1. Data acquisition using imaging flow cytometry
NOTE: Refer to Rodrigues et al.16 with the following modifications, noting that the acquisition regions using IFC may need to be modified for optimal image capture:
<ol>
	<li>For the non-Cyt-B method, perform a cell count using a commercially available cell counter following the manufacturer&#39;s instructions (see Table of Materials) on each culture immediately before culture and immediately after the recovery period.</li>
	<li>If running samples on a single camera imaging flow cytometer, place the Brightfield (BF) in Channel 4. Replace M01 with M04, and M07 with M01. 
	NOTE: &#34;M&#34; refers to the camera channel on the IFC.</li>
	<li>Use the 40x magnification during acquisition.</li>
	<li>On the BF area versus BF aspect ratio plot during acquisition, use the following region coordinates: 
	X-coordinates: 100 and 900; Y-coordinates: 0.7 and 1 (Cyt-B method) 
	X-coordinates: 100 and 600; Y-coordinates: 0.7 and 1</li>
	<li>On the Hoechst intensity plot, use the following region coordinates: 
	X-coordinates: 55 and 75; Y-coordinates: 9.5 and 15 (Cyt-B method) 
	X-coordinates: 55 and 75; Y-coordinates: 13 and 21 (non-Cyt-B method)</li>
	<li>To remove images of apoptotic and necrotic objects from the data, launch the IDEAS 6.3 software package (henceforth referred to as the &#34;image analysis software&#34;; see Table of Materials). 
	&#8203;NOTE: The AI software has been designed to work with .daf files that have been processed using the latest version of the image analysis software. Ensure that the image analysis software is up to date.</li>
	<li>Save this work as a template (.ast) file.</li>
</ol>
2. Creating .daf files for all .rif files
<ol>
	<li>The AI software only permits importing .daf files. Create .daf files for all .rif files in the experiment through batch processing.</li>
	<li>Under the Tools menu, click on Batch Data Files and then click on Add Batch.</li>
	<li>In the new window, select Add Files and select the .rif files to be added to the batch. Under the Select a Template or Data Analysis File (.ast, .daf) option, select the .ast file that was created previously.</li>
	<li>Assign a batch name if needed and click on OK to create .daf files for all loaded .rif files.</li>
</ol>
3. Creating an experiment in the AI software
<ol>
	<li>Refer to the flow chart in Figure 1 that describes the process of creating a deep learning model using the AI software.</li>
	<li>Launch the AI software and ensure the most recent version is installed by clicking on About in the bottom left corner of the window. If the most recent version is not installed, contact support@luminexcorp.com to obtain it.</li>
	<li>The default screen in the software is the New Experiment screen. Use the Folder icon to choose where to save the experiment, and type a name for the experiment (e.g., &#34;MN model&#34;).</li>
	<li>Under Experiment Type, click the radio button beside Train to start a training experiment to begin building the CNN model. Click on Next.
	<ol>
		<li>Optional: if a model has been previously trained, it can be used as a template for a new AI model, and can be selected as a template for creation of a new model from the Select Template Model screen. If no template model exists simply skip this step by clicking Next.</li>
	</ol>
	</li>
	<li>The next screen is the Define New Model screen. Under Model, the name that was given to the model in step 3.3 will be automatically populated.
	<ol>
		<li>Under Description, type a description for the model (optional) and leave the maximum image size at 150 pixels.</li>
		<li>Under Channels, click on Add BF to add a brightfield channel to the list. Under Name, double-click on Brightfield and rename this channel to BF. Click on Add FL to add a fluorescent channel to the list. Under Name, double-click on Fluorescent and rename this channel to DNA.</li>
		<li>Under Class Names, click on Add. In the pop-up window, type Mononucleated and click on OK. This adds the mononucleated class to the list of class names. Repeat this process to ensure the following six classes are defined in the list: 
		Mononucleated 
		Mononucleated with MN 
		Binucleated 
		Binucleated with MN 
		Polynucleated 
		Irregular morphology 
		&#8203;Click on Next. 
		NOTE: These six ground truth model classes will represent the key events to be scored, as well as images with morphology that differs from the accepted scoring criteria5.
		<ol>
			<li>Optional: If desired, the analysis template from 1.7 can be included to use features from the image analysis software. If you would like to include these features in the AI model, browse for the .ast file, then from the channel specific dropdowns, choose the feature subsets you would like to include.</li>
		</ol>
		</li>
		<li>Under Select Files, click on Add Files and browse for the desired files to be added to the AI software to build the ground truth data. Click on Next. 
		NOTE: It is important to add multiple data files (e.g., positive and negative control data) that contain a sufficient number of all key events.</li>
	</ol>
	</li>
	<li>Next, on the Select Base Populations screen, locate the Non-Apoptotic population from the population hierarchy. Right-click on the Non-Apoptotic population and select Select All Matching Populations. Click on Next. 
	NOTE: It is important to exclude any populations that should not be classified (e.g., beads, debris, doublets, etc.)</li>
	<li>This screen is the Select Truth Populations screen.
	<ol>
		<li>If tagged truth populations of the key events have not been created in the image analysis software, then click on Next.</li>
		<li>If tagged truth populations have been created in the image analysis software, assign them to the appropriate model class.</li>
		<li>To assign a tagged truth population of MONO cells with MN, click on the Mononucleated with MN class under Model Classes on the left. Then click on the appropriate tagged truth population on the right that contains these events.</li>
		<li>If the tagged truth populations have been created in more than one data file, right-click on one of the truth populations and select Select All Matching Populations to add tagged populations from multiple files to the appropriate class.</li>
		<li>Once all appropriate truth populations have been assigned, click on Next.</li>
	</ol>
	</li>
	<li>On the Select Channels screen, choose the appropriate channels for the experiment. Here, set BF to channel 1 and Hoechst to channel 7. Right-click on a channel and select Apply to All. Click on Next.</li>
	<li>Finally, on the Confirmation screen, click on Create Experiment.</li>
	<li>The AI software loads images from the data files and creates the model classes defined in step 3.5.3 with the ground truth imagery that was assigned in step 3.7. Click on Finish.</li>
	<li>Once the experiment is created, five options are presented: 
	Experiment: provides details of the experiment, including data files loaded, channels chosen, and defined ground truth model classes. 
	Tagging: launches the tagging tool through which users can populate ground truth data. 
	Training: trains a model based on the ground truth data. 
	Classify: uses trained models to classify data. 
	&#8203;Results: provides results from both a training experiment and a classify experiment.</li>
