Scholarlink

<p>Infertility is a global issue, and approximately 50% of cases are due to male factors, with defective spermatogenesis being the main one. For studies of spermatogenesis, evaluating the seminiferous tubule stage is essential. However, current evaluation methods involve labor-intensive manual tasks with a lack of reproducibility owing to the subjective nature of visual evaluation by experts. Here, we propose a deep-learning-based method for automatically and objectively evaluating the seminiferous tubule stage. Our approach predicts which of 12 seminiferous tubule stages is represented in bright-field microscopic images of mouse seminiferous tubules stained by hematoxylin-PAS. The maximum prediction accuracy of our approach was 79.58% which rose to 98.33% with allowance for a prediction error of <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_6727_Article_IEq1.gif" Format="GIF" Height="14" Rendition="HTML" Resolution="72" Type="Linedraw" Width="24" /> </InlineMediaObject> <EquationSource Format="TEX">\(\pm 1\)</EquationSource> </InlineEquation> stage. Remarkably, although the model was not explicitly trained on the stage transition patterns, it inferred the patterns involved in the spermatogenesis. This method not only advances our understanding of spermatogenesis but also holds promise for improving the automated diagnosis of infertility.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep-learning-based automated prediction of mouse seminiferous tubule stage by using bright-field microscopy

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月1日

查看全文
  • Yuta Tokuoka,
  • Tsutomu Endo,
  • Takashi Morikura,
  • Yuki Hiradate,
  • Masahito Ikawa,
  • Akira Funahashi

摘要

Infertility is a global issue, and approximately 50% of cases are due to male factors, with defective spermatogenesis being the main one. For studies of spermatogenesis, evaluating the seminiferous tubule stage is essential. However, current evaluation methods involve labor-intensive manual tasks with a lack of reproducibility owing to the subjective nature of visual evaluation by experts. Here, we propose a deep-learning-based method for automatically and objectively evaluating the seminiferous tubule stage. Our approach predicts which of 12 seminiferous tubule stages is represented in bright-field microscopic images of mouse seminiferous tubules stained by hematoxylin-PAS. The maximum prediction accuracy of our approach was 79.58% which rose to 98.33% with allowance for a prediction error of \(\pm 1\) stage. Remarkably, although the model was not explicitly trained on the stage transition patterns, it inferred the patterns involved in the spermatogenesis. This method not only advances our understanding of spermatogenesis but also holds promise for improving the automated diagnosis of infertility.