2 The diagnostic tests

Clinical need and practice

2.1 Lung cancer is one of the most common types of cancer in the UK. It causes symptoms such as persistent cough, coughing up blood, and feeling short of breath. People in the early stages of the disease may not have symptoms, so lung cancer is often diagnosed late. In 2018, more than 65% of lung cancers were diagnosed at stage 3 or 4 (Cancer Research UK). The NHS Long Term Plan sets out the NHS's ambition to diagnose 75% of all cancers at stages 1 or 2 by 2028.

2.2 Detecting lung nodules (small growths in the lung, which can be cancerous) could help find lung cancer early. Lung nodules can be seen on a chest CT scan. The scan may be done because of signs and symptoms that suggest lung cancer, or as part of targeted lung health checks. Lung nodules can also be detected incidentally on CT scans done for reasons unrelated to lung cancer, such as trauma or heart problems.

2.3 Computer-aided detection (CAD) software with artificial intelligence (AI)‑derived algorithms can be used to automatically detect and measure lung nodules on chest CT scan images. This could help radiologists or other healthcare professionals review scan images, and support clinical decisions about the need for CT surveillance or further investigation. Using it alongside clinician review may help to find and treat lung cancer early by:

  • increasing detection of lung nodules that need further investigation or surveillance

  • improving reporting of nodule characteristics (such as nodule volume) to support decision making

  • helping assess the growth of lung nodules under CT surveillance

  • reducing the time to review and report CT scans.

The interventions

2.4 The CAD software included in this evaluation has AI‑derived automated nodule detection and volume measurement capability. All software technologies in clinical settings use fixed algorithms. They cannot adapt in real time using data from the clinical practice setting in which they are used. In the NHS, AI-based technologies are only used alongside healthcare professionals, not as standalone interventions. The healthcare professional who reviews the CT scan using the software makes the final reporting decision.

2.5 The technologies in this evaluation are:

  • AI-Rad Companion Chest CT (class 2a medical device, Siemens Healthineers)

  • AVIEW LCS+ (class 2a medical device [information from public domain], Coreline Soft)

  • ClearRead CT (class 2a medical device, Riverain Technologies)

  • contextflow SEARCH Lung CT (class 2a medical device, contextflow)

  • InferRead CT Lung (class 2a medical device, Infervision)

  • JLD-01K (class 1 medical device, JLK Inc.)

  • Lung AI (class 2 medical device [information from public domain], Arterys)

  • Lung Nodule AI (at the time of writing, Lung Nodule AI does not have a CE mark, Fujifilm)

  • qCT‑Lung (class 2b medical device, Qure.ai)

  • SenseCare‑Lung Pro (class 2b medical device [information from public domain], SenseTime)

  • Veolity (class 2a medical device, MeVis)

  • Veye Lung Nodules (class 2b medical device, Aidence)

  • VUNO Med-LungCT AI (class 2a medical device [information from public domain], VUNO).

    At the time of writing, JLD-01K and Lung Nodule AI were not available in the UK.

The comparator

2.6 The comparator is a chest CT scan review by a radiologist or other healthcare professional without assistance from AI‑derived CAD software. The healthcare professional reviewing the scan may or may not be specialised in reviewing chest CT images. In NHS England's Targeted Lung Health Checks programme (which provides a starting point for the implementation of targeted lung cancer screening in England), the healthcare professionals reviewing scans are radiologists specialised in reviewing chest CT images. In other CT scan settings, levels of specialisation and experience vary.

  • National Institute for Health and Care Excellence (NICE)