</ol>
4. Populating the ground truth data using AI-assisted tagging tools
<ol>
	<li>Click on Tagging to launch the tagging tool interface.
	<ol>
		<li>Click on the zoom tools (magnifying glass icons) to crop the images for easier viewing.</li>
		<li>Click on the slider bar to adjust the image size to change how many images are shown in the gallery.</li>
		<li>Click on the Display Setting option, and choose Min-Max, which provides the best contrast image for identifying all key events.</li>
		<li>Click on Setup Gallery Display to change the color of the DNA image to yellow or white, which will improve the visualization of small objects (e.g., MN).</li>
	</ol>
	</li>
	<li>Click on Cluster to run the algorithm to group objects with similar morphology together.&#160;Once clustering is complete, the individual clusters with the number of objects per cluster are shown in a list under Unknown Populations. Select the individual clusters to view the objects within the cluster and assign these objects to their appropriate model classes.</li>
	<li>After a minimum of 25 objects have been assigned to each model class, the Predict algorithm becomes available. Click on Predict. 
	NOTE: Objects that don&#39;t fit well into any population remain classified as Unknown. As more objects are added to the truth populations, the prediction accuracy improves.</li>
	<li>Continue to populate the ground truth model classes with appropriate imagery until a sufficient number of objects in each class is reached.</li>
	<li>Once a minimum of 100 objects have been assigned to each model class, click on the Training tab at the top of the screen. Click on the Train button to create a model using the Random Forest and CNN algorithms.&#160; 
	NOTE:&#160;The AI software creates models using both the Random Forest and CNN algorithms, the checkboxes permit creation of models using Random Forest of CNN algorithms only.</li>
</ol>
5. Assessing model accuracy
<ol>
	<li>Once model training is complete, click on View Results.</li>
	<li>Use the results screen to assess model accuracy.&#160;Use the pulldown menu to switch between Random Forest and CNN.&#160; 
	NOTE: The truth populations can be updated, and the model can be re-trained or used as-is to classify additional data.
	<ol>
		<li>To update the truth populations, click on Tagging at the top and follow section 4.</li>
	</ol>
	</li>
</ol>
6. Classifying data using the model
<ol>
	<li>Launch the AI software. The default screen is the New Experiment screen. Use the Folder icon to choose where to save the experiment and type a name for the experiment.</li>
	<li>Under Experiment Type, click the radio button beside Classify to start a classification experiment. Click on Next.</li>
	<li>Click on the model to be used for classification, then click on Next.</li>
	<li>On the Select Files screen, click on Add Files and browse for the files to be classified by the CNN model. Click on Next.</li>
	<li>Next, on the Select Base Populations screen, click on the checkbox next to the Non-Apoptotic population in one of the loaded files. Right-click on the Non-Apoptotic population and click on Select All Matching Populations to select this population from all loaded files. Click on Next.</li>
	<li>Optional: if the data to be classified contains truth populations, they can be assigned to the appropriate model classes on the Select Truth Populations screen. Otherwise, click Next to skip this step.</li>
	<li>On the Select Channels screen, choose Channel 1 for brightfield and Channel 7 for the DNA stain. Right-click on a channel and click on Apply to All. Then click on Next.</li>
	<li>Finally, on the Confirmation screen, click on Create Experiment. The AI software loads the selected model and all images from the chosen data files. Click on Finish.</li>
	<li>Click on Classify to launch the classification screen. Click on the Classify button. This begins the process of using the RF and CNN model to classify additional data and identify all objects that belong in the specified model classes. 
	NOTE: The checkboxes can be used to select the RF model and/or the CNN model.</li>
	<li>Once the classification is complete, click on View Results.</li>
	<li>Click the Update DAFs button to bring up the Update DAFs with Classification Results window. Click on OK to update the .daf files.</li>
</ol>
7. Generating a report of the classification results
<ol>
	<li>On the Results screen, click on Generate Report. Select the checkbox beside Create Report for Each Input DAF if an individual report for each input daf is required. Click on OK.</li>
	<li>Once completed, open the folder where the report files have been saved. Within the folder, there is an experiment .pdf report and a Resources folder.</li>
	<li>Open the .pdf to view the report. The report contains model and experiment information, the list of input .daf files, the class counts and class percentages in tabular and histogram format, and a confusion matrix summarizing the median prediction probability across all input .daf files.</li>
	<li>Open the Resources folder and then the CNN folder. Within this folder are .png files of the class count and percentage bar graphs, as well as the confusion matrix. Additionally, there are .csv files containing the class counts and percentages for each input file.</li>
</ol>
8. Determining MN frequency and cytotoxicity
<ol>
	<li>Calculating MN frequency
	<ol>
		<li>Non Cyt-B method: To determine MN frequency, open the class_count.csv file from step 7.4. For each input file, divide the counts in the &#34;Mononucleated with MN&#34; population by the counts in the &#34;Mononucleated&#34; population and multiply by 100: 
		<img alt="Equation 1" src="/files/ftp_upload/64549/64549eq01.jpg" style="margin: auto;" /></li>
		<li>Cyt-B method: To determine MN frequency, open the class_count.csv file from step 7.4. For each input file, divide the counts in the &#34;Binucleated with MN&#34; population by the counts in the &#34;Binucleated&#34; population and multiply by 100: 
		<img alt="Equation 2" src="/files/ftp_upload/64549/64549eq02.jpg" style="margin: auto;" /></li>
	</ol>
	</li>
	<li>Calculating cytotoxicity
	<ol>
		<li>Non Cyt-B method:
		<ol>
			<li>Using the initial cell counts and the post-treatment cell counts, first calculate the population doubling (PD) for each sample2: 
			<img alt="Equation 3" src="/files/ftp_upload/64549/64549eq03.jpg" style="margin: auto;" /></li>
			<li>Next, calculate the relative population doubling2: 
			<img alt="Equation 4" src="/files/ftp_upload/64549/64549eq04.jpg" style="margin: auto;" /></li>
			<li>Finally, calculate the cytotoxicity2 for each sample: 
			<img alt="Equation 5" src="/files/ftp_upload/64549/64549eq05.jpg" style="margin: auto;" /></li>
		</ol>
		</li>
		<li>Cyt-B method:
		<ol>
			<li>To calculate Cytokinesis-Block Proliferation Index (CBPI)2, use the counts in the mononucleated, binucleated, and polynucleated classes for each sample from the class_count.csv file: 
			<img alt="Equation 6" src="/files/ftp_upload/64549/64549eq06v2.jpg" style="margin: auto;" /></li>
			<li>To calculate cytotoxicity2, use the CBPI from the control cultures (C) and exposed cultures (T): 
			<img alt="Equation 7" src="/files/ftp_upload/64549/64549eq07.jpg" style="margin: auto;" /></li>
		</ol>
		</li>
	</ol>
	</li>
</ol>

