AI discovers cellular structures that humans can’t see

The development of medicine was possible when humans became familiar with our bodies. Today, medical scientists are constantly studying our bodies, and now the human eye is facing a tiny basic unit of cells in our bodies.

Of course we have a microscope. But if you go into a very small cell unit, the microscope can’t help but have limitations. Scientists have used many methods to observe living cells as they are. Fluorescent dyeing was typical. You literally dye the cells fluorescently and observe their shape. The problem is that it’s expensive, it’s harmful to living cells, and it can damage them. We don’t have enough.

The alternative is optical microscopy, which has the advantage of being able to observe inexpensive, living cells as they are, but it wasn’t easy to observe.

AI was used to discover living cell structures by combining the advantages of these two technologies. Scientists at Allen Institute have developed a technique for learning 3D images of fluorescent-dyed cells to find out what their structure looks like with just photos of cells taken under an optical microscope without fluorescent dyeing. It’s a technology that uses deep learning algorithms to see DNA and detail of nuclei, including cell membranes and mitochondria, in 3D. This technology ‘predicts’ how fluorescent materials will be dyed by observing them with an optical microscope. It takes only 0.065 seconds to predict the structure.

A neural network technology called GAN was also used. GAN is a machine learning method that automatically creates images, videos, and voices that are close to the real world as generative and discriminant models compete. These finely trained models of artificial intelligence allow us to observe even microscopic cellular structures that humans cannot even observe. Of course, training takes a lot of resources and time. A supercomputer with multiple graphics processing units may require a few weeks. But once this is done, the prediction model can use a laptop or even a cell phone.

Wouldn’t it be possible for all the medical professionals around the world to learn and study it together on the Ainize, which is based on the blockchain that AI network advocates? You don’t need a supercomputer. How good would it be if the blockchain could be used to achieve the collective intelligence of all medical professionals around the world?!

Source: https://www.nature.com/articles/d41586-021-00812-7

AI network is a blockchain-based platform and aims to innovate the AI development environment. It represents a global back-end infrastructure with millions of open source projects deployed live.

If you want to know more about us,

--

--

--

AI Network official account. Please contact me here. info@ainetwork.ai

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Algorithms are the New Drugs

A machine-generated book and an algorithmic author

Lenovo Delivers Artificial Intelligence at the Edge to Drive Business Transformation

Is AI the Secret Ingredient in Covid-19 Vaccine Rollout and Tracking?

Why Chatbots?

Chatbots for Business: Needs, Misconceptions, and Marketing Hype

AGI, GPT-3 and French patisserie-driving value with AI

The emerging DevOps trend with AI and ML

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
AI Network

AI Network

AI Network official account. Please contact me here. info@ainetwork.ai

More from Medium

Artificial Intelligence — Reality v/s Fiction

Do You Think We Will Live On Mars In The Future?

AI & Law: Multijurisdictional Lawyering

How AI will revolutionize video games | Game World Observer