Researchers have repurposed a Netflix algorithm designed to predict users’ film preferences to assist with biological image analysis.

The algorithm could be used to assist clinical applications such as tumour detection or tissue analysis.

Scientists at The Optical Society say that the new method is faster than traditional methods, as it is able to process images in the range of a few tens of seconds compared to minutes.

The Netflix algorithm fills in data gaps during Raman spectroscopy, a non-invasive analysis technique used to determine the chemical composition of complex samples.

Raman spectroscopy typically requires image speeds that are too slow for use in biological specimens because processing the large amount of data is time-consuming.

But with the Netflix algorithm filling in the information gaps, less data is needed and the spectroscopic imaging process is faster.

How well do you really know your competitors?

Access the most comprehensive Company Profiles on the market, powered by GlobalData. Save hours of research. Gain competitive edge.

Company Profile – free sample

Thank you!

Your download email will arrive shortly

Not ready to buy yet? Download a free sample

We are confident about the unique quality of our Company Profiles. However, we want you to make the most beneficial decision for your business, so we offer a free sample that you can download by submitting the below form

By GlobalData

“Although compressive Raman approaches have been reported previously, they couldn’t be used with biological tissues because of their chemical complexity,” said Hilton de Aguiar, leader of the research team at École Normale Supérieure in France.

“We combined compressive imaging with fast computer algorithms that provide the kind of images clinicians use to diagnose patients, but rapidly and without laborious manual post-processing.”

Netflix and spectroscopy

Researchers also swapped slower cameras normally used in Raman spectroscopy with a faster digital micromirror device known as a spatial light modulator, which is able to compress the image size as they are acquired.

“A very fast spatial light modulator made it possible to acquire images and skip data bits very quickly,” said de Aguiar.

“The spatial light modulator we used is orders of magnitude less expensive and faster than other options on the market, making the overall optical setup cheap and fast.”

The algorithm was originally developed in 2009 for a Netflix movie preference prediction competition. It did not win the $1m prize, but could now be used to help analyse more tissue types if further tests are successful.

The findings were published in scientific journal Optica.

Read more: Machine learning model classifies lung cancer slides in under a minute