Simple Science

Cutting edge science explained simply

# Biology # Cell Biology

Revolutionizing Cell Counting with Ilastik

Machine learning is changing how scientists count muscle stem cells.

Alma Zuniga Munoz, Kartik Soni, Angela Li, Vedant Lakkundi, Arundati Iyer, Ari Adler, Kathryn Kirkendall, Frank Petrigliano, Bérénice A. Benayoun, Thomas P. Lozito, Albert E. Almada

― 6 min read


Cell Counting Transformed Cell Counting Transformed by Ilastik analysis significantly. Ilastik speeds up muscle stem cell
Table of Contents

Studying how cells behave in living animals is like trying to catch a fish with your bare hands – it can be tricky! Scientists often slice up tissue to analyze it, looking for fluorescent signals that tell them about specific cells. To do this, they take pictures of the slices and measure the signals in random areas. But alas, this method can lead to mistakes, skip over important data, and take ages to finish.

The Problem with Old Methods

Traditionally, researchers use a method called Immunohistochemistry (IHC) to stain tissue slices, highlighting the specific cells they want to examine. The process involves preparing the tissue, slicing it thin, and applying special colored antibodies that stick to particular cell markers. After the staining, scientists take random pictures of the tissue and then manually count the cells they are interested in.

While this tried-and-true method has worked for years, it has several flaws. First, analyzing just a few images may not give a full picture of the tissue. Second, it relies heavily on the person counting the cells to choose the right areas to examine, which introduces human error. Finally, counting a large number of cells can be as tedious as watching paint dry.

This combination of issues slows down research in regenerative biology – the field aimed at understanding how to repair damaged tissues and organs. It also contributes to challenges with data reliability in scientific studies.

Enter Machine Learning

In recent times, smart computer programs using machine learning, a type of artificial intelligence, have come to the rescue. These programs can analyze data-rich images much faster and more accurately than a human ever could. Some popular choices include Imaris, Cell Profiler, and – you guessed it – Ilastik.

Ilastik stands out because it has an easy-to-use interface. Researchers don’t need advanced programming skills to use it. However, despite the advantages, many scientists still prefer to manually count cells. Perhaps they are stuck in their ways, or maybe they just don’t trust the machine yet.

The Aim of the Study

In this study, researchers decided to use Ilastik to see how well it could identify special Muscle Stem Cells (MuSCs) in various animals like mice, humans, axolotl salamanders, and killifish. The goal was to show that Ilastik could quickly and accurately count these cells, something that would normally take many hours or even days to do by hand.

The Steps in Using Ilastik

Using Ilastik for analysis involves a four-step process. Think of it as a cooking recipe:

  1. Sample Acquisition: Scientists collect the muscle tissue samples from their animal subjects.

  2. Pre-processing of Images: After staining the tissue with specific markers, they make sure to adjust the brightness and contrast so that the images are clear.

  3. Pixel Classification in Ilastik: Here, researchers teach Ilastik to recognize the cells they want to count. This is done by selecting examples of the cells from the images, letting the program learn the differences between the types of cells.

  4. Object Classification in Ilastik: Finally, the program refines the cell counts, filtering out unwanted data according to size and other features. The final results can be easily exported for further analysis.

Testing Ilastik on Different Species

To test how well Ilastik works, researchers collected muscle samples from several different vertebrate species. They stained these samples to look for Pax7, a marker that identifies muscle stem cells. After processing the images, they used Ilastik to analyze the samples, comparing the results to manual counts done by trained researchers.

Results in Mice

First, they looked at mouse muscle samples. They found that Ilastik accurately identified the number of PAX7+ cells before and after muscle injury, matching the counts obtained through manual counting. In fact, what took researchers days to complete could be done by Ilastik in just a few hours!

Results in Humans

Next, human muscle biopsies were analyzed. Again, Ilastik accurately identified the PAX7+ cells throughout the muscle sections. The findings were consistent with those obtained from manual counting, demonstrating that Ilastik works well in human tissues as well.

