Quantifying co-cultured cell phenotypes in high-throughput using pixel-based classification
Biologists increasingly use co-culture systems in which two or more cell types are grown in cell culture together in order to better model cells’ native microenvironments. Co-cultures are often required for cell survival or proliferation, or to maintain physiological functioning in vitro. Having two...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Elsevier
2017
|
| Online Access: | http://hdl.handle.net/1721.1/110768 https://orcid.org/0000-0003-0590-9937 https://orcid.org/0000-0002-1293-2097 |
| _version_ | 1826213681029971968 |
|---|---|
| author | Logan, David J Shan, Jing Bhatia, Sangeeta N Van Dyk, Anne Carpenter |
| author2 | Massachusetts Institute of Technology. Institute for Medical Engineering & Science |
| author_facet | Massachusetts Institute of Technology. Institute for Medical Engineering & Science Logan, David J Shan, Jing Bhatia, Sangeeta N Van Dyk, Anne Carpenter |
| author_sort | Logan, David J |
| collection | MIT |
| description | Biologists increasingly use co-culture systems in which two or more cell types are grown in cell culture together in order to better model cells’ native microenvironments. Co-cultures are often required for cell survival or proliferation, or to maintain physiological functioning in vitro. Having two cell types co-exist in culture, however, poses several challenges, including difficulties distinguishing the two populations during analysis using automated image analysis algorithms. We previously analyzed co-cultured primary human hepatocytes and mouse fibroblasts in a high-throughput image-based chemical screen, using a combination of segmentation, measurement, and subsequent machine learning to score each cell as hepatocyte or fibroblast. While this approach was successful in counting hepatocytes for primary screening, segmentation of the fibroblast nuclei was less accurate. Here, we present an improved approach that more accurately identifies both cell types. Pixel-based machine learning (using the software ilastik) is used to seed segmentation of each cell type individually (using the software CellProfiler). This streamlined and accurate workflow can be carried out using freely available and open source software. |
| first_indexed | 2024-09-23T15:53:08Z |
| format | Article |
| id | mit-1721.1/110768 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:53:08Z |
| publishDate | 2017 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | mit-1721.1/1107682022-10-02T04:51:01Z Quantifying co-cultured cell phenotypes in high-throughput using pixel-based classification Logan, David J Shan, Jing Bhatia, Sangeeta N Van Dyk, Anne Carpenter Massachusetts Institute of Technology. Institute for Medical Engineering & Science Broad Institute of MIT and Harvard Harvard University--MIT Division of Health Sciences and Technology Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Koch Institute for Integrative Cancer Research at MIT Logan, David J Shan, Jing Bhatia, Sangeeta N Van Dyk, Anne Carpenter Biologists increasingly use co-culture systems in which two or more cell types are grown in cell culture together in order to better model cells’ native microenvironments. Co-cultures are often required for cell survival or proliferation, or to maintain physiological functioning in vitro. Having two cell types co-exist in culture, however, poses several challenges, including difficulties distinguishing the two populations during analysis using automated image analysis algorithms. We previously analyzed co-cultured primary human hepatocytes and mouse fibroblasts in a high-throughput image-based chemical screen, using a combination of segmentation, measurement, and subsequent machine learning to score each cell as hepatocyte or fibroblast. While this approach was successful in counting hepatocytes for primary screening, segmentation of the fibroblast nuclei was less accurate. Here, we present an improved approach that more accurately identifies both cell types. Pixel-based machine learning (using the software ilastik) is used to seed segmentation of each cell type individually (using the software CellProfiler). This streamlined and accurate workflow can be carried out using freely available and open source software. National Science Foundation (U.S.) (NSF CAREER DBI 1148823) National Institutes of Health (U.S.) (NIH UH3 EB017103) 2017-07-18T17:57:26Z 2017-07-18T17:57:26Z 2015-12 2015-12 Article http://purl.org/eprint/type/JournalArticle 1046-2023 1095-9130 http://hdl.handle.net/1721.1/110768 Logan, David J.; Shan, Jing; Bhatia, Sangeeta N. et al.“Quantifying Co-Cultured Cell Phenotypes in High-Throughput Using Pixel-Based Classification.” Methods 96 (March 2016): 6–11 © 2015 Elsevier Inc https://orcid.org/0000-0003-0590-9937 https://orcid.org/0000-0002-1293-2097 en_US http://dx.doi.org/10.1016/j.ymeth.2015.12.002 Methods Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Elsevier PMC |
| spellingShingle | Logan, David J Shan, Jing Bhatia, Sangeeta N Van Dyk, Anne Carpenter Quantifying co-cultured cell phenotypes in high-throughput using pixel-based classification |
| title | Quantifying co-cultured cell phenotypes in high-throughput using pixel-based classification |
| title_full | Quantifying co-cultured cell phenotypes in high-throughput using pixel-based classification |
| title_fullStr | Quantifying co-cultured cell phenotypes in high-throughput using pixel-based classification |
| title_full_unstemmed | Quantifying co-cultured cell phenotypes in high-throughput using pixel-based classification |
| title_short | Quantifying co-cultured cell phenotypes in high-throughput using pixel-based classification |
| title_sort | quantifying co cultured cell phenotypes in high throughput using pixel based classification |
| url | http://hdl.handle.net/1721.1/110768 https://orcid.org/0000-0003-0590-9937 https://orcid.org/0000-0002-1293-2097 |
| work_keys_str_mv | AT logandavidj quantifyingcoculturedcellphenotypesinhighthroughputusingpixelbasedclassification AT shanjing quantifyingcoculturedcellphenotypesinhighthroughputusingpixelbasedclassification AT bhatiasangeetan quantifyingcoculturedcellphenotypesinhighthroughputusingpixelbasedclassification AT vandykannecarpenter quantifyingcoculturedcellphenotypesinhighthroughputusingpixelbasedclassification |