A machine learning approach toward automating spatial identification of LAG3+/CD3+ cells in ulcerative colitis
Abstract Over the past decade, automation of digital image analysis has become commonplace in both research and clinical settings. Spurred by recent advances in artificial intelligence and machine learning (AI/ML), tissue sub-compartments and cellular phenotypes within those compartments can be iden...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-12-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-49163-5 |
| _version_ | 1797398046307254272 |
|---|---|
| author | Edward D. Bonnevie Eric Dobrzynski Dylan Steiner Deon Hildebrand James Monslow Mohan Singh Vilma Decman David L. Krull |
| author_facet | Edward D. Bonnevie Eric Dobrzynski Dylan Steiner Deon Hildebrand James Monslow Mohan Singh Vilma Decman David L. Krull |
| author_sort | Edward D. Bonnevie |
| collection | DOAJ |
| description | Abstract Over the past decade, automation of digital image analysis has become commonplace in both research and clinical settings. Spurred by recent advances in artificial intelligence and machine learning (AI/ML), tissue sub-compartments and cellular phenotypes within those compartments can be identified with higher throughput and accuracy than ever before. Recently, immune checkpoints have emerged as potential targets for auto-immune diseases. As such, spatial identification of these proteins along with immune cell markers (e.g., CD3+/LAG3+ T-cells) is a crucial step in understanding the potential and/or efficacy of such treatments. Here, we describe a semi-automated imaging and analysis pipeline that identifies CD3+/LAG3+ cells in colorectal tissue sub-compartments. While chromogenic staining has been a clinical mainstay and the resulting brightfield images have been utilized in AI/ML approaches in the past, there are associated drawbacks in phenotyping algorithms that can be overcome by fluorescence imaging. To address these tradeoffs, we developed an analysis pipeline combining the strengths of brightfield and fluorescence images. In this assay, immunofluorescence imaging was conducted to identify phenotypes followed by coverslip removal and hematoxylin and eosin staining of the same section to inform an AI/ML tissue segmentation algorithm. This assay proved to be robust in both tissue segmentation and phenotyping, was compatible with automated workflows, and revealed presence of LAG3+ T-cells in ulcerative colitis biopsies with spatial context preserved. |
| first_indexed | 2024-03-09T01:20:00Z |
| format | Article |
| id | doaj.art-e4d5d37e8b8a44a48b999a78c3bb3162 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-09T01:20:00Z |
| publishDate | 2023-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-e4d5d37e8b8a44a48b999a78c3bb31622023-12-10T12:16:12ZengNature PortfolioScientific Reports2045-23222023-12-0113111210.1038/s41598-023-49163-5A machine learning approach toward automating spatial identification of LAG3+/CD3+ cells in ulcerative colitisEdward D. Bonnevie0Eric Dobrzynski1Dylan Steiner2Deon Hildebrand3James Monslow4Mohan Singh5Vilma Decman6David L. Krull7Cellular Biomarkers, GSKCellular Biomarkers, GSKCellular Biomarkers, GSKNCS-Pathology, GSKCellular Biomarkers, GSKCellular Biomarkers, GSKCellular Biomarkers, GSKCellular Biomarkers, GSKAbstract Over the past decade, automation of digital image analysis has become commonplace in both research and clinical settings. Spurred by recent advances in artificial intelligence and machine learning (AI/ML), tissue sub-compartments and cellular phenotypes within those compartments can be identified with higher throughput and accuracy than ever before. Recently, immune checkpoints have emerged as potential targets for auto-immune diseases. As such, spatial identification of these proteins along with immune cell markers (e.g., CD3+/LAG3+ T-cells) is a crucial step in understanding the potential and/or efficacy of such treatments. Here, we describe a semi-automated imaging and analysis pipeline that identifies CD3+/LAG3+ cells in colorectal tissue sub-compartments. While chromogenic staining has been a clinical mainstay and the resulting brightfield images have been utilized in AI/ML approaches in the past, there are associated drawbacks in phenotyping algorithms that can be overcome by fluorescence imaging. To address these tradeoffs, we developed an analysis pipeline combining the strengths of brightfield and fluorescence images. In this assay, immunofluorescence imaging was conducted to identify phenotypes followed by coverslip removal and hematoxylin and eosin staining of the same section to inform an AI/ML tissue segmentation algorithm. This assay proved to be robust in both tissue segmentation and phenotyping, was compatible with automated workflows, and revealed presence of LAG3+ T-cells in ulcerative colitis biopsies with spatial context preserved.https://doi.org/10.1038/s41598-023-49163-5 |
| spellingShingle | Edward D. Bonnevie Eric Dobrzynski Dylan Steiner Deon Hildebrand James Monslow Mohan Singh Vilma Decman David L. Krull A machine learning approach toward automating spatial identification of LAG3+/CD3+ cells in ulcerative colitis Scientific Reports |
| title | A machine learning approach toward automating spatial identification of LAG3+/CD3+ cells in ulcerative colitis |
| title_full | A machine learning approach toward automating spatial identification of LAG3+/CD3+ cells in ulcerative colitis |
| title_fullStr | A machine learning approach toward automating spatial identification of LAG3+/CD3+ cells in ulcerative colitis |
| title_full_unstemmed | A machine learning approach toward automating spatial identification of LAG3+/CD3+ cells in ulcerative colitis |
| title_short | A machine learning approach toward automating spatial identification of LAG3+/CD3+ cells in ulcerative colitis |
| title_sort | machine learning approach toward automating spatial identification of lag3 cd3 cells in ulcerative colitis |
| url | https://doi.org/10.1038/s41598-023-49163-5 |
| work_keys_str_mv | AT edwarddbonnevie amachinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT ericdobrzynski amachinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT dylansteiner amachinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT deonhildebrand amachinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT jamesmonslow amachinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT mohansingh amachinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT vilmadecman amachinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT davidlkrull amachinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT edwarddbonnevie machinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT ericdobrzynski machinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT dylansteiner machinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT deonhildebrand machinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT jamesmonslow machinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT mohansingh machinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT vilmadecman machinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis AT davidlkrull machinelearningapproachtowardautomatingspatialidentificationoflag3cd3cellsinulcerativecolitis |