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

Abstract 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...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuta Tokuoka, Tsutomu Endo, Takashi Morikura, Yuki Hiradate, Masahito Ikawa, Akira Funahashi
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-06727-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334784631767040
author Yuta Tokuoka
Tsutomu Endo
Takashi Morikura
Yuki Hiradate
Masahito Ikawa
Akira Funahashi
author_facet Yuta Tokuoka
Tsutomu Endo
Takashi Morikura
Yuki Hiradate
Masahito Ikawa
Akira Funahashi
author_sort Yuta Tokuoka
collection DOAJ
description Abstract 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.
format Article
id doaj-art-9765bc0da65e4242a6adb1ca45116af3
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-9765bc0da65e4242a6adb1ca45116af32025-08-20T03:45:28ZengNature PortfolioScientific Reports2045-23222025-07-0115111110.1038/s41598-025-06727-xDeep-learning-based automated prediction of mouse seminiferous tubule stage by using bright-field microscopyYuta Tokuoka0Tsutomu Endo1Takashi Morikura2Yuki Hiradate3Masahito Ikawa4Akira Funahashi5Department of Biosciences and Informatics, Keio UniversityCenter for Experimental Animals, Research Facility Cluster, Tokyo Medical and Dental UniversityDepartment of Biosciences and Informatics, Keio UniversityResearch Institute for Microbial Diseases, Osaka UniversityResearch Institute for Microbial Diseases, Osaka UniversityDepartment of Biosciences and Informatics, Keio UniversityAbstract 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.https://doi.org/10.1038/s41598-025-06727-x
spellingShingle Yuta Tokuoka
Tsutomu Endo
Takashi Morikura
Yuki Hiradate
Masahito Ikawa
Akira Funahashi
Deep-learning-based automated prediction of mouse seminiferous tubule stage by using bright-field microscopy
Scientific Reports
title Deep-learning-based automated prediction of mouse seminiferous tubule stage by using bright-field microscopy
title_full Deep-learning-based automated prediction of mouse seminiferous tubule stage by using bright-field microscopy
title_fullStr Deep-learning-based automated prediction of mouse seminiferous tubule stage by using bright-field microscopy
title_full_unstemmed Deep-learning-based automated prediction of mouse seminiferous tubule stage by using bright-field microscopy
title_short Deep-learning-based automated prediction of mouse seminiferous tubule stage by using bright-field microscopy
title_sort deep learning based automated prediction of mouse seminiferous tubule stage by using bright field microscopy
url https://doi.org/10.1038/s41598-025-06727-x
work_keys_str_mv AT yutatokuoka deeplearningbasedautomatedpredictionofmouseseminiferoustubulestagebyusingbrightfieldmicroscopy
AT tsutomuendo deeplearningbasedautomatedpredictionofmouseseminiferoustubulestagebyusingbrightfieldmicroscopy
AT takashimorikura deeplearningbasedautomatedpredictionofmouseseminiferoustubulestagebyusingbrightfieldmicroscopy
AT yukihiradate deeplearningbasedautomatedpredictionofmouseseminiferoustubulestagebyusingbrightfieldmicroscopy
AT masahitoikawa deeplearningbasedautomatedpredictionofmouseseminiferoustubulestagebyusingbrightfieldmicroscopy
AT akirafunahashi deeplearningbasedautomatedpredictionofmouseseminiferoustubulestagebyusingbrightfieldmicroscopy