[论文解读] Deep learning mediated single time-point image-based prediction of embryo developmental outcome at the cleavage stage

Manoj Kumar Kanakasabapathy, Prudhvi Thirumalaraju+7 more|arXiv (Cornell University)|May 21, 2020

Reproductive Biology and Fertility参考文献 20被引用 11

一句话总结

本研究提出了一种基于深度学习的系统，采用卷积神经网络（CNN）与遗传算法，仅通过单次时间点图像预测卵裂期胚胎的发育潜能。该模型在受精后70小时（hpi）的胚胎图像上进行训练，识别出将发育为优质囊胚的胚胎的准确率达到64%，超过胚胎学家的表现，为IVF诊所提供了一种成本低廉、自动化的解决方案，尤其适用于资源有限的环境。

ABSTRACT

In conventional clinical in-vitro fertilization practices embryos are transferred either at the cleavage or blastocyst stages of development. Cleavage stage transfers, particularly, are beneficial for patients with relatively poor prognosis and at fertility centers in resource-limited settings where there is a higher chance of developmental failure in embryos in-vitro. However, one of the major limitations of embryo selections at the cleavage stage is the availability of very low number of manually discernable features to predict developmental outcomes. Although, time-lapse imaging systems have been proposed as possible solutions, they are cost-prohibitive and require bulky and expensive hardware, and labor-intensive. Advances in convolutional neural networks (CNNs) have been utilized to provide accurate classifications across many medical and non-medical object categories. Here, we report an automated system for classification and selection of human embryos at the cleavage stage using a trained CNN combined with a genetic algorithm. The system selected the cleavage stage embryo at 70 hours post insemination (hpi) that ultimately developed into top-quality blastocyst at 70 hpi with 64% accuracy, outperforming the abilities of embryologists in identifying embryos with the highest developmental potential. Such systems can have a significant impact on IVF procedures by empowering embryologists for accurate and consistent embryo assessment in both resource-poor and resource-rich settings.

研究动机与目标

• 开发一种无需依赖时间-延时成像系统的自动化、低成本方法，用于预测卵裂期胚胎的发育潜能。
• 克服卵裂期胚胎选择中可手动识别的形态学特征数量有限的问题。
• 通过实现准确、一致的胚胎选择，改善IVF结果，适用于资源丰富和资源匮乏的临床环境。
• 利用深度学习与遗传算法从单次时间点胚胎图像中提取预测性特征。

提出的方法

• 在受精后70小时（hpi）的人类胚胎单次时间点明场图像上训练卷积神经网络（CNN）。
• 采用遗传算法优化CNN的超参数，以提升分类性能。
• 该模型被训练为根据胚胎在第5天（120 hpi）发育为优质囊胚的可能性进行分类。
• 图像数据来自临床IVF周期，提取形态学特征并用于训练深度学习模型。
• 通过胚胎学家的临床评估对系统进行验证，以比较预测准确性。

实验结果

研究问题

• RQ1 能否利用单次时间点的卵裂期胚胎图像准确预测其发育为囊胚的潜能？
• RQ2 深度学习模型在卵裂期选择具有最高发育潜能的胚胎方面是否优于人类胚胎学家？
• RQ3 基于CNN的系统是否能在无需时间-延时成像或昂贵硬件的情况下实现高准确率的胚胎选择？
• RQ4 遗传算法在多大程度上可提升CNN在胚胎图像分类中的性能？

主要发现

• 深度学习模型在70 hpi时对将发育为优质囊胚的卵裂期胚胎的分类准确率达到64%。
• 该性能优于经验丰富的胚胎学家在选择最高发育潜能胚胎方面的准确率。
• 该系统可仅使用单次时间点图像实现自动化、基于图像的胚胎选择，无需依赖时间-延时成像系统。
• 由于其低硬件和运行需求，该方法具有可扩展性，适用于资源有限和资源丰富的生育诊所。