<ol>
	<li>Fenech, M., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=HUMN+project+initiative+and+review+of+validation,+quality+control+and+prospects+for+further+development+of+automated+micronucleus+assays+using+image+cytometry+systems.">HUMN project initiative and review of validation, quality control and prospects for further development of automated micronucleus assays using image cytometry systems.</a> International Journal of Hygiene and Environmental Health. 216 (5), 541-552 (2013).</li><li>OECD. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Test+No.+487:+In+Vitro+Mammalian+Cell+Micronucleus+Test.+Section+4.">Test No. 487: In Vitro Mammalian Cell Micronucleus Test. Section 4.</a> OECD Guidelines for the Testing of Chemicals. , (2016).</li><li>Fenech, M. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=The+in+vitro+micronucleus+technique.">The in vitro micronucleus technique.</a> Mutation Research/Fundamental and Molecular Mechanisms of Mutagenesis. 455 (1), 81-95 (2000).</li><li>Bonassi, S., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=An+increased+micronucleus+frequency+in+peripheral+blood+lymphocytes+predicts+the+risk+of+cancer+in+humans.">An increased micronucleus frequency in peripheral blood lymphocytes predicts the risk of cancer in humans.</a> Carcinogenesis. 28 (3), 625-631 (2007).</li><li>Fenech, M. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Cytokinesis-block+micronucleus+cytome+assay.">Cytokinesis-block micronucleus cytome assay.</a> Nature Protocols. 2 (5), 1084-1104 (2007).</li><li>Fenech, M. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Commentary+on+the+SFTG+international+collaborative+study+on+the+in+vitro+micronucleus+test:+To+Cyt-B+or+not+to+Cyt-B.">Commentary on the SFTG international collaborative study on the in vitro micronucleus test: To Cyt-B or not to Cyt-B.</a> Mutation Research/Fundamental and Molecular Mechanisms of Mutagenesis. 607 (1), 9-12 (2006).</li><li>Seager, A. L., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Recommendations,+evaluation+and+validation+of+a+semi-automated,+fluorescent-based+scoring+protocol+for+micronucleus+testing+in+human+cells.">Recommendations, evaluation and validation of a semi-automated, fluorescent-based scoring protocol for micronucleus testing in human cells.</a> Mutagenesis. 29 (3), 155-164 (2014).</li><li>Rossnerova, A., Spatova, M., Schunck, C., Sram, R. J. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Automated+scoring+of+lymphocyte+micronuclei+by+the+MetaSystems+Metafer+image+cytometry+system+and+its+application+in+studies+of+human+mutagen+sensitivity+and+biodosimetry+of+genotoxin+exposure.">Automated scoring of lymphocyte micronuclei by the MetaSystems Metafer image cytometry system and its application in studies of human mutagen sensitivity and biodosimetry of genotoxin exposure.</a> Mutagenesis. 26 (1), 169-175 (2011).</li><li>Bryce, S. M., Bemis, J. C., Avlasevich, S. L., Dertinger, S. D. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=In+vitro+micronucleus+assay+scored+by+flow+cytometry+provides+a+comprehensive+evaluation+of+cytogenetic+damage+and+cytotoxicity.">In vitro micronucleus assay scored by flow cytometry provides a comprehensive evaluation of cytogenetic damage and cytotoxicity.</a> Mutation Research/Genetic Toxicology and Environmental Mutagenesis. 630 (1), 78-91 (2007).</li><li>Avlasevich, S. L., Bryce, S. M., Cairns, S. E., Dertinger, S. D. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=In+vitro+micronucleus+scoring+by+flow+cytometry:+Differential+staining+of+micronuclei+versus+apoptotic+and+necrotic+chromatin+enhances+assay+reliability.">In vitro micronucleus scoring by flow cytometry: Differential staining of micronuclei versus apoptotic and necrotic chromatin enhances assay reliability.</a> Environmental and Molecular Mutagenesis. 47 (1), 56-66 (2006).</li><li>Basiji, D. A. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Principles+of+Amnis+imaging+flow+cytometry.">Principles of Amnis imaging flow cytometry.</a> Methods in Molecular Biology. 1389, 13-21 (2016).</li><li>Rodrigues, M. A. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Automation+of+the+in+vitro+micronucleus+assay+using+the+Imagestream&#174;+imaging+flow+cytometer.">Automation of the in vitro micronucleus assay using the Imagestream&#174; imaging flow cytometer.</a> Cytometry Part A. 93 (7), 706-726 (2018).</li><li>Verma, J. R., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Investigating+FlowSight&#174;+imaging+flow+cytometry+as+a+platform+to+assess+chemically+induced+micronuclei+using+human+lymphoblastoid+cells+in+vitro.">Investigating FlowSight&#174; imaging flow cytometry as a platform to assess chemically induced micronuclei using human lymphoblastoid cells in vitro.</a> Mutagenesis. 33 (4), 283-289 (2018).</li><li>Wills, J. W., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Inter-laboratory+automation+of+the+in+vitro+micronucleus+assay+using+imaging+flow+cytometry+and+deep+learning.">Inter-laboratory automation of the in vitro micronucleus assay using imaging flow cytometry and deep learning.</a> Archives of Toxicology. 95 (9), 3101-3115 (2021).</li><li>Rodrigues, M. A., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=The+in+vitro+micronucleus+assay+using+imaging+flow+cytometry+and+deep+learning.">The in vitro micronucleus assay using imaging flow cytometry and deep learning.</a> Npj Systems Biology and Applications. 7 (1), 20 (2021).</li><li>Rodrigues, M. A. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=An+automated+method+to+perform+the+in+vitro+micronucleus+assay+using+multispectral+imaging+flow+cytometry.">An automated method to perform the in vitro micronucleus assay using multispectral imaging flow cytometry.</a> Journal of Visualized Experiments. (147), e59324 (2019).</li><li>Lovell, D. P., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Analysis+of+negative+historical+control+group+data+from+the+in+vitro+micronucleus+assay+using+TK6+cells.">Analysis of negative historical control group data from the in vitro micronucleus assay using TK6 cells.</a> Mutation Research/Genetic Toxicology and Environmental Mutagenesis. 825, 40-50 (2018).</li><li>Berg, S., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=ilastik:+interactive+machine+learning+for+(bio)image+analysis.">ilastik: interactive machine learning for (bio)image analysis.</a> Nature Methods. 16 (12), 1226-1232 (2019).</li><li>Hennig, H., et al. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=An+open-source+solution+for+advanced+imaging+flow+cytometry+data+analysis+using+machine+learning.">An open-source solution for advanced imaging flow cytometry data analysis using machine learning.</a> Methods. 112, 201-210 (2017).</li></ol>

The authors are employed by Luminex Corporation, a DiaSorin Company, the manufacturer of the ImageStream imaging flow cytometer and the Amnis AI software used in this work.

The work presented here describes the use of deep learning algorithms to automate the scoring of the MN assay. Several recent publications have shown that intuitive, interactive tools allow the creation of deep learning models to analyze image data without the need for in-depth computational knowledge18,19. The protocol described in this work using a user interface-driven software package has been designed to work well with very large data files and permit the cr...

The micronucleus (MN) assay is fundamental in genetic toxicology to evaluate DNA damage in the development of cosmetics, pharmaceuticals, and chemicals for human use1,2,3,4. Micronuclei are formed from whole chromosomes or chromosome fragments that do not incorporate into the nucleus following division and condense into small, circular bodies separate from the nucleus. Thus, MN can be used as an endpoint to quantify DNA damage in genotoxicity testing1.
The preferred method for quantifying MN is within once-divided binucleated cells (BNCs) by blocking division using Cytochalasin-B (Cyt-B). In this version of the assay, cytotoxicity is also assessed by scoring mononucleated (MONO) and polynucleated (POLY) cells. The assay can also be performed by scoring MN in unblocked MONO cells, which is faster and easier to score, with cytotoxicity being assessed using pre- and post-exposure cell counts to assess proliferation5,6.
Physical scoring of the assay has historically been performed through manual microscopy, since this permits visual confirmation of all key events. However, manual microscopy is challenging and subjective1. Thus, automated techniques have been developed, including microscope slide scanning and flow cytometry, each with their own advantages and limitations. While slide-scanning methods allow key events to be visualized, slides must be created at optimal cell density, which can be difficult to achieve. Additionally, this technique often lacks cytoplasmic visualization, which can compromise the scoring of MONO and POLY cells7,8. While flow cytometry offers high-throughput data capture, the cells must be lysed, thus not permitting the use of the Cyt-B form of the assay. Additionally, as a non-imaging technique, conventional flow cytometry does not provide visual validation of key events9,10.
Therefore, imaging flow cytometry (IFC) has been investigated to perform the MN assay. The ImageStreamX Mk II combines the speed and statistical robustness of conventional flow cytometry with the high-resolution imaging capabilities of microscopy in a single system11. It has been shown that by using IFC, high-resolution imagery of all key events can be captured and automatically scored using feature-based12,13 or artificial intelligence (AI) techniques14,15. By using IFC to perform the MN assay, the automatic scoring of many more cells compared to microscopy in a shorter amount of time is achievable.
This work deviates from a previously described image analysis workflow16 and discusses all steps required to develop and train a Random Forest (RF) and/or&#160;convolutional neural network (CNN) model using the Amnis AI software (henceforth referred to as &#34;AI software&#34;). All necessary steps are described, including populating ground truth data using AI-assisted tagging tools, interpretation of model training results, and application of the model to classify additional data, permitting calculation of genotoxicity and cytotoxicity15.

