Is AI the key to effective and sustainable lung cancer screening?

Radiology as the starting point

The goal of screening is to pick up early cancers which can be treated and potentially cured, therefore improving patient outcomes (as outlined in my previous blog and the NHSE long term plan). Low dose CT has been shown to provide sufficient image quality for detection of early disease, whilst minimising radiation dose in asymptomatic individuals. Thoracic radiology expertise is required to determine which lung nodules may be malignant and therefore require invasive investigation, and which are likely benign and can be monitored with intermittent imaging. Appropriate follow-up recommendation helps avoid unnecessary invasive procedures, such as biopsies, and minimise patient anxiety, which are important measures of the efficacy of lung cancer screening programmes.

End to end lung cancer screening involves input from many healthcare professionals, and intelligent computer systems across specialities would benefit multidisciplinary teamwork. Thus, beyond image analysis, there are many opportunities for technology to add further support for effective and sustainable screening programmes. For instance, it could aid in the optimisation of image acquisition, access to imaging reports and relevant clinical details, tracking patient follow up, or in communication between patients and GPs.

Where AI-based image analysis makes a difference

1. Performance

  • Detection of elusive lung nodules, and differentiation of subtle changes
  • Automatic volume measurements, to help determine the appropriate frequency of monitoring (e.g. stable vs growing nodule, according to the BTS guidelines)

What further distinguishes computers from humans is the absolute consistency in their high performance, without being impacted by common external stressors to which a radiologist would be exposed (e.g. time-pressure, workload, interruptions).

2. (E)quality

Another use case concerns quality assurance when outsourcing to teleradiology companies. AI-based image analysis can improve consistency of reporting, drive the recommended terminology use, and, essential for lung cancer screening, ensure access to relevant prior imaging for comparison and change assessment over time.

3. Efficiency (via integration)

Older CAD technology was often described as ‘clunky’ — requiring images to be uploaded to separate systems for analysis. Additional manual steps between image acquisition and the radiology report make the process time consuming, and often require radiology support staff to manage the workflow. It is important to consider allocative and technical efficiency which play important roles in the evaluation of screening programmes, and their impact on healthcare systems.

An AI-driven image analysis software which is fully-integrated in the radiologist’s pre-existing workflow can provide automatic results, without needing additional departmental resources. An additional benefit of fully-integrated AI solutions is that their use is not restricted by time or place, therefore supporting flexible and remote working. In the context of the COVID-19 pandemic, it’s been encouraging to see the increase in remote reporting, whilst maintaining a functioning department, in many hospital trusts. Going forward, it will be interesting to see whether radiologists will have the option to continue to work remotely where possible.

Valuing input from healthcare professionals

In our experience, close collaboration between medtech and healthcare professionals is important for learning lessons along the way. Understanding radiologists’ needs helps tech teams develop a clinically valuable tool.

For example, our interactive lung nodule reporting tool, Veye Reporting, was designed based on the needs of radiologists involved in reporting lung screening scans. From our conversations with them, we understood that following the detailed and complex reporting protocols in lung cancer screening programmes make for labour-intensive, repetitive tasks.

To help them produce reports that follow the standardised NHSE proforma and facilitate audit for quality assurance, we added Veye Reporting as a feature to Veye Lung Nodules, focusing on making it easy-to-use and efficient. With this tool, the radiologists further have control over which nodules to include in the report, different sharing options, and the choice to add incidental findings.

Veye Reporting

What’s next?

The British Society of Thoracic Imaging and the Royal College of Radiologists released these considerations for optimum lung cancer screening roll-out over the next five years. Their statement below is a reminder of why it is worth overcoming challenges and leveraging technology to make screening programmes a success:

About Lizzie

Lizzie is originally from Manchester, UK. After graduating from the University of Leeds Medical School (MBChB), and Barts and the London School of Medicine (BSc sports & exercise medicine), she spent four years working as a doctor in Manchester and Liverpool NHS Trusts, including two years in Clinical Radiology. Lizzie’s areas of interest are thoracic radiology & medicine, innovation, and improving patient outcomes and healthcare professionals’ wellbeing. She has presented her work on lung cancer imaging at national/international conferences, and recently contributed to Lung Cancer Europe’s “Early Diagnosis and Screening” event at the EU Parliament in Brussels.

Connect with Lizzie on LinkedIn or Twitter.

Building clinical applications for the oncology pathway. Insights and opinions on medical imaging AI. https://www.aidence.com/