New system allows automatic analysis of biomedical videos captured by microscopy


Researchers at the Carlos III University of Madrid (UC3M) have developed a system based on computer vision techniques that allows the automatic analysis of biomedical videos captured by microscopy in order to characterize and describe the behavior of cells that appear in images.

These new techniques developed by the UC3M engineering team have been used for measurements on living tissues, in research carried out with scientists from the National Center for Cardiovascular Research (CNIC in its Spanish acronym). As a result, the team discovered that neutrophils (a type of immune cell) exhibit different behaviors in the blood during inflammatory processes and identified that one of them, caused by the Fgr molecule, is associated with development of cardiovascular diseases. This work, recently published in the journal Nature, could allow the development of new treatments to minimize the consequences of heart attacks. Researchers from the Vithas Foundation, the University of Castilla-La Mancha, the Singapore Agency for Science, Technology and Research (ASTAR) and Harvard University (USA), among others centers, participated in the study.

“Our contribution consists in the design and development of a fully automatic system, based on computer vision techniques, which allows us to characterize the cells under study by analyzing videos captured by biologists using the technique of intravital microscopy”, explains one of the authors of this work, Professor Fernando Díaz de María, head of the UC3M Multimedia Processing Group. Automatic measurements of the shape, size, movement and position relative to the blood vessel of a few thousand cells have been achieved, compared to traditional biological studies which typically rely on analyzes of a few hundred cells manually characterized. In this way, it was possible to perform a more advanced biological analysis with greater statistical significance.

This new system has several advantages, according to the researchers, in terms of time and accuracy. Generally speaking, “it is not an option to keep an expert biologist segmenting and tracking cells on video for months. On the other hand, to give a rough idea (because it depends on the number of cells and the depth of the 3D volume), our system only takes 15 minutes to analyze a 5-minute video,” says another of the researchers, Ivan González Díaz, associate professor in the Signal and Communications Theory Department at UC3M.

Deep neural networks, the tools these engineers rely on for cell segmentation and detection, are essentially algorithms that learn from examples, so to deploy the system in a new context, it is necessary to generate enough examples to allow their training. These networks are part of machine learning techniques, which in turn is a discipline within the field of artificial intelligence (AI). In addition, the system incorporates other types of statistical techniques and geometric models, all of which are described in another article, recently published in the Analysis of medical images newspaper.

The software that implements the system is versatile and can be adapted to other problems within weeks. “In fact, we are already applying it in other different scenarios, studying the immunological behavior of T cells and dendritic cells in cancerous tissue. And the interim results are promising,” says another of the team’s researchers. UC3M, Miguel Molina Moreno.

However, when conducting research in this area, researchers emphasize the importance of interdisciplinary teamwork.

In this context, it is important to recognize the prior communication effort between biologists, mathematicians and engineers, necessary to understand the basic concepts of other disciplines, before real progress can be made.

Professor Fernando Díaz de María, Head of the UC3M Multimedia Processing Group


Journal reference:

Molina-Moreno, M., et al. (2022) ACME: Automated Feature Extraction for Examination of Cell Migration by Intravital Microscopy Imaging. Analysis of medical images.


About Author

Comments are closed.