Automated spermatogenic staging in PAS-stained testes of Sprague-Dawley rats using a deep learning model for nomal and atrophied tissues

Abstract

The spermatogenic stage serves as a vital criterion for assessing normal spermatogenesis and is central to evaluating reproductive toxicity. Current manual methods for spermatogenic stage evaluation are time-intensive, require expert knowledge, and are less effective in detecting subtle changes or comparing stage frequencies across samples. To overcome these limitations, this study introduces a method leveraging the object detection models, Region-based Convolutional Neural Networks (R-CNN), for efficient and accurate spermatogenic stage evaluation. 14 stages were identified using Periodic Acid-Schiff (PAS)-stained Sprague-Dawley (SD) rat testicular tissue, and the approach was further applied to atrophied testicular samples as a real-world example. The model achieved a mean average precision of 0.869 and a mean average recall of 0.977 in detecting spermatogenic stages and atrophy. Agreement with pathologist assessments exceeded 91%, providing objective benchmarks for stage evaluation and facilitating the comparison of stage frequencies across multiple samples. In atrophied tissues, the model enabled quantitative grading by analyzing proportional changes in atrophied seminiferous tubules relative to normal tubules. This automated approach reduces the workload of pathologists while delivering rapid and precise assessments of toxicological changes in spermatogenesis. By integrating deep learning models, this study enhances both the accuracy and efficiency of pathological evaluations, offering a transformative tool for reproductive toxicity studies.