Advancements in the future of automating micromanipulation techniques in the IVF laboratory using deep convolutional neural networks.
Advancements in the future of automating micromanipulation techniques in the IVF laboratory using deep convolutional neural networks.
复制标题
使用深度卷积神经网络在 IVF 实验室中实现自动化显微操作技术的未来进展。
DOI：
10.1007/s10815-022-02685-9
复制
发表时间：
2023
影响因子：
3.1
通讯作者：
Shafiee,Hadi
中科院分区：
文献类型：
--
作者：
Jiang,VictoriaS;Kartik,Deeksha;Thirumalaraju,Prudhvi;Kandula,Hemanth;Kanakasabapathy,ManojKumar;Souter,Irene;Dimitriadis,Irene;Bormann,CharlesL;Shafiee,Hadi
为了确定深度学习人工智能算法是否可以用于准确识别卵母细胞和卵裂期胚胎图像上的关键形态标志，用于显微操作程序，如胞浆内单精子注射（ICSI）或辅助孵化（AH）。并进行了三次重复测试，以确定用于指导胚胎学家进行显微操作程序的关键形态标志。第一个模型（CNN-ICSI）经过训练（n = 13，992）、验证（n = 1920）和测试（n = 3900），以通过极体识别确定ICSI的最佳位置。第二个模型（CNN-AH）被训练（n = 13，908），已验证（n = 1908），结果CNN-ICSI模型准确地识别了极体和相应的最佳ICSI位置，准确率为98.9（95% CI 98.5 - 99.2%），受试者操作特征（ROC）的微观和宏观曲线下面积（AUC）为1。CNN-AH模型准确地识别了最佳AH位置，准确率为99.41%（95%CI 99.11 - 99.62%），ROC的微观和宏观AUC均为1。这些发现是新颖的，必要的垫脚石，在自动化的显微操作程序。
PurposeTo determine if deep learning artificial intelligence algorithms can be used to accurately identify key morphologic landmarks on oocytes and cleavage stage embryo images for micromanipulation procedures such as intracytoplasmic sperm injection (ICSI) or assisted hatching (AH).MethodsTwo convolutional neural network (CNN) models were trained, validated, and tested over three replicates to identify key morphologic landmarks used to guide embryologists when performing micromanipulation procedures. The first model (CNN-ICSI) was trained (n= 13,992), validated (n= 1920), and tested (n= 3900) to identify the optimal location for ICSI through polar body identification. The second model (CNN-AH) was trained (n= 13,908), validated (n= 1908), and tested (n= 3888) to identify the optimal location for AH on the zona pellucida that maximizes distance from healthy blastomeres.ResultsThe CNN-ICSI model accurately identified the polar body and corresponding optimal ICSI location with 98.9% accuracy (95% CI 98.5–99.2%) with a receiver operator characteristic (ROC) with micro and macro area under the curves (AUC) of 1. The CNