DART

The unmet need

The earlier that lung cancer is diagnosed, the more likely that treatment will be successful but currently only 16% patients are diagnosed at the earliest stage of the disease.  

A team of academics and NHS clinicians will join with three leading industrial partners to define a new set of standards for lung cancer screening to increase the number of lung cancers diagnosed earlier, and therefore treated more successfully and with fewer invasive clinical procedures. 

Algorithms will be developed to better evaluate risks from comorbidities such as chronic obstructive pulmonary disease (COPD). In addition, this programme will link to data from primary care to better assess risk in the general population to refine the right at-risk individuals to be selected for screening.  

DART will use NCIMI’s established data infrastructure to collect and transfer clinical data, CT scans, digitised images of stained tissue sections (digital pathology) and blood-derived data from the consented participants of the lung cancer screening programme to the NCIMI secure data ‘lake’ based at the University of Oxford. This will be the first time, these diverse data types have been integrated using Artificial Intelligence algorithms to enable further and improved characterisation of disease than is possible by a radiologist alone. By linking the additional information available at diagnosis to outcome data, we will be able to refine the lung cancer treatment guidelines. We will link to data from primary care to better define risk in the general population.

Project aims

Randomised controlled trials show lung screening can reduce mortality by 20-33% 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, DART, working with the 10 pilot Lung Health Check sites (LHCs), will collect data from the sites and their onward referral hospitals. 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.  

DART aims to generate disruptive integrated diagnostic innovations that: 

1. more accurately diagnose lung cancer with enhanced prognostic information
2. reduce the occurrence of harmful invasive procedures in the diagnostic pathway
3. improve patient selection for lung cancer screening and reduce costs
4. improve assessment of risks from comorbidities; such as chronic obstructive pulmonary disease (COPD) 
5. improve patient outcomes 
6. generate and store a large amount of data that can be used for future research

The project expects to start collecting data when the Lung Health Checks open in Spring 2021, as their operation has been affected by COVID. 

DART currently has 9 work packages to collect, curate, and share data to improve artificial intelligence (AI) for early detection of lung cancer.