Lucida Medical’s AI based and CE marked prostate cancer detection software, Prostate Intelligence™ (Pi™) is to undergo a retrospective cohort validation study .
In May 2021, Lucida Medical was granted a CE Mark for Prostate Intelligence™ (Pi™ ), its AI-machine learning software for detecting prostate cancer from MRI, enabling faster and more accurate prostate cancer detection. This makes Lucida one of the first companies in the world to commercialise artificial intelligence software to identify cancer in prostate MRI scans.
CE marking allows Pi™ to help radiologists assess and report MRI imaging studies, support the decision whether or not to biopsy and accurately target biopsies where needed.
The burden of prostate cancer
According to GLOBOCAN 2020 estimates of cancer incidence and mortality produced by the International Agency for Research on Cancer, worldwide, an estimated 19.3 million new cancer cases occurred in 2020 including approximately 1.4 million cases of prostate cancer.
International mortality rates for prostate cancer vary considerably worldwide . In 2018, the highest mortality rates were recorded in Central America (10.7 per 100,000 people), followed by Australia and New Zealand (10.2) and Western Europe (10.1). The lowest rate was reported in the countries of Asia (South-Central, 3.3; Eastern, 4.7 and South-Eastern, 5.4) and Northern Africa (5.8). One-third of the deaths for prostate cancer occurred in Asia (33.0%, 118,427 of deaths), followed by Europe (29.9%, 107,315 of deaths).
About the use of MRI for the detection of prostate cancer
MRI is currently the preferred technique to assess a range of cancers, including prostate and metastatic disease. However, the current process of radiologists interpreting oncological MRI requires specialist training and is labour-intensive, creating a growing skills challenge. The shortfall in the UK radiologist workforce is forecast to reach 43% by 2024.
Prostate cancer diagnosis using MRI represents a major step forward compared to earlier methods but remains prone to human error. The ground-breaking PROMIS study (Lancet 2017; 389: 815–22) indicated that radiologists can miss 12% of significant cancers on MRI, and lead to 55% of individuals without significant cancer receiving a painful and costly biopsy. The study presented at European Congress of Radiology (ECR) 2021 suggests that Lucida Medical’s AI technology could help cut missed cancers to 7% and unnecessary biopsies to 24%, as well as making the process faster.
The goal of Lucida Medical to enable faster and more accurate prostate cancer detection
Lucida Medical’s goal is to significantly improve the prostate cancer diagnostic pathway with technology that finds cancer more accurately by analysing MRI, enabling radiologists to save time and patients to receive the best possible diagnosis and treatment. It will help providers offer RAPID ‘one stop shop’ diagnosis, enabling patients to have an MRI, report and biopsy in one visit, and ensure consistent reporting quality across imaging networks.
Lucida Medical’s Prostate Intelligence™ (Pi™ ) technology uses AI to achieve its goal
Lucida Medical’s Prostate Intelligence™ (Pi™ ) technology uses radiogenomics, machine learning (a subset of Artifical Intelligence) and image processing to analyse magnetic resonance imaging (MRI) scans. Results presented at the European Congress of Radiology (ECR) in March 2021 indicate that it can help automate labour-intensive tasks such as marking out lesions, and avoid unnecessary invasive biopsies, with unprecedented accuracy and consistency.
What are the next steps now that the CE Mark has been granted?
For the UK NHS to adopt this technology, its accuracy needs to be proven in a range of settings. Most studies on AI for radiology to date have used data from single centres, but it is known that performance can vary between hospitals and with equipment from different scanner types.
In this case, a retrospective cohort validation study (PAIR 1) of AI-based prostate cancer diagnosis support software Pi ™ led by the UK Hampshire Hospitals NHS Foundation Trust (HHNFT) and Lucida Medical will be conducted.
This collaborative research led by HHFT is specifically setting out to test how the software would work at a range of different NHS hospitals and with all major MRI scanner manufacturers.
The PAIR-1 (Prostate AI Research – 1) study will collect data on 2100 patients who were diagnosed at 7 different centres. All data will be de-identified so that the researchers will not be able to link it to individuals, following a strict protocol approved by the UK Health Research Authority.
Just over half of this data will be used first to make sure that the software will work well across the full range of scanners and scanning methods in different hospitals. The developers will use this data to check that the AI software is correctly calibrated, and to change settings if necessary. The remainder of the data will then be used to test how well the AI software works with unseen patients, paving the way for it to be used in a clinical setting.
This work is especially valuable because it will allow the software to be tested with the same types of patients, scanners and hospitals that would be encountered in practical clinical use, but without impacting on patients’ care.