{"doi":"10.1371/journal.pone.0263409","title":"Validation of a deep learning-based image analysis system to diagnose subclinical endometritis in dairy cows","abstract":"<jats:p>The assessment of polymorphonuclear leukocyte (PMN) proportions (%) of endometrial samples is the hallmark for subclinical endometritis (SCE) diagnosis. Yet, a non-biased, automated diagnostic method for assessing PMN% in endometrial cytology slides has not been validated so far. We aimed to validate a computer vision software based on deep machine learning to quantify the PMN% in endometrial cytology slides. Uterine cytobrush samples were collected from 116 postpartum Holstein cows. After sampling, each cytobrush was rolled onto three different slides. One slide was stained using Diff-Quick, while a second was stained using Naphthol (golden standard to stain PMN). One single observer evaluated the slides twice at different days under light microscopy. The last slide was stained with a fluorescent dye, and the PMN% were assessed twice by using a fluorescence microscope connected to a smartphone. Fluorescent images were analyzed via the Oculyze Monitoring Uterine Health (MUH) system, which uses a deep learning-based algorithm to identify PMN. Substantial intra-method repeatabilities (via Spearman correlation) were found for Diff-Quick, Naphthol, and Oculyze MUH (r = 0.67 to 0.76). The intra-method agreements (via Kappa value) at ≥1% PMN (κ = 0.44 to 0.47) were lower than at &gt;5 (κ = 0.69 to 0.78) or &gt;10% (κ = 0.67 to 0.85) PMN cut-offs. The inter-method repeatabilities (via Lin’s correlation) were also substantial, and values between Diff-Quick and Oculyze MUH, Naphthol and Diff-Quick, and Naphthol and Oculyze MUH were 0.68, 0.69, and 0.77, respectively. The agreements among evaluation methods at ≥1% PMN were weak (κ = 0.06 to 0.28), while it increased at &gt;5 (κ = 0.48 to 0.81) or &gt;10% (κ = 0.50 to 0.65) PMN cut-offs. To conclude, deep learning-based algorithms in endometrial cytology are reliable and useful for simplifying and reducing the diagnosis bias of SCE in dairy cows.</jats:p>","journal":"PLOS ONE","year":2022,"id":685791,"datarank":0.48283137373023016,"base_score":3.2188758248682006,"endowment":3.2188758248682006,"self_citation_contribution":0.48283137373023016,"citation_network_contribution":0.0,"self_endowment_contribution":0.48283137373023016,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":24,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":12,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1791707,"name":"Hannah-Sophie Braun","orcid":null,"position":1,"is_corresponding":false},{"id":1791708,"name":"Berner Panti","orcid":null,"position":2,"is_corresponding":false},{"id":1791709,"name":"Geert Opsomer","orcid":"0000-0002-6131-1000","position":3,"is_corresponding":false},{"id":1791710,"name":"Osvaldo Bogado Pascottini","orcid":"0000-0002-5305-2133","position":4,"is_corresponding":false},{"id":1247948,"name":"Hafez Sadeghi","orcid":"0000-0003-1409-0118","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Validation of a deep learning-based image analysis system to diagnose subclinical endometritis in dairy cows","abstract":"<jats:p>The assessment of polymorphonuclear leukocyte (PMN) proportions (%) of endometrial samples is the hallmark for subclinical endometritis (SCE) diagnosis. Yet, a non-biased, automated diagnostic method for assessing PMN% in endometrial cytology slides has not been validated so far. We aimed to validate a computer vision software based on deep machine learning to quantify the PMN% in endometrial cytology slides. Uterine cytobrush samples were collected from 116 postpartum Holstein cows. After sampling, each cytobrush was rolled onto three different slides. One slide was stained using Diff-Quick, while a second was stained using Naphthol (golden standard to stain PMN). One single observer evaluated the slides twice at different days under light microscopy. The last slide was stained with a fluorescent dye, and the PMN% were assessed twice by using a fluorescence microscope connected to a smartphone. Fluorescent images were analyzed via the Oculyze Monitoring Uterine Health (MUH) system, which uses a deep learning-based algorithm to identify PMN. Substantial intra-method repeatabilities (via Spearman correlation) were found for Diff-Quick, Naphthol, and Oculyze MUH (r = 0.67 to 0.76). The intra-method agreements (via Kappa value) at ≥1% PMN (κ = 0.44 to 0.47) were lower than at &gt;5 (κ = 0.69 to 0.78) or &gt;10% (κ = 0.67 to 0.85) PMN cut-offs. The inter-method repeatabilities (via Lin’s correlation) were also substantial, and values between Diff-Quick and Oculyze MUH, Naphthol and Diff-Quick, and Naphthol and Oculyze MUH were 0.68, 0.69, and 0.77, respectively. The agreements among evaluation methods at ≥1% PMN were weak (κ = 0.06 to 0.28), while it increased at &gt;5 (κ = 0.48 to 0.81) or &gt;10% (κ = 0.50 to 0.65) PMN cut-offs. To conclude, deep learning-based algorithms in endometrial cytology are reliable and useful for simplifying and reducing the diagnosis bias of SCE in dairy cows.</jats:p>","is_dataset_classified":null,"base_score":3.2188758248682006,"endowment":3.2188758248682006,"datacite_reuse_total":12,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"35089986","pmcid":"PMC8797203","openalex_id":"https://openalex.org/W4210489309","authors":[],"funders":[{"funder_name":"European Regional Development Fund","grant_id":"80176988","title":null},{"funder_name":"Research Fundation Flanders","grant_id":"12Y5220N","title":null}],"total_grants":2,"fwci":5.3477,"citation_percentile":0.95955824,"influential_citations":0,"citation_trend":[{"year":2022,"count":2},{"year":2023,"count":1},{"year":2024,"count":14},{"year":2025,"count":5},{"year":2026,"count":2}],"oa_status":"gold","license":"cc-by","oa_locations":[{"url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0263409&type=printable","host_type":"journal"},{"url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0263409&type=printable","host_type":"publisher"},{"url":"https://dx.plos.org/10.1371/journal.pone.0263409","host_type":"publisher"},{"url":"https://doi.org/10.1371/journal.pone.0263409","host_type":"journal"},{"url":"https://pubmed.ncbi.nlm.nih.gov/35089986","host_type":"repository"},{"url":"https://biblio.ugent.be/publication/8749649","host_type":"repository"},{"url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8797203","host_type":"repository"},{"url":"https://hdl.handle.net/10067/1872650151162165141","host_type":"repository"},{"url":"https://doaj.org/article/18cfe06f38dd40a6be6e1aae007c2682","host_type":"repository"},{"url":"https://biblio.ugent.be/publication/8749649/file/8749650.pdf","host_type":"repository"},{"url":"https://europepmc.org/articles/PMC8797203","host_type":"Europe_PMC"},{"url":"https://europepmc.org/articles/PMC8797203?pdf=render","host_type":"Europe_PMC"}],"fields_of_study":["Reproductive Physiology in Livestock","Genetic and phenotypic traits in livestock","Effects of Environmental Stressors on Livestock","Animals","Cattle","Dairying","Deep Learning","Endometritis","Endometrium","Female","Image Processing, Computer-Assisted","Leukocytes, Mononuclear","Reproducibility of Results"],"mesh_terms":["Deep Learning","Animals","Cattle","Dairying","Endometritis","Endometrium","Female","Image Processing, Computer-Assisted","Leukocytes, Mononuclear","Reproducibility of Results"],"keywords":["Endometritis","Subclinical infection","Medicine","Pathology","Biology","Pregnancy"],"sdg_mappings":[],"linked_datasets":[{"doi":"10.6084/m9.figshare.25150585","title":"Additional file 1 of Comparison of Sysmex XN-V body fluid mode and deep-learning-based quantification with manual techniques for total nucleated cell count and differential count for equine bronchoalveolar lavage samples","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.25150585.v1","title":"Additional file 1 of Comparison of Sysmex XN-V body fluid mode and deep-learning-based quantification with manual techniques for total nucleated cell count and differential count for equine bronchoalveolar lavage samples","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26676914.v1","title":"Additional file 3 of Comparison of Sysmex XN-V body fluid mode and deep-learning-based quantification with manual techniques for total nucleated cell count and differential count for equine bronchoalveolar lavage samples","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26676914","title":"Additional file 3 of Comparison of Sysmex XN-V body fluid mode and deep-learning-based quantification with manual techniques for total nucleated cell count and differential count for equine bronchoalveolar lavage samples","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26676917.v1","title":"Additional file 4 of Comparison of Sysmex XN-V body fluid mode and deep-learning-based quantification with manual techniques for total nucleated cell count and differential count for equine bronchoalveolar lavage samples","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26676917","title":"Additional file 4 of Comparison of Sysmex XN-V body fluid mode and deep-learning-based quantification with manual techniques for total nucleated cell count and differential count for equine bronchoalveolar lavage samples","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26676920.v1","title":"Additional file 5 of Comparison of Sysmex XN-V body fluid mode and deep-learning-based quantification with manual techniques for total nucleated cell count and differential count for equine bronchoalveolar lavage samples","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26676923.v1","title":"Additional file 6 of Comparison of Sysmex XN-V body fluid mode and deep-learning-based quantification with manual techniques for total nucleated cell count and differential count for equine bronchoalveolar lavage samples","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26676920","title":"Additional file 5 of Comparison of Sysmex XN-V body fluid mode and deep-learning-based quantification with manual techniques for total nucleated cell count and differential count for equine bronchoalveolar lavage samples","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.26676923","title":"Additional file 6 of Comparison of Sysmex XN-V body fluid mode and deep-learning-based quantification with manual techniques for total nucleated cell count and differential count for equine bronchoalveolar lavage samples","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.25150674.v1","title":"Additional file 2 of Comparison of Sysmex XN-V body fluid mode and deep-learning-based quantification with manual techniques for total nucleated cell count and differential count for equine bronchoalveolar lavage samples","publisher":"figshare","resource_type":"Dataset"},{"doi":"10.6084/m9.figshare.25150674","title":"Additional file 2 of Comparison of Sysmex XN-V body fluid mode and deep-learning-based quantification with manual techniques for total nucleated cell count and differential count for equine bronchoalveolar lavage samples","publisher":"figshare","resource_type":"Dataset"}],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-18T17:41:03.819849Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}