Results in Axolotl Salamanders

Moving on to axolotl salamanders, known for their amazing ability to regenerate lost limbs, researchers tested Ilastik on muscle samples taken before and after tail amputation. Findings indicated that Ilastik was just as effective at counting PAX7+ cells in the regenerating tissues as in mouse and human samples.

Results in Killifish

Finally, they examined the African turquoise killifish, a short-lived species. Researchers compared the number of PAX7+ cells in young and old fish. Once again, Ilastik provided accurate counts, helping to highlight a decrease in these important cells as the fish aged.

Key Steps for Accurate Image Analysis

While the benefits of using Ilastik are clear, it’s important to note that there are crucial steps that must be taken to ensure accurate results.

Brightness and Contrast Adjustment

Getting the brightness and contrast just right is essential. If one signal is too dim compared to another, it can lead to incorrect counts. Researchers suggest checking pixel intensity distribution carefully. Properly adjusted images will yield clear results, whereas poorly adjusted ones will leave researchers guessing.

Training the Program

Training Ilastik to recognize the specific cells is another critical step. Scientists must label a variety of cell types and ensure they capture different conditions and appearances. Including cells with varying expression levels and shapes helps the program learn better.

Size Filtering and Thresholding

The final step involves filtering the selected cells by size. By adjusting the parameters, researchers can ensure that only the appropriate cells are counted, further maximizing the precision of the data obtained.

Conclusion: A New Age for Cell Count Analysis

Using Ilastik simplifies the laborious task of counting cells, making it much faster and more reliable. By effectively analyzing large amounts of imaging data, researchers can make better biological observations without spending weeks on manual counts.

This shift may change the game for scientists studying cell behavior, especially in regenerative biology, where understanding cell fates is key. It opens the door to a new world of possibilities in research, allowing researchers to work more efficiently and accurately.

So, let’s embrace the future of science, one machine-learning program at a time! And who knows? Maybe one day, counting cells could be as easy as counting sheep – assuming we wake up from that long nap, of course.

Original Source

Title: Ilastik: a machine learning image analysis platform to interrogate stem cell fate decisions across multiple vertebrate species

Abstract: Stem cells are the key cellular source for regenerating tissues and organs in vertebrate species. Historically, the investigation of stem cell fate decisions in vivo has been assessed in tissue sections using immunohistochemistry (IHC), where a trained user quantifies fluorescent signal in multiple randomly selected images using manual counting--which is prone to inaccuracies, bias, and is very labor intensive. Here, we highlight the performance of a recently developed machine-learning (ML)-based image analysis program called Ilastik using skeletal muscle as a model system. Interestingly, we demonstrate that Ilastik accurately quantifies Paired Box Protein 7 (PAX7)-positive muscle stem cells (MuSCs) before and during the regenerative process in whole muscle sections from mice, humans, axolotl salamanders, and short-lived African turquoise killifish, to a precision that exceeds human capabilities and in a fraction of the time. Overall, Ilastik is a free user-friendly ML-based program that will expedite the analysis of stained tissue sections in vertebrate animals.

Authors: Alma Zuniga Munoz, Kartik Soni, Angela Li, Vedant Lakkundi, Arundati Iyer, Ari Adler, Kathryn Kirkendall, Frank Petrigliano, Bérénice A. Benayoun, Thomas P. Lozito, Albert E. Almada

Last Update: Dec 22, 2024

Language: English

Source URL: https://www.biorxiv.org/content/10.1101/2024.12.21.629913

Source PDF: https://www.biorxiv.org/content/10.1101/2024.12.21.629913.full.pdf

Licence: https://creativecommons.org/licenses/by/4.0/

Changes: This summary was created with assistance from AI and may have inaccuracies. For accurate information, please refer to the original source documents linked here.

Thank you to biorxiv for use of its open access interoperability.

Similar Articles