A new, quick and non-invasive screening method combining laser analysis with AI can identify patients in the earliest stage of breast cancer, suggests new study.
Researchers led by a team at the University of Edinburgh have published their analysis of a new AI-powered screening method for breast cancer. They claim that it could improve early detective and may lead to faster, less invasive screening tests for other kinds of cancer.
Photo by ANIRUDH
At present, standard tests for breast cancer include such methods as physical examination, x-ray or ultrasound scans, and biopsy – the analysis of a sample of breast tissue. Early detection strategies tend to focus on screening based on age and particular at-risk groups.
The new technique instead reveals subtle changes in the bloodstream that occur during the initial, stage 1a phase of breast cancer – changes which are not detectable via other methods.
Researchers optimised a laser analysis technique known as Raman spectroscopy, shining a laser beam into blood plasma taken from patients. A spectrometer analysed the properties of the light after it interacted with the blood to reveal tiny changes in the chemical make-up of cells and tissues, known to be indicators of the disease.
A machine-learning algorithm – commonly referred to as artificial intelligence or AI – was employed to interpret the results, identifying similar features and helping to classify samples.
The pilot study involved 12 samples from patients with breast cancer and 12 ‘control’ samples from healthy patients, which were provided by the Breast Cancer Now Tissue Bank and Northern Ireland Biobank. The technique proved to be 98% effective at identifying breast cancer at stage 1a. The team says this is particularly significant because while similar approaches have been tested in screening for other types of cancer, the earliest these have been able to disease was at stage 2.
The new test was also able to distinguish between each of the four main subtypes of breast cancer with an accuracy of more than 90%. This, says the research team, could enable patients to receive more effective, personalised treatment in future.
Implementing this as a screening test would help identify more people in the earliest stages of breast cancer and improve the chances of treatment being successful, the team says. They aim to expand the work to involve more participants and include tests for early forms of other cancer types.
You can read the full paper, “Subtype-Specific Detection in Stage Ia Breast Cancer: Integrating Raman Spectroscopy, Machine Learning, and Liquid Biopsy for Personalised Diagnostics”, in the Journal of Biophotonics. The study was led by Dr Andy Downes at the University of Edinburgh’s School of Engineering and involved researchers from the University of Aberdeen, the Rhine-Waal University of Applied Sciences and the Graduate School for Applied Research in North Rhine-Westphalia.
Dr Downes says: ‘Most deaths from cancer occur following a late-stage diagnosis after symptoms become apparent, so a future screening test for multiple cancer types could find these at a stage where they can be far more easily treated. Early diagnosis is key to long-term survival and we finally have the technology required. We just need to apply it to other cancer types and build up a database, before this can be used as a multi-cancer test.’
In related news:
Bristol team establishes no ‘one size fits all’ treatment for diabetes
Leave a Reply