Researchers Use Netflix Algorithm to Accelerate Biological Imaging

Researchers have found a way to use an algorithm that was actually created for Netflix’s 2009 movie prediction competition to carve out a method for getting classical Raman spectroscopy images of biological tissues at unparalleled speeds. This new technological advancement has the ability to make the label-free, yet simple imaging method practical enough for applications on the clinical scene. Examples of such applications include tissue analysis or tumor detection.

A research report by the Optical Society’s journal for high-impact research (a multinational group of researchers) revealed that compressive imaging; a well-known computational imaging approach can heighten the speed of imaging by reducing the amount of the needed amount of the acquired Raman Spectra data. Typically, for images that would take minutes to acquire, they only take a few tens of seconds to acquire them. Furthermore, they have revealed that future implementations would achieve speeds as fast as sub-seconds.

Raman spectroscopy is quite preferable as it is a non-invasive technique. It doesn’t call for the preparation of samples to ascertain the chemical composition of advanced samples. Quite alright, it has revealed the potential to identify cancer cells and analyzing every tissue for disease, it usually needs image acquisition speeds that are actually too slow to get the dynamics of biological specimens. 

Although the algorithm did not win the competition and the Netflix $1 million prize that accrued to the winner, it is amazing that it can get to solve other problems in the real world. In this case, the algorithm was transferred into one that can provide a solution for biological imaging; helping in the process of achieving better biological imaging.   In the words of the leader of the research team, Hilton de Aguiar, “Although compressive Raman approaches have been reported previously, they couldn’t be used with biological tissues because of their chemical complexity. We combined compressive imaging with fast compute algorithms that provide the kind of images clinicians use to diagnose patients, but rapidly and without laborious manual post-processing.”