Lu Haoda, Zang Min, Marini Gabriel Pik Liang, Wang Xiangxue, Jiao Yiping, Ao Nianfei, Ong Kokhaur, Huo Xinmi, Li Longjie, Xu Eugene Yujun, Goh Wilson Wen Bin, Yu Weimiao, Xu Jun
Institute for AI in Medicine, School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing 210044, China.
Bioinformatics Institute, A*STAR, Singapore 138673, Singapore.
Bioinformatics. 2022 Nov 30;38(23):5307-5314. doi: 10.1093/bioinformatics/btac677.
Differentiating 12 stages of the mouse seminiferous epithelial cycle is vital towards understanding the dynamic spermatogenesis process. However, it is challenging since two adjacent spermatogenic stages are morphologically similar. Distinguishing Stages I-III from Stages IV-V is important for histologists to understand sperm development in wildtype mice and spermatogenic defects in infertile mice. To achieve this, we propose a novel pipeline for computerized spermatogenesis staging (CSS).
The CSS pipeline comprises four parts: (i) A seminiferous tubule segmentation model is developed to extract every single tubule; (ii) A multi-scale learning (MSL) model is developed to integrate local and global information of a seminiferous tubule to distinguish Stages I-V from Stages VI-XII; (iii) a multi-task learning (MTL) model is developed to segment the multiple testicular cells for Stages I-V without an exhaustive requirement for manual annotation; (iv) A set of 204D image-derived features is developed to discriminate Stages I-III from Stages IV-V by capturing cell-level and image-level representation. Experimental results suggest that the proposed MSL and MTL models outperform classic single-scale and single-task models when manual annotation is limited. In addition, the proposed image-derived features are discriminative between Stages I-III and Stages IV-V. In conclusion, the CSS pipeline can not only provide histologists with a solution to facilitate quantitative analysis for spermatogenesis stage identification but also help them to uncover novel computerized image-derived biomarkers.
https://github.com/jydada/CSS.
Supplementary data are available at Bioinformatics online.
区分小鼠生精上皮周期的12个阶段对于理解动态精子发生过程至关重要。然而，这具有挑战性，因为两个相邻的生精阶段在形态上相似。区分I-III期与IV-V期对于组织学家了解野生型小鼠的精子发育和不育小鼠的生精缺陷很重要。为了实现这一点，我们提出了一种用于计算机化精子发生分期（CSS）的新颖流程。
CSS流程包括四个部分：（i）开发了一种生精小管分割模型以提取每一个小管；（ii）开发了一种多尺度学习（MSL）模型以整合生精小管的局部和全局信息，从而区分I-V期与VI-XII期；（iii）开发了一种多任务学习（MTL）模型，用于分割I-V期的多个睾丸细胞，而无需详尽的手动注释；（iv）通过捕获细胞水平和图像水平的表征，开发了一组204D图像衍生特征，以区分I-III期与IV-V期。实验结果表明，在手动注释有限的情况下，所提出的MSL和MTL模型优于经典的单尺度和单任务模型。此外，所提出的图像衍生特征在I-III期和IV-V期之间具有区分性。总之，CSS流程不仅可以为组织学家提供一种便于对精子发生阶段进行定量分析的解决方案，还可以帮助他们发现新的计算机化图像衍生生物标志物。
https://github.com/jydada/CSS。
补充数据可在《生物信息学》在线获取。
