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 University of Oxford is leading two programmes of research focused on accelerating pathways for the earlier diagnosis of lung cancer. These programmes have received a total of >£12.5 million funding from UK Research and Innovation, the National Institute for Health Research, Cancer Research UK and industry.

Background

Lung cancer is the biggest cause of cancer mortality in the UK and worldwide, costing the NHS £307 million each year in England alone1. Earlier diagnosis is critical: current one-year survival reaches 88% in stage 1 compared with 19% in stage 4 disease; however, only 16% of all patients are diagnosed at stage 1 (CRUK).

lungcancerstats.png

 

Two research programmes led by the University of Oxford are aiming to improve the diagnosis of lung cancer.

 

IDEAL: Artificial Intelligence and Big Data for Early Lung Cancer Diagnosis

Growths in the lung, called nodules, can be detected using a computed tomography (CT) scan, but it is challenging to diagnose whether the nodule is benign or malignant without performing multiple scans for up to two years to detect nodule growth that would suggest it is malignant. This slows diagnosis and increases patient anxiety.

In the IDEAL study, academic clinicians from Oxford (led by Professor Fergus Gleeson), Nottingham (led by Professor David Baldwin), Leeds (led by Dr Matthew Callister) and Reading (Dr Tara Barton) are collaborating with Oxford-based Optellum Ltd to use artificial intelligence (AI) to extract information about a lung nodule from a CT scan and predict malignancy by comparing it to data from thousands of nodules where the diagnosis is known.

This AI model is currently undergoing validation2 and rigorous testing in a representative clinical environment. The aim is to implement the model into a clinical system that will support clinicians, deliver improvements to patient care, and save the NHS money. 

 

DART: The Integration and Analysis of Data using Artificial Intelligence to Improve Patient Outcomes with Thoracic Diseases

Randomised controlled trials show lung screening can reduce mortality by 20-33%3,4, and detect co-morbidities. In 2020, NHS England launched a four-year Lung Health Checks programme, at a cost of £70 million. 600,000 people aged 55-74 who are at higher risk of lung cancer will be invited to participate in a lung health check and, if necessary a low-dose CT scan at 10 sites in England*.

To improve patient care beyond the current screening guidelines, in the DART study, clinical, imaging and molecular data will be integrated for the first time using AI algorithms with the aim of earlier and more accurate diagnosis of lung cancer. DART builds on existing infrastructure from the National Consortium of Intelligent Medical Imaging (NCIMI) and exploits the multidisciplinary strengths of the team. Working with NHS England’s Lung Health Check programme, DART aims to generate disruptive integrated diagnostic innovations that:

  • more accurately diagnose lung cancer with enhanced prognostic information
  • reduce the occurrence of invasive procedures in the diagnostic pathway
  • improve patient selection for lung cancer screening
  • better assess risks from co-morbidities such as chronic obstructive pulmonary disease (COPD)
  • improve patient outcomes
  • save the NHS money

FigureDARTaimsforweb.jpg

 

DART Team

The DART team is led by Professor Fergus Gleeson and has several closely interacting components:

 

* The 10 NHS England Lung Health Check sites are:

North East and Cumbria Cancer Alliance (Newcastle Gateshead CCG), Greater Manchester Cancer Alliance (Tameside and Glossop CCG), Cheshire and Merseyside Cancer Alliance (Knowsley CCG and Halton CCG), Lancashire and South Cumbria Cancer Alliance (Blackburn with Darwen CCG and Blackpool CCG), West Yorkshire Cancer Alliance (North Kirklees CCG), South Yorkshire Cancer Alliance (Doncaster CCG), Humber, Coast and Vale Cancer Alliance (Hull CCG), East of England Cancer Alliance (Thurrock CCG and Luton CCG), East Midlands Cancer Alliance (Northamptonshire CCG and Mansfield and Ashfield CCG), Wessex Cancer Alliance (Southampton CCG).

 

References

1. Laudicella M, Walsh B, Burns E and Smith PC (2016). Cost of care for cancer patients in England: evidence from population-based patient-level data. British Journal of Cancer 114, 1286–1292. doi: 10.1038/bjc.2016.77

2. Baldwin DR, Gustafson J, Pickup L, Arteta C, Novotny P, Declerck J, Kadir T, Figueiras C, Sterba A, Exell A, Potesil V, Holland P, Spence H, Clubley A, O'Dowd E, Clark M, Ashford-Turner V, Callister MEJ, Gleeson FV (2020). External validation of a convolutional neural network artificial intelligence tool to predict malignancy in pulmonary nodules. Thorax doi: 10.1136/thoraxjnl-2019-214104

3. National Lung Screening Trial Research Team, Aberle DR, Adams AM, Berg CD, Black WC, Clapp JD, Fagerstrom RM, Gareen IF, Gatsonis C, Marcus PM, Sicks JD (2011). Reduced lung-cancer mortality with low-dose computed tomographic screening. N Engl J Med. 4;365(5):395-409. doi: 10.1056/NEJMoa1102873.

4. Patz EF Jr, Greco E, Gatsonis C, Pinsky P, Kramer BS, Aberle DR (2016). Lung cancer incidence and mortality in National Lung Screening Trial participants who underwent low-dose CT prevalence screening: a retrospective cohort analysis of a randomised, multicentre, diagnostic screening trial. Lancet Oncol. 17(5):590-9. doi: 10.1016/S1470-2045(15)00621-X.

 

See related stories

Oxford University to lead a new national programme of AI research to improve lung cancer screening

External validation of an artificial intelligence tool for predicting malignancy in patients with lung nodules

 

UKRI logonihr_logo.pngCRUK_Masterbrand_logo_JPEG_bottom aligned.jpgRoche logo.pngGE healthcare logo.pngOptellum-logo.pngRoy-Castle-LCF_Logo_BlueLong.jpg