Editorial Feature

Robots and Optical Microscopy

Robotics have been applied to optical microscopy for around 15 years and in that time, automated microscopy has grown by leaps and bounds.

Developed by Steven Finkbeiner at the Gladstone Institute in San Francisco, the first-recognised robotic microscopy system was capable of tracking millions of individuals cells around the clock.

As with other applications of robotics, the robotic microscope opened up new possibilities by automating mundane and repetitive tasks. Freed from monitoring cells ‘by hand’, laboratory researchers could put more time and energy into analysis and problem solving.

Finkbeiner and his team were able to demonstrate the power of this system by using it to make a major breakthrough on the neurodegenerative disorder known as Huntington’s disease. The robotic microscope was used to monitor a set of 24 plastic wells, with each one holding approximately 50,000 brain cells.

Konstantin Kolosov/Shutterstock

The automated microscope was capable of returning to the exact location of each individual cell and monitoring their development for weeks. The system wasn’t even disturbed by the tray holding the samples being moved from storage to the microscope and back.

Early robotic microscopy systems held significant promise in the area of drug research. Infected cells could be observed as prospective medications were introduced. The responses of cells over time could then be documented and reviewed.

Another promising application was in the evaluation of the effects of cellular genetic engineering. Because the system allowed for the monitoring of individual cells, scientists could track mixed populations of cells where some had been genetically modified, and others had not.

Genetic scientists could erase particular genes in some cells and quickly figure out if the modified cells were more or less prone to disease than their naturally-occurring counterparts.

Monitoring the Oceans

Over the past decade and a half, robotic microscopy has gone far beyond those initial stages at the Gladstone Institute. In a cutting edge application, that is being developed by IBM, small robotic microscopes will be used to monitor the health of the world’s oceans.

When it comes to monitoring the conditions of our oceans and waterways, researchers find it difficult to gather and evaluate even the most basic data in real time. While there are remote sensors that identify particular chemicals and qualities in water, they are unable to handle the unexpected introduction of invasive species or certain chemicals.

IBM has announced that its scientists are developing small, robotic microscopes that can be put into bodies of water to monitor plankton, with the idea that these tiny microorganisms can indicate water quality based on their response to various environmental changes.

The tiny microscope being developed by IBM uses an imager chip, like the one found in smartphones, to image the shadow of a plankton as it passes by. This produces a digital record of the plankton's health that can be analyzed.

IBM has said it expects a network of these small robotic microscopes to be deployed around the planet and connected to the cloud in five years. Down the road, IBM said, the microscope might be equipped with AI technology so that it can assess the data it collects, reporting any irregularities in real-time.

More Insight through Machine Learning

In 2014, researchers from Google approached Finkbeiner about applying complex machine learning algorithms to robotic microscopy. The idea was to use machine learning to pull key data points from an exceptionally large data set, like a collection of pictures, and use them to generate a predictive tool.

Once they have been ‘trained’, machine learning algorithms can put that training into use to assess other data sets, possibly from very disparate sources.

The process could be used to deal with extremely difficult, intricate issues, and be capable of spotting patterns in information that are too big and intricate for us to comprehend.

Because Finkbeiner and his team couldn’t process microscopy data at the rate it was being generated, he agreed to collaborate with the Google researchers. Recently, the joint venture was able to develop a machine learning algorithm that is able to predict the types of labels that should be used on an unknown collection of cells.

Scientists are now incorporating machine learning algorithms with robotic microscopy to categorize cellular pictures, conduct genomic testing, discover new drugs, and make connections across various information types.

Sources and Further Reading

Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.

Brett Smith

Written by

Brett Smith

Brett Smith is an American freelance writer with a bachelor’s degree in journalism from Buffalo State College and has 8 years of experience working in a professional laboratory.

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Smith, Brett. (2020, October 01). Robots and Optical Microscopy. AZoRobotics. Retrieved on February 21, 2024 from https://www.azorobotics.com/Article.aspx?ArticleID=288.

  • MLA

    Smith, Brett. "Robots and Optical Microscopy". AZoRobotics. 21 February 2024. <https://www.azorobotics.com/Article.aspx?ArticleID=288>.

  • Chicago

    Smith, Brett. "Robots and Optical Microscopy". AZoRobotics. https://www.azorobotics.com/Article.aspx?ArticleID=288. (accessed February 21, 2024).

  • Harvard

    Smith, Brett. 2020. Robots and Optical Microscopy. AZoRobotics, viewed 21 February 2024, https://www.azorobotics.com/Article.aspx?ArticleID=288.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this article?

Leave your feedback
Your comment type
Submit