Transformational AI Cancer Diagnostics Tool to Improve Patient Outcomes
Tests carried out by pathologists on cancer biopsy tissue help determine the best treatment options for patients. Rapid and accurate testing is critical, but testing is expensive, results can be slow, and inaccuracies may occur.
Sonrai Analytics is developing a transformational cancer diagnostics tool to aid pathologists, enabling faster and more accurate patient test results.
In collaboration with Precision Medicine Centre (PMC) at Queen’s University, our expert team are developing new Artificial Intelligence IVD medical devices. The cloud-based devices enable pathologists to upload images of resection and biopsy samples and ‘run’ them against Sonrai Analytics algorithms.
Our IVD medical devices will focus on MSI testing for Lynch Syndrome and Tumour Proportion Scoring for PD-L1 in Non-Small Cell Lunch Cancer samples.
0
Patients diagnosed with colorectal cancer (16k deaths pa and 53% survival rate) who require MSI/MMR tests
0
with non-small cell lung cancer (35k deaths and 10% survival rate) who need a PD-L1 test
Tests carried out by pathologists on cancer biopsy tissue help determine the best treatment options for patients. Rapid and accurate testing is critical, but testing is expensive, results can be slow, and inaccuracies may occur.
- Test results can be slow - MSI results take 14 days on average.
- Traditional PD-L1 testing is difficult, and inaccuracies may occur.
- These tests are expensive and cost a total of £11.1m - £15.5m per year to the NHS.
- Not all areas can deliver these tests.
- Today cancer biopsies are processed and analysed by pathologists who manually identify cancer subtypes based on their knowledge and experience.
Today cancer biopsies are processed and analysed by pathologists who manually identify cancer subtypes based on their knowledge and experience. The new approach will mean that the AI will analyse images of the slides and help pathologists diagnose and determine treatment options more accurately and consistently.
Using cloud-based technologies will allow both the images and data to be stored and shared securely and will accelerate the diagnostic workflows within pathology labs.
Through the active involvement of the Northern Ireland Cancer Research Consumer Forum, the project will also work to enhance public understanding of the benefits of AI in cancer diagnostics.
The programme is funded by an Artificial Intelligence in Health and Care Award to deliver novel AI cancer screenings across the NHS. The AI screening method will mean more accurate testing and faster results for patients and potential savings for the NHS of up to £3.2m each year.
- CE marked clinical assistive tools for pathologists
- The benefits for patients are faster and more accurate testing (results in 24-48 hours)
- Annual savings for NHS of £648,500 - £3,228,500. Indirect savings associated with more accurate PD-L1 testing would impact 10% of patients and £35m of the therapeutics budget.
- A proven model of AI-based testing which can be adopted across the NHS
Sonrai Analytics has already developed two algorithms prototypes and with this award plan to:
- Increase their accuracy by training them on datasets.
- Create a testing platform where users can upload biopsy images and ‘run’ them against the algorithms.
- Obtain clinical validation and regulatory approval and promote NHS adoption.
The Artificial Intelligence in Health and Care Award is one of the NHS AI Lab programmes led by NHSX. The competitive award scheme is run by the Accelerated Access Collaborative (AAC) runs the competitive award scheme in partnership with the National Institute for Health Research (NIHR). The AI Award is making £140 million available over four years to accelerate the testing and evaluation of artificial intelligence technologies which meet the aims set out in the NHS Long Term Plan.
The Award aims to increase the impact of AI-driven technologies to help solve clinical and operational challenges across the NHS and care settings. It will speed up the most promising technologies through the regulatory process by building an evidence base to demonstrate the effectiveness and safety of AI-driven technologies in health and social care.
Each round of the Award will support different categories of technology to address clinical and patient needs.
- Increase their accuracy by training them on datasets.
- Create a testing platform where users can upload biopsy images and ‘run’ them against the algorithms.
- Obtain clinical validation and regulatory approval and promote NHS adoption.