New stage helps non-specialists use AI to examine microscopy pictures
- Post By : Kumar Jeetendra
- Date: 24 Apr,2021
A new, publicly available platform helps non-experts utilize artificial intelligence to examine microscopy images. The platform has been developed at Åbo Akademi University in Finland and Instituto Gulbenkian de Ciência, Portugal, and will be of big help in research and diagnostics using modern day microscopes.
Software using artificial intelligence, AI, is revolutionizing how microscopy images are analyzed. For instance, AI can be used to detect features in pictures (i.e., tumours in biopsy samples) or enhance the quality of images by removing unwanted noise. However, non-experts are still AI technology difficult to use.
In the article”Democratising deep learning for microscopy using ZeroCostDL4Mic”, published in Nature Communications on 15 April 2021, researchers describe a platform named ZeroCostDL4Mic, making these AI technologies available to everybody.
“The important novelty is that ZeroCostDL4Mic runs in the cloud for free and does not require users to have any coding experience or advanced computational skills. Effectively, it runs on any computer which has a web browser,” says Guillaume Jacquemet, Senior Researcher in Cell Biology at Åbo Akademi University.
Over the past 400 years, microscopes have enabled mankind to observe objects that are otherwise too small to be seen with the naked eye. Today, microscopy is a leading technology used worldwide to perform not only research but also diagnostics.
Modern microscopes are directly linked to digital cameras, resulting in the acquisition of hundreds to thousands of images per sample. These images will need to be processed on a computer to gain meaningful data, which is a massive undertaking.
To help with the number of images, Jacquemet and his colleagues have used AI to train a machine to do the work. In practice, ZeroCostDL4Mic is a collection of self-explanatory laptops for Google Colab, including an easy-to-use graphical user interface.
It involved a large international consortium encompassing 12 laboratories, spread across nine countries and two continents.
von Chamier, L., et al. (2021) Democratising deep learning for microscopy with ZeroCostDL4Mic. Nature Communications. doi.org/10.1038/s41467-021-22518-0.