Alexandra Keller, McKenna Maus, Emma Keller, Karl Kerns
{"title":"Deep learning classification method for boar sperm morphology analysis","authors":"Alexandra Keller, McKenna Maus, Emma Keller, Karl Kerns","doi":"10.1111/andr.13758","DOIUrl":null,"url":null,"abstract":"BackgroundBoar semen quality emphasizes three major criteria: sperm concentration, motility, and morphology. Methods to analyze concentration and motility quickly and objectively readily exist, but few exist for analyzing morphology outside of subjective manual counting. Other vital factors for fertilization, like acrosome health, lack efficient detection methods due to limitations in detection by the human eye and costly biomarker analysis, which is rarely used in semen diagnostics.ObjectiveTo overcome these challenges, we propose a novel approach integrating deep‐learning technology with high‐throughput image‐based flow cytometry (IBFC) for objective and accurate analysis of both morphology and label‐free acrosome health of thousands of individual spermatozoa at once, as opposed to manually counting on a microscope slide.Materials and methodsImages of 10,000 spermatozoa were captured using an IBFC and manually annotated based on the primary morphological defect or acrosome health status for the training of the convolutional neural network (CNN). The CNN used these images to train and then applied that training to unannotated images to predict the model accuracy.ResultsUsing the CNNs, high F1 scores of 96.73%, 98.55%, and 99.31% for 20x, 40x, and 60x magnifications, respectively, for morphological classification were attained. Additionally, the model demonstrates an F1 score of 99.8% in detecting subtle acrosome health variations at the 60x magnification.Discussion and conclusionsWe have established an integrated approach to rapidly collect and classify morphological defects and acrosome health status, without the use of manual counting or biomarker labeling. Our study underscores the potential of artificial intelligence in semen diagnostics, reducing technician variability, streamlining assays, and facilitating the development of additional label‐free detection methods. This innovative approach addresses the barriers hindering biomarker adoption in semen analysis, offering a promising avenue for enhancing reproductive health assessments.","PeriodicalId":7898,"journal":{"name":"Andrology","volume":"37 1","pages":""},"PeriodicalIF":3.2000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Andrology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/andr.13758","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ANDROLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
BackgroundBoar semen quality emphasizes three major criteria: sperm concentration, motility, and morphology. Methods to analyze concentration and motility quickly and objectively readily exist, but few exist for analyzing morphology outside of subjective manual counting. Other vital factors for fertilization, like acrosome health, lack efficient detection methods due to limitations in detection by the human eye and costly biomarker analysis, which is rarely used in semen diagnostics.ObjectiveTo overcome these challenges, we propose a novel approach integrating deep‐learning technology with high‐throughput image‐based flow cytometry (IBFC) for objective and accurate analysis of both morphology and label‐free acrosome health of thousands of individual spermatozoa at once, as opposed to manually counting on a microscope slide.Materials and methodsImages of 10,000 spermatozoa were captured using an IBFC and manually annotated based on the primary morphological defect or acrosome health status for the training of the convolutional neural network (CNN). The CNN used these images to train and then applied that training to unannotated images to predict the model accuracy.ResultsUsing the CNNs, high F1 scores of 96.73%, 98.55%, and 99.31% for 20x, 40x, and 60x magnifications, respectively, for morphological classification were attained. Additionally, the model demonstrates an F1 score of 99.8% in detecting subtle acrosome health variations at the 60x magnification.Discussion and conclusionsWe have established an integrated approach to rapidly collect and classify morphological defects and acrosome health status, without the use of manual counting or biomarker labeling. Our study underscores the potential of artificial intelligence in semen diagnostics, reducing technician variability, streamlining assays, and facilitating the development of additional label‐free detection methods. This innovative approach addresses the barriers hindering biomarker adoption in semen analysis, offering a promising avenue for enhancing reproductive health assessments.
期刊介绍:
Andrology is the study of the male reproductive system and other male gender related health issues. Andrology deals with basic and clinical aspects of the male reproductive system (gonads, endocrine and accessory organs) in all species, including the diagnosis and treatment of medical problems associated with sexual development, infertility, sexual dysfunction, sex hormone action and other urological problems. In medicine, Andrology as a specialty is a recent development, as it had previously been considered a subspecialty of urology or endocrinology