Deep Learning–Based Spermatogenic Staging in Tissue Sections of Cynomolgus Macaque Testes

Abstract

The indirect assessment of adverse effects on fertility in cynomolgus monkeys requires that tissue sections of the testis be microscopically evaluated with awareness of the stage of spermatogenesis that a particular cross-section of a seminiferous tubule is in. This difficult and subjective task could very much benefit from automation. Using digital whole slide images (WSIs) from tissue sections of testis, we have developed a deep learning model that can annotate the stage of each tubule with high sensitivity, precision, and accuracy. The model was validated on six WSI using a six-stage spermatogenic classification system. Whole slide images contained an average number of 4938 seminiferous tubule cross-sections. On average, 78% of these tubules were staged with 29% in stage I-IV, 12% in stage V-VI, 4% in stage VII, 19% in stage VIII-IX, 18% in stage X-XI, and 17% in stage XII. The deep learning model supports pathologists in conducting a stage-aware evaluation of the testis. It also allows derivation of a stage-frequency map. The diagnostic value of this stage-frequency map is still unclear, as further data on its variability and relevance need to be generated for testes with spermatogenic disturbances.