<table><tbody><tr><td>15 mL centrifuge tube</td><td>Falcon</td><td>352096</td><td></td></tr><tr><td>Cleanser - Coulter Clenz&amp;nbsp;</td><td>Beckman Coulter</td><td>8546931</td><td>Fill container with 200 mL of Cleanser.&amp;nbsp; https://www.beckmancoulter.com/wsrportal/page/itemDetails?itemNumber=8546931#2/10//0/25/&lt;br/&gt; 1/0/asc/2/8546931///0/1//0/</td></tr><tr><td>Colchicine</td><td>MilliporeSigma</td><td>64-86-8</td><td></td></tr><tr><td>Corning bottle-top vacuum filter&amp;nbsp;</td><td>MilliporeSigma</td><td>CLS430769</td><td>0.22 &amp;micro;m filter, 500 mL bottle</td></tr><tr><td>Cytochalasin B</td><td>MilliporeSigma</td><td>14930-96-2</td><td>5 mg bottle</td></tr><tr><td>Debubbler - 70% Isopropanol</td><td>MilliporeSigma</td><td>1.3704</td><td>Fill container with 200 mL of Debubbler.&amp;nbsp; http://www.emdmillipore.com/US/en/product/2-Propanol-70%25-%28V%2FV%29-0.1-%C2%B5m-filtred,MDA_CHEM-137040?ReferrerURL=https%3A%2F%2Fwww.google.com%2F</td></tr><tr><td>Dimethyl Sulfoxide (DMSO)</td><td>MilliporeSigma</td><td>67-68-5</td><td></td></tr><tr><td>Dulbecco&#039;s Phosphate Buffered Saline 1X</td><td>EMD Millipore</td><td>BSS-1006-B</td><td>PBS Ca&lt;sup&gt;++&lt;/sup&gt;MG&lt;sup&gt;++&lt;/sup&gt; Free&amp;nbsp;</td></tr><tr><td>Fetal Bovine Serum</td><td>HyClone</td><td>SH30071.03</td><td></td></tr><tr><td>Formaldehyde, 10%, methanol free, Ultra Pure</td><td>Polysciences, Inc.</td><td>04018</td><td>This is what is used for the 4% and 1% Formalin. CAUTION: Formalin/Formaldehyde toxic by inhalation and if swallowed.&amp;nbsp; Irritating to the eyes, respiratory systems and skin.&amp;nbsp; May cause sensitization by inhalation or skin contact. Risk of serious damage to eyes.&amp;nbsp; Potential cancer hazard.&amp;nbsp; http://www.polysciences.com/default/catalog-products/life-sciences/histology-microscopy/fixatives/formaldehydes/formaldehyde-10-methanol-free-pure/</td></tr><tr><td>Guava Muse Cell Analyzer</td><td>Luminex</td><td>0500-3115</td><td>A standard configuration Guava Muse Cell Analyzer was used.</td></tr><tr><td>Hoechst 33342</td><td>Thermo Fisher</td><td>H3570</td><td>10 mg/mL solution</td></tr><tr><td>Mannitol</td><td>MilliporeSigma</td><td>69-65-8</td><td></td></tr><tr><td>MEM Non-Essential Amino Acids 100X</td><td>HyClone</td><td>SH30238.01</td><td></td></tr><tr><td>MIFC - ImageStreamX Mark II</td><td>Luminex, a DiaSorin company</td><td>100220</td><td>A 2 camera ImageStreamX Mark II eqiped with the 405 nm, 488 nm, and 642 nm lasers was used.</td></tr><tr><td>MIFC analysis software - IDEAS</td><td>Luminex, a DiaSorin company</td><td>100220</td><td>&quot;Image analysis sofware&quot;&lt;br/&gt; The companion software to the MIFC (ImageStreamX MKII)</td></tr><tr><td>MIFC software - INSPIRE</td><td>Luminex, a DiaSorin company</td><td>100220</td><td>&quot;Image acquisition software&quot;&lt;br/&gt; This is the software that runs the MIFC (ImageStreamX MKII)</td></tr><tr><td>Amnis AI software</td><td>Luminex, a DiaSorin company</td><td>100221</td><td>&quot;AI software&quot;&lt;br/&gt; This is the software that permits the creation of artificial intelligence models to analyze data</td></tr><tr><td>Mitomycin C</td><td>MilliporeSigma</td><td>50-07-7</td><td></td></tr><tr><td>NEAA Mixture 100x</td><td>Lonza BioWhittaker</td><td>13-114E</td><td></td></tr><tr><td>Penicllin/Streptomycin/Glutamine solution 100X</td><td>Gibco</td><td>15070063</td><td></td></tr><tr><td>Potassium Chloride (KCl)</td><td>MilliporeSigma</td><td>P9541</td><td></td></tr><tr><td>Rinse - Ultrapure water or deionized water</td><td>NA</td><td>NA</td><td>Use any ultrapure water or deionized water.&amp;nbsp; Fill container with 900 mL of Rinse.</td></tr><tr><td>RNase</td><td>MilliporeSigma</td><td>9001-99-4</td><td></td></tr><tr><td>RPMI-1640 Medium 1x</td><td>HyClone</td><td>SH30027.01</td><td></td></tr><tr><td>Sheath - PBS</td><td>MilliporeSigma</td><td>BSS-1006-B</td><td>This is the same as Dulbecco&#039;s Phosphate Buffered Saline 1x&amp;nbsp; Ca&lt;sup&gt;++&lt;/sup&gt;MG&lt;sup&gt;++&lt;/sup&gt; free.&amp;nbsp; Fill container with 900 mL of Sheath.</td></tr><tr><td>Sterile water</td><td>HyClone</td><td>SH30529.01</td><td></td></tr><tr><td>Sterilizer - 0.4%&amp;ndash;0.7% Hypochlorite</td><td>VWR</td><td>JT9416-1</td><td>This is assentually 10% Clorox bleach that can be made by deluting Clorox bleach with water.&amp;nbsp; Fill container with 200 mL of Sterilzer.</td></tr><tr><td>T25 flask</td><td>Falcon</td><td>353109</td><td></td></tr><tr><td>T75 flask</td><td>Falcon</td><td>353136</td><td></td></tr><tr><td>TK6 cells</td><td>MilliporeSigma</td><td>95111735</td><td></td></tr></tbody></table>

automation of the micronucleus assay using imaging flow cytometry and artificial intelligence

The micronucleus (MN) assay is used worldwide by regulatory bodies to evaluate chemicals for genetic toxicity. The assay can be performed in two ways: by scoring MN in once-divided, cytokinesis-blocked binucleated cells or fully divided mononucleated cells. Historically, light microscopy has been the gold standard method to score the assay, but it is laborious and subjective. Flow cytometry has been used in recent years to score the assay, but is limited by the inability to visually confirm key aspects of cellular imagery. Imaging flow cytometry (IFC) combines high-throughput image capture and automated image analysis, and has been successfully applied to rapidly acquire imagery of and score all key events in the MN assay. Recently, it has been demonstrated that artificial intelligence (AI) methods based on convolutional neural networks can be used to score MN assay data acquired by IFC. This paper describes all steps to use AI software to create a deep learning model to score all key events and to apply this model to automatically score additional data. Results from the AI deep learning model compare well to manual microscopy, therefore enabling fully automated scoring of the MN assay by combining IFC and AI.

Figure 1&#160;shows the workflow for using the AI software to create a model for the MN assay. The user loads the desired .daf files into the AI software, then assigns objects to the ground truth model classes using the AI-assisted cluster (Figure 2) and predict (Figure 3) tagging algorithms. Once all ground truth model classes have been populated with sufficient objects, the model can be trained using the RF or CNN algorithms. Foll...

Watch this Scientific Journal Video about Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence at JoVE.com

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

The micronucleus (MN) assay is a well-established test for quantifying DNA damage. However, scoring the assay using conventional techniques such as manual microscopy or feature-based image analysis is laborious and challenging. This paper describes the methodology to develop an artificial intelligence model to score the MN assay using imaging flow cytometry data.

The micronucleus (MN) assay is used worldwide by regulatory bodies to evaluate chemicals for genetic toxicity. The assay can be performed in two ways: by ...

automation-micronucleus-assay-using-imaging-flow-cytometry-artificial

Research

JoVE Journal

Bioengineering

2.0K Views.  Luminex Corporation. Het uitvoeren van de micronucleustest met behulp van beeldvormende flowcytometrie overwint veel beperkingen van traditionele methoden, waaronder lage doorvoer, scorevariabiliteit en gebrek aan visuele bevestiging van gebeurtenissen. Het belangrijkste voordeel van deze techniek is dat alle belangrijke gebeurtenissen kunnen worden verkregen met behulp van imaging flow cytometrie en geanalyseerd met behulp van kunstmatige intelligentie. Deze methode kan worden gebruikt bij grootschalige screenin...

Video: Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Analyzing Cellular Internalization of Nanoparticles and Bacteria by Multi-spectral Imaging Flow Cytometry

Nanoparticulate systems have emerged as valuable tools in vaccine delivery through their ability to efficiently deliver cargo, including proteins, to antigen presenting cells1-5. Internalization of nanoparticles (NP) by antigen presenting cells is a critical step in generating an effective immune response to the encapsulated antigen. To determine how changes in nanoparticle formulation impact function, we sought to develop a high throughput, quantitative experimental protocol that was compatible with detecting internalized nanoparticles as well as bacteria. To date, two independent techniques, microscopy and flow cytometry, have been the methods used to study the phagocytosis of nanoparticles. The high throughput nature of flow cytometry generates robust statistical data. However, due to low resolution, it fails to accurately quantify internalized versus cell bound nanoparticles. Microscopy generates images with high spatial resolution; however, it is time consuming and involves small sample sizes6-8. Multi-spectral imaging flow cytometry (MIFC) is a new technology that incorporates aspects of both microscopy and flow cytometry that performs multi-color spectral fluorescence and bright field imaging simultaneously through a laminar core. This capability provides an accurate analysis of fluorescent signal intensities and spatial relationships between different structures and cellular features at high speed.
	Herein, we describe a method utilizing MIFC to characterize the cell populations that have internalized polyanhydride nanoparticles or Salmonella enterica serovar Typhimurium. We also describe the preparation of nanoparticle suspensions, cell labeling, acquisition on an ImageStreamX system and analysis of the data using the IDEAS application. We also demonstrate the application of a technique that can be used to differentiate the internalization pathways for nanoparticles and bacteria by using cytochalasin-D as an inhibitor of actin-mediated phagocytosis.

In this article, we describe a method utilizing multi-spectral imaging flow cytometry to quantify the internalization of polyanhydride nanoparticles or bacteria by RAW 264.7 cells.

Nanoparticulate  systems have emerged as valuable tools in vaccine delivery through their  ability to efficiently deliver cargo, including proteins, to ...

Microfluidic Imaging Flow Cytometry by Asymmetric-detection Time-stretch Optical Microscopy (ATOM)

Scaling the number of measurable parameters, which allows for multidimensional data analysis and thus higher-confidence statistical results, has been the main trend in the advanced development of flow cytometry. Notably, adding high-resolution imaging capabilities allows for the complex morphological analysis of cellular/sub-cellular structures. This is not possible with standard flow cytometers. However, it is valuable for advancing our knowledge of cellular functions and can benefit life science research, clinical diagnostics, and environmental monitoring. Incorporating imaging capabilities into flow cytometry compromises the assay throughput, primarily due to the limitations on speed and sensitivity in the camera technologies. To overcome this speed or throughput challenge facing imaging flow cytometry while preserving the image quality, asymmetric-detection time-stretch optical microscopy (ATOM) has been demonstrated to enable high-contrast, single-cell imaging with sub-cellular resolution, at an imaging throughput as high as 100,000 cells/s. Based on the imaging concept of conventional time-stretch imaging, which relies on all-optical image encoding and retrieval through the use of ultrafast broadband laser pulses, ATOM further advances imaging performance by enhancing the image contrast of unlabeled/unstained cells. This is achieved by accessing the phase-gradient information of the cells, which is spectrally encoded into single-shot broadband pulses. Hence, ATOM is particularly advantageous in high-throughput measurements of single-cell morphology and texture &#8211; information indicative of cell types, states, and even functions. Ultimately, this could become a powerful imaging flow cytometry platform for the biophysical phenotyping of cells, complementing the current state-of-the-art biochemical-marker-based cellular assay. This work describes a protocol to establish the key modules of an ATOM system (from optical frontend to data processing and visualization backend), as well as the workflow of imaging flow cytometry based on ATOM, using human cells and micro-algae as the examples.

Microfluidic Imaging Flow Cytometry by Asymmetric-detection Time-stretch Optical Microscopy ATOM

This protocol describes the implementation of an asymmetric-detection time-stretch optical microscopy system for single-cell imaging in ultrafast microfluidic flow and its applications in imaging flow cytometry.

Scaling the number of measurable parameters, which allows for multidimensional data analysis and thus higher-confidence statistical results, has been the ...

Engineering

An Automated Differential Nuclear Staining Assay for Accurate Determination of Mitocan Cytotoxicity

The contribution of mitochondria to oncogenic transformation is a subject of wide interest and active study. As the field of cancer metabolism becomes more complex, the goal of targeting mitochondria using various compounds that inflict mitochondrial damage (so-called mitocans) is becoming quite popular. Unfortunately, many existing cytotoxicity assays, such as those based on tetrazolium salts or resazurin require functional mitochondrial enzymes for their performance. The damage inflicted by compounds that target mitochondria often compromises the accuracy of these assays. Here, we describe a modified protocol based on differential staining with two fluorescent dyes, one of which is cell-permeant (Hoechst 33342) and the other of which is not (propidium iodide). The difference in staining allows living and dead cells to be discriminated. The assay is amenable to automated microscopy and image analysis, which increases throughput and reduces bias. This also allows the assay to be used in high-throughput fashion using 96-well plates, making it a viable option for drug discovery efforts, particularly when the drugs in question have some level of mitotoxicity. Importantly, results obtained by Hoechst/PI staining assay show increased consistency, both with trypan blue exclusion results and between biological replicates when the assay is compared to other methods.

The protocol describes a rapid, high-throughput, reliable, inexpensive, and unbiased assay for efficiently determining cellular viability. This assay is particularly useful when cells&#39; mitochondria have been damaged, which interferes with other assays. The assay uses automated counting of cells stained with two nuclear dyes &#8211; Hoechst 33342 and propidium iodide.

The contribution of mitochondria to oncogenic transformation is a subject of wide interest and active study. As the field of cancer metabolism becomes ...

Cancer Research

An Automated Microscopic Scoring Method for the &#947;-H2AX Foci Assay in Human Peripheral Blood Lymphocytes

Ionizing radiation is a potent inducer of DNA damage and a well-documented carcinogen. Biological dosimetry comprises the detection of biological effects induced by exposure to ionizing radiation to make an individual dose assessment. This is pertinent in the framework of radiation emergencies, where health assessments and planning of clinical treatment for exposed victims are critical. Since DNA double strand breaks (DSB) are considered to be the most lethal form of radiation-induced DNA damage, this protocol presents a method to detect DNA DSB in blood samples. The methodology is based on the detection of a fluorescent labelled phosphorylated DNA repair protein, namely, &#947;-H2AX. The use of an automated microscopy platform to score the number of &#947;-H2AX foci per cell allows a standardized analysis with a significant decrease in the turn-around time. Therefore, the &#947;-H2AX assay has the potential to be one of the fastest and sensitive assays for biological dosimetry. In this protocol, whole blood samples from healthy adult volunteers will be processed and irradiated in vitro in order to illustrate the usage of the automated and sensitive &#947;-H2AX foci assay for biodosimetry applications. An automated slide scanning system and analysis platform with an integrated fluorescence microscope is used, which allows the fast, automatic scoring of DNA DSB with a reduced degree of bias.

This protocol presents the slide preparation and automated scoring of the &#947;-H2AX foci assay on peripheral blood lymphocytes. To illustrate the method and sensitivity of the assay, isolated lymphocytes were irradiated in vitro. This automated method of DNA DSB detection is useful for fast and high-throughput biological dosimetry applications.

Ionizing radiation is a potent inducer of DNA damage and a well-documented carcinogen. Biological dosimetry comprises the detection of biological effects ...

Simultaneous Imaging and Flow-Cytometry-based Detection of Multiple Fluorescent Senescence Markers in Therapy-Induced Senescent Cancer Cells

Chemotherapeutic drugs can induce irreparable DNA damage in cancer cells, leading to apoptosis or premature senescence. Unlike apoptotic cell death, senescence is a fundamentally different machinery restraining&#160;propagation of cancer cells. Decades of scientific studies have revealed the complex pathological effects of senescent cancer cells in tumors and microenvironments that modulate cancer cells and stromal cells. New evidence suggests that senescence is a potent prognostic factor during cancer treatment, and therefore rapid and accurate detection of senescent cells in cancer samples is essential. This paper presents a method to visualize and detect therapy-induced senescence (TIS) in cancer cells. Diffuse large B-cell lymphoma (DLBCL) cell lines were treated with mafosfamide (MAF) or daunorubicin (DN) and examined for the senescence marker, senescence-associated &#946;-galactosidase (SA-&#946;-gal), the DNA synthesis marker 5-ethynyl-2&#8242;-deoxyuridine (EdU), and the DNA damage marker gamma-H2AX (&#947;H2AX). Flow cytometer imaging can help generate high-resolution single-cell images in a short period of time to simultaneously visualize and quantify the three markers in cancer cells.

Here we present a flow cytometry-based method for visualization and quantification of multiple senescence-associated markers in single cells.

Chemotherapeutic drugs can induce irreparable DNA damage in cancer cells, leading to apoptosis or premature senescence. Unlike apoptotic cell death, ...

Multiplex Immunofluorescence and Spatial Image Analysis of the Tumor Microenvironment

Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment

The tumor microenvironment (TME) is composed of a plethora of different cell types, such as cytotoxic immune cells and immunomodulatory cells. Depending on its composition and the interactions between cancer cells and peri-tumoral cells, the TME may affect cancer progression. The characterization of tumors and their complex microenvironment could improve the understanding of cancer diseases and may help scientists and clinicians to discover new biomarkers.
We recently developed several multiplex immunofluorescence (mIF) panels based on tyramide signal amplification (TSA) for the characterization of the TME in colorectal cancer, head and neck squamous cell carcinoma, melanoma, and lung cancer. Once the staining and scanning of the corresponding panels are completed, the samples are analyzed on an image analysis software. The spatial position and the staining of each cell are then exported from this quantification software into R. We developed R scripts that allow us not only to analyze the density of each cell type in several tumor compartments (e.g. the center of the tumor, the margin of the tumor, and the stroma) but also to perform distance-based analyses between different cell types.
This particular workflow adds a spatial dimension to the classical density analysis already routinely performed for several markers. mIF analysis could allow scientists to have a better understanding of the complex interaction between cancer cells and the TME and to discover new predictive biomarkers of response to treatments, such as immune checkpoint inhibitors, and targeted therapies.

Author Spotlight: Multiplex Immunofluorescence Combined with Spatial Image Analysis for the Clinical and Biological Assessment of the Tumor Microenvironment  

In this article, a protocol for manual tyramide signal amplification (TSA) multiplex immunofluorescence (mIF) combined with image analysis and spatial analysis is described. This protocol can be used with formalin-fixed paraffin-embedded (FFPE) sections for the staining of two to six antigens per slide depending on the slide scanner available in the laboratory.

The tumor microenvironment (TME) is composed of a plethora of different cell types, such as cytotoxic immune cells and immunomodulatory cells. Depending ...

An Automated Method to Perform The In Vitro Micronucleus Assay using Multispectral Imaging Flow Cytometry

The in vitro micronucleus (MN) assay is often used to evaluate cytotoxicity and genotoxicity but scoring the assay via manual microscopy is laborious and introduces uncertainty in results due to variability between scorers. To remedy this, automated slide-scanning microscopy as well as conventional flow cytometry methods have been introduced in an attempt to remove scorer bias and improve throughput. However, these methods have their own inherent limitations such as inability to visualize the cytoplasm of the cell and the lack of visual MN verification or image data storage with flow cytometry. Multispectral Imaging Flow Cytometry (MIFC) has the potential to overcome these limitations. MIFC combines the high resolution fluorescent imagery of microscopy with the statistical robustness and speed of conventional flow cytometry. In addition, all collected imagery can be stored in dose-specific files. This paper describes the protocol developed to perform a fully automated version of the MN assay on MIFC. Human lymphoblastoid TK6 cells were enlarged using a hypotonic solution (75 mM KCl), fixed with 4% formalin and the nuclear content was stained with Hoechst 33342. All samples were run in suspension on the MIFC, permitting acquisition of high resolution images of all key events required for the assay (e.g. binucleated cells with and without MN as well as mononucleated and polynucleated cells). Images were automatically identified, categorized and enumerated in the MIFC data analysis software, allowing for automated scoring of both cytotoxicity and genotoxicity. Results demonstrate that using MIFC to perform the in vitro MN assay allows statistically significant increases in MN frequency to be detected at several different levels of cytotoxicity when compared to solvent controls following exposure of TK6 cells to Mitomycin C and Colchicine, and that no significant increases in MN frequency are observed following exposure to Mannitol.

The in vitro micronucleus assay is a well-established method for evaluating genotoxicity and cytotoxicity but scoring the assay using manual microscopy is laborious and suffers from subjectivity and inter-scorer variability. This paper describes the protocol developed to perform a fully automated version of the assay using multispectral imaging flow cytometry.

The in vitro micronucleus (MN) assay is often used to evaluate cytotoxicity and genotoxicity but scoring the assay via manual microscopy is laborious and ...

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Quantification of cells is necessary for a wide range of biological and biochemical studies. Conventional image analysis of cells typically employs either fluorescence detection approaches, such as immunofluorescent staining or transfection with fluorescent proteins or edge detection techniques, which are often error-prone due to noise and other non-idealities in the image background. 
We designed a new algorithm that could accurately count and distinguish macrophages and fibroblasts, cells of different phenotypes that often colocalize during tissue regeneration. MATLAB was used to implement the algorithm, which differentiated distinct cell types based on differences in height from the background. A primary algorithm was developed using an area-based method to account for variations in cell size/structure and high-density seeding conditions. 
Non-idealities in cell structures were accounted for with a secondary, iterative algorithm utilizing internal parameters such as cell coverage computed using experimental data for a given cell type. Finally, an analysis of coculture environments was carried out using an isolation algorithm in which various cell types were selectively excluded based on the evaluation of relative height differences within the image. This approach was found to accurately count cells within a 5% error margin for monocultured cells and within a 10% error margin for cocultured cells.

We present a method, which utilizes a generalizable area-based image analysis approach to identify cell counts. Analysis of different cell populations exploited the significant cell height and structure differences between distinct cell types within an adaptive algorithm.

Quantification of cells is necessary for a wide range of biological and biochemical studies. Conventional image analysis of cells typically employs either ...

Artificial Intelligence Approaches to Assessing Primary Cilia

Cilia are microtubule based cellular appendages that function as signaling centers for a diversity of signaling pathways in many mammalian cell types. Cilia length is highly conserved, tightly regulated, and varies between different cell types and tissues and has been implicated in directly impacting their signaling capacity. For example, cilia have been shown to alter their lengths in response to activation of ciliary G protein-coupled receptors. However, accurately and reproducibly measuring the lengths of numerous cilia is a time-consuming and labor-intensive procedure. Current approaches are also error and bias prone. Artificial intelligence (Ai) programs can be utilized to overcome many of these challenges due to capabilities that permit assimilation, manipulation, and optimization of extensive data sets. Here, we demonstrate that an Ai module can be trained to recognize cilia in images from both in vivo and in vitro samples. After using the trained Ai to identify cilia, we are able to design and rapidly utilize applications that analyze hundreds of cilia in a single sample for length, fluorescence intensity and co-localization. This unbiased approach increased our confidence and rigor when comparing samples from different primary neuronal preps in vitro as well as across different brain regions within an animal and between animals. Moreover, this technique can be used to reliably analyze cilia dynamics from any cell type and tissue in a high-throughput manner across multiple samples and treatment groups. Ultimately, Ai-based approaches will likely become standard as most fields move toward less biased and more reproducible approaches for image acquisition and analysis.

The use of artificial intelligence (Ai) to analyze images is emerging as a powerful, less biased, and rapid approach compared with commonly used methods. Here we trained Ai to recognize a cellular organelle, primary cilia, and analyze properties such as length and staining intensity in a rigorous and reproducible manner.

Cilia are microtubule based cellular appendages that function as signaling centers for a diversity of signaling pathways in many mammalian cell types. ...

Biology

Automated Imaging and Analysis for the Quantification of Fluorescently Labeled Macropinosomes

Macropinocytosis is a non-specific fluid-phase uptake pathway that allows cells to internalize large extracellular cargo, such as proteins, pathogens, and cell debris, through bulk endocytosis. This pathway plays an essential role in a variety of cellular processes, including the regulation of immune responses and cancer cell metabolism. Given this importance in biological function, examining cell culture conditions can provide valuable information by identifying regulators of this pathway and optimizing conditions to be employed in the discovery of novel therapeutic approaches. The study describes an automated imaging and analysis technique using standard laboratory equipment and a cell imaging multi-mode plate reader for the rapid quantification of the macropinocytic index in adherent cells. The automated method is based on the uptake of high molecular weight fluorescent dextran and can be applied to 96-well microplates to facilitate assessments of multiple conditions in one experiment or fixed samples mounted onto glass coverslips. This approach is aimed at maximizing reproducibility and reducing experimental variation while being both time-saving and cost-effective.

Automated assays using multi-well microplates are advantageous approaches for identifying pathway regulators by allowing the assessment of a multitude of conditions in a single experiment. Here, we have adapted the well-established macropinosome imaging and quantification protocol to a 96-well microplate format and provide a comprehensive outline for automation using a multi-mode plate reader.

Macropinocytosis is a non-specific fluid-phase uptake pathway that allows cells to internalize large extracellular cargo, such as proteins, pathogens, and ...

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Samenvatting

Meer video's verkennen