance are not known.

In a report published in the journal European Radiology, Dr Madhurima Chetan (Oxford University Hospitals NHS Trust) and colleagues investigated the importance of CT imaging features that contributed to the enhanced performance of LCP-CNN.

Read the full story on the Oxford Centre for Early Cancer Detection website. 

 

Related Stories:

Press Release: Optellum attains CE marking for its early lung cancer diagnosis AI technology

Oxford study on Optellum software published in European Radiology

Similar stories

Com-COV vaccine study to research third dose booster options for 12-to-15-year-olds

Researchers running the University of Oxford-led Com-COV programme have launched a further study of COVID-19 vaccination schedules in young people aged 12 to 15 – with a focus on assessing different options for a third dose booster vaccination.

Population-scale study highlights ongoing risk of COVID-19 in some cancer patients despite vaccination

COVID-19 vaccination is effective in most cancer patients, but the level of protection against COVID-19 infection, hospitalisation and death offered by the vaccine is less than in the general population and vaccine effectiveness wanes more quickly.

New reporting guidelines developed to improve AI in healthcare settings

New reporting guidelines, jointly published in Nature Medicine and the BMJ by Oxford researchers, will ensure that early studies on using Artificial Intelligence (AI) to treat real patients will give researchers the information needed to develop AI systems safely and effectively.

Major boost for Oxford’s mission to counter future pandemic threats

The Moh Family Foundation has given a substantial gift to support the work of Oxford University’s Pandemic Sciences Institute, greatly strengthening its ability to identify and counter future pandemic threats and ensure equitable access to treatments and vaccines around the world.

Three NHSBT research units launch at University of Oxford

The NIHR has awarded three new Blood and Transplant Research Units (BTRUs) to the University of Oxford.