Faculty of Informatics, Multimedia Engineering Department, Kaunas University of Technology, Kaunas, Lithuania.
Faculty of Electrical Engineering, Control Systems Department, Kaunas University of Technology, K. Baršausko St. 59-A338, LT-51423 Kaunas, Lithuania.
Comput Methods Programs Biomed. 2019 Aug;177:161-174. doi: 10.1016/j.cmpb.2019.05.027. Epub 2019 May 29.
Time-lapse microscopy has become an important tool for studying the embryo development process. Embryologists can monitor the entire embryo growth process and thus select the best embryos for fertilization. This time and the resource consuming process are among the key factors for success of pregnancies. Tools for automated evaluation of the embryo quality and development stage prediction are developed for improving embryo selection.
We present two-classifier vote-based method for embryo image classification. Our classification algorithms have been trained with features extracted using a Convolutional Neural Network (CNN). Prediction of embryo development stage is then completed by comparing confidence of two classifiers. Images are labeled depending on which one receives a larger confidence rating.
The evaluation has been done with imagery of real embryos, taken in the ESCO Time Lapse incubator from four different developing embryos. The results illustrate the most effective combination of two classifiers leading to an increase of prediction accuracy and achievement of overall 97.62% accuracy for a test set classification.
We have presented an approach for automated prediction of the embryo development stage for microscopy time-lapse incubator image. Our algorithm has extracted high-complexity image feature using CNN. Classification is done by comparing prediction of two classifiers and selecting the label of that classifier, which has a higher confidence value. This combination of two classifiers has allowed us to increase the overall accuracy of CNN from 96.58% by 1.04% up to 97.62%. The best results are achieved when combining the CNN and Discriminant classifiers. Practical implications include improvement of embryo selection process for in vitro fertilization.
延时显微镜已成为研究胚胎发育过程的重要工具。胚胎学家可以监测整个胚胎的生长过程，从而选择最佳的胚胎进行受精。这个时间和资源消耗的过程是妊娠成功的关键因素之一。开发用于自动评估胚胎质量和预测胚胎发育阶段的工具是为了改善胚胎选择。
我们提出了一种基于两分类器投票的胚胎图像分类方法。我们的分类算法是使用卷积神经网络（CNN）提取的特征进行训练的。然后通过比较两个分类器的置信度来完成胚胎发育阶段的预测。根据哪个分类器获得更大的置信度评分来对图像进行标记。
评估是使用来自四个不同发育胚胎的 ESCO 延时培养箱中的真实胚胎图像进行的。结果说明了两个分类器的最佳组合，从而提高了预测准确性，并实现了 97.62%的测试集分类准确性。
我们提出了一种用于显微镜延时培养箱图像的胚胎发育阶段自动预测的方法。我们的算法使用 CNN 提取了高复杂度的图像特征。分类是通过比较两个分类器的预测并选择置信度值较高的分类器的标签来完成的。这种组合两个分类器的方法使我们能够将 CNN 的整体准确性从 96.58%提高 1.04%至 97.62%。当结合 CNN 和判别分类器时，可获得最佳结果。实际意义包括改进体外受精的胚胎选择过程。
