Deep Learning–Based Image Analysis Model for Classification and Quantification of Multiple Histopathological Findings in Rat Testis and Epididymis
Toxicologic Pathology · 2026-06 · 54 (4) · 307-320
DOI: 10.1177/01926233261429448 ↗Kurz gefasst
Fachartikel in der Zeitschrift Toxicologic Pathology, online erschienen am 05.04.2026. Verfasst von Taishi Shimazaki und 8 weiteren Autor:innen. Beteiligte Einrichtung: Toxicology Research Laboratories, Shionogi & Co., Ltd., Yokohama, Japan. Hauptthemen laut MEDLINE: Testis, Deep Learning, Epididymis, Image Processing, Computer-Assisted. Die Arbeit nennt 17 Literaturangaben.
Abstract (Originalsprache)
Supervised deep learning–based image analysis models using whole slide images (WSIs) have been reported to be effective for detecting simple histopathological findings in laboratory animals. However, there are no models that simultaneously detect multiple types of abnormal testicular findings on hematoxylin and eosin (H&E)-stained specimens in rats. In this study, we developed a model that can detect, classify, and quantify major 7 testicular toxicity findings in rats (degeneration of germ cell, tubular atrophy, tubular dilatation, vacuolation of Sertoli cell, multinucleated giant cell in the testis, and decreased sperm and cell debris in the epididymis) in addition to classify spermatogenic stages on H&E-stained WSIs. For training the model, we used WSIs of the testis and epididymis of rats that were administered various compounds in toxicity studies, and we developed it using supervised deep learning algorithms and WSI data sets. Detection accuracy of the spermatogenic stage classification and the 7 findings generated by the model was compared with histopathological diagnoses made by board-certified pathologists and confirmed to be high performance. Therefore, this model is a useful tool to support histopathological evaluation, especially in initial screening in rat toxicity studies and is expected to improve work efficiency and prevent errors due to oversights.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Toxicology Research Laboratories, Shionogi & Co., Ltd., Yokohama, Japan.
- AIRA Matrix Private Limited, Dosti Pinnacle, Thane, India.
ORCID-Profile: Taishi Shimazaki, Toshiyuki Shoda
Zitieren
APA
Shimazaki, T., Garg, R., Samanta, P., Mohanty, A., Thomas, T., Muta, K., Yamada, N., Yasui, Y., & Shoda, T. (2026). Deep Learning–Based Image Analysis Model for Classification and Quantification of Multiple Histopathological Findings in Rat Testis and Epididymis. Toxicologic Pathology, 54(4), 307-320. https://doi.org/10.1177/01926233261429448
Vancouver
Shimazaki T, Garg R, Samanta P, Mohanty A, Thomas T, Muta K, et al. Deep Learning–Based Image Analysis Model for Classification and Quantification of Multiple Histopathological Findings in Rat Testis and Epididymis. Toxicologic Pathology. 2026;54(4):307-320. doi:10.1177/01926233261429448
BibTeX
@article{Shimazaki2026,
author = {Shimazaki, Taishi and Garg, Rohit and Samanta, Pranab and Mohanty, Amogh and Thomas, Tijo and Muta, Kyotaka and Yamada, Naohito and Yasui, Yuzo and Shoda, Toshiyuki},
title = {Deep Learning–Based Image Analysis Model for Classification and Quantification of Multiple Histopathological Findings in Rat Testis and Epididymis},
journal = {Toxicologic Pathology},
year = {2026},
volume = {54},
number = {4},
pages = {307--320},
doi = {10.1177/01926233261429448}
}
EUVIMED