Department of Histology and Embryology, Medical University of Silesia, Faculty of Medical Sciences, 18 Medyków St., 40-752, Katowice, Poland.
Center for Reproductive Medicine Bocian, 26 Akademicka St., 15-267, Białystok, Poland.
Biomed Eng Online. 2021 Apr 23;20(1):40. doi: 10.1186/s12938-021-00864-w.
Infertility is a significant problem of humanity. In vitro fertilisation is one of the most effective and frequently applied ART methods. The effectiveness IVF depends on the assessment and selection of gametes and embryo with the highest developmental potential. The subjective nature of morphological assessment of oocytes and embryos is still one of the main reasons for seeking effective and objective methods for assessing quality in automatic manner. The most promising methods to automatic classification of oocytes and embryos are based on image analysis aided by machine learning techniques. The special attention is paid on deep neural networks that can be used as classifiers solving the problem of automatic assessment of the oocytes/embryos.
This paper deals with semantic segmentation of human oocyte images using deep neural networks in order to develop new version of the predefined neural networks. Deep semantic oocyte segmentation networks can be seen as medically oriented predefined networks understanding the content of the image. The research presented in the paper is focused on the performance comparison of different types of convolutional neural networks for semantic oocyte segmentation. In the case study, the merits and limitations of the selected deep neural networks are analysed.
71 deep neural models were analysed. The best score was obtained for one of the variants of DeepLab-v3-ResNet-18 model, when the training accuracy (Acc) reached about 85% for training patterns and 79% for validation ones. The weighted intersection over union (wIoU) and global accuracy (gAcc) for test patterns were calculated, as well. The obtained values of these quality measures were 0,897 and 0.93, respectively.
The obtained results prove that the proposed approach can be applied to create deep neural models for semantic oocyte segmentation with the high accuracy guaranteeing their usage as the predefined networks in other tasks.
不孕是人类面临的一个重大问题。体外受精是最有效和最常应用的辅助生殖技术（ART）方法之一。IVF 的有效性取决于对具有最高发育潜力的配子和胚胎的评估和选择。卵母细胞和胚胎形态评估的主观性仍然是寻求有效和客观的自动评估质量方法的主要原因之一。自动分类卵母细胞和胚胎最有前途的方法是基于机器辅助的图像分析和机器学习技术。特别关注的是深度神经网络，它可以用作分类器，解决卵母细胞/胚胎自动评估的问题。
本文使用深度神经网络对人类卵母细胞图像进行语义分割，以开发新版本的预定义神经网络。深度语义卵母细胞分割网络可以被视为理解图像内容的面向医学的预定义网络。本文的研究重点是比较不同类型的卷积神经网络在语义卵母细胞分割中的性能。在案例研究中，分析了所选深度神经网络的优缺点。
分析了 71 个深度神经网络模型。对于 DeepLab-v3-ResNet-18 模型的一个变体，当训练准确率（Acc）达到训练模式的 85%左右，验证模式的 79%左右时，获得了最佳分数。还计算了测试模式的加权交并比（wIoU）和全局准确率（gAcc）。这些质量指标的获得值分别为 0.897 和 0.93。
所获得的结果证明，所提出的方法可用于创建具有高准确性的语义卵母细胞分割深度神经网络，保证它们在其他任务中作为预定义网络的使用。
