{"title":"An automatic classification method of testicular histopathology based on SC-YOLO framework.","authors":"Jinggen Wu,Yao Sun,Yangbo Jiang,Yangcheng Bu,Chong Chen,Jingping Li,Lejun Li,Weikang Chen,Keren Cheng,Jian Xu","doi":"10.1080/07366205.2024.2393544","DOIUrl":null,"url":null,"abstract":"The pathological diagnosis and treatment of azoospermia depend on precise identification of spermatogenic cells. Traditional methods are time-consuming and highly subjective due to complexity of Johnsen score, posing challenges for accurately diagnosing azoospermia. Here, we introduce a novel SC-YOLO framework for automating the classification of spermatogenic cells that integrates S3Ghost module, CoordAtt module and DCNv2 module, effectively capturing texture and shape features of spermatogenic cells while reducing model parameters. Furthermore, we propose a simplified Johnsen score criteria to expedite the diagnostic process. Our SC-YOLO framework presents the higher efficiency and accuracy of deep learning technology in spermatogenic cell recognition. Future research endeavors will focus on optimizing the model's performance and exploring its potential for clinical applications.","PeriodicalId":8945,"journal":{"name":"BioTechniques","volume":null,"pages":null},"PeriodicalIF":2.2000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"BioTechniques","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1080/07366205.2024.2393544","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"BIOCHEMICAL RESEARCH METHODS","Score":null,"Total":0}
引用次数: 0
Abstract
The pathological diagnosis and treatment of azoospermia depend on precise identification of spermatogenic cells. Traditional methods are time-consuming and highly subjective due to complexity of Johnsen score, posing challenges for accurately diagnosing azoospermia. Here, we introduce a novel SC-YOLO framework for automating the classification of spermatogenic cells that integrates S3Ghost module, CoordAtt module and DCNv2 module, effectively capturing texture and shape features of spermatogenic cells while reducing model parameters. Furthermore, we propose a simplified Johnsen score criteria to expedite the diagnostic process. Our SC-YOLO framework presents the higher efficiency and accuracy of deep learning technology in spermatogenic cell recognition. Future research endeavors will focus on optimizing the model's performance and exploring its potential for clinical applications.
期刊介绍:
BioTechniques is a peer-reviewed, open-access journal dedicated to publishing original laboratory methods, related technical and software tools, and methods-oriented review articles that are of broad interest to professional life scientists, as well as to scientists from other disciplines (e.g., chemistry, physics, computer science, plant and agricultural science and climate science) interested in life science applications for their technologies.
Since 1983, BioTechniques has been a leading peer-reviewed journal for methods-related research. The journal considers:
Reports describing innovative new methods, platforms and software, substantive modifications to existing methods, or innovative applications of existing methods, techniques & tools to new models or scientific questions
Descriptions of technical tools that facilitate the design or performance of experiments or data analysis, such as software and simple laboratory devices
Surveys of technical approaches related to broad fields of research
Reviews discussing advancements in techniques and methods related to broad fields of research
Letters to the Editor and Expert Opinions highlighting interesting observations or cautionary tales concerning experimental design, methodology or analysis.