Could AI plus lasers help catch very early breast cancers?

Very early-stage breast cancers are notoriously tough to spot via mammograms, but new technology might make detection easier.

According to a new study published recently in the Journal of Biophotonics, Scottish researchers are combining AI with high-tech “laser analysis” to spot changes in circulating blood that could signal the earliest stages of breast tumors.

Innovations like these could end up saving cancer patients’ lives, said lead study author Andy Downes, a senior lecturer in engineering at the University of Edinburgh in Scotland.

“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,” Downes noted in a university news release.

The small study involved 24 blood samples: 12 obtained from breast cancer patients and 12 from healthy people.

The new technology involves subjecting the blood’s plasma to laser beam analysis (a technology called Raman spectroscopy) and then using a device called a spectrometer to analyze the ways in which laser light interacts with the blood.

As Downes’ team explained, even tiny shifts in the chemical make-up of cells and tissues under spectroscopy can provide clues to where cancer is present.

AI is then used to help quickly and accurately interpret the findings.

The result: In this small study, at least, the new technology was 98% effective in spotting stage 1a breast cancers, the very earliest stage.

Beyond that, the strategy was 90% effective in differentiating between the 4 major subtypes of breast cancer.

Knowing the exact type of cancer a person has, at a very early stage, makes decisions around treatment easier and could save lives.

Downes explained that the findings are still early, but could have implications that reach far beyond breast cancer.

“Early diagnosis is key to long-term survival, and we finally have the technology required,” Downes concluded. “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.”

Copyright © 2024 HealthDay. All rights reserved.