Automated spermatogenic staging in periodic acid-Schiff-stained testes of Sprague–Dawley rats using a deep learning model for normal and atrophied tissues

Da-Mi Kim, Jin-Hyung Rho, So-Young Wee, Hwa-Young Son · 2026

Read Automated spermatogenic staging in periodic acid-Schiff-stained testes of Sprague–Dawley rats using a deep learning model for normal and atrophied tissues by Da-Mi Kim, Jin-Hyung Rho, So-Young Wee, Hwa-Young Son (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0337245.txt.

Description

Da-Mi Kim and three colleagues automate a laboratory judgement in reproductive toxicology. Their 2026 study concerns staging sperm production inside rat testes. Experts normally stage tissue by eye under the microscope. That is slow, expert-dependent, and weak at spotting subtle change. The team trained a deep learning model on slide images of stained testicular tissue. Sixteen slides from Sprague-Dawley rats covered normal and shrunken, atrophied tissue.

Fourteen stages were taught to the model. On held-out test slides it detected stages with high precision and recall. On fresh inference slides, its staging agreed with pathologists more than ninety-one percent of the time. Atrophied samples, the real-world hard case, were handled too. An objective staging benchmark lets toxicologists compare stage frequencies between dose groups fairly. Safety studies for new chemicals and drugs could run faster, with less argument about what one expert thought they saw.

Catalog record

CREATORDa-Mi Kim, Jin-Hyung Rho, So-Young Wee, Hwa-Young Son
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE35420
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0337245

Browse the full library · About the Tower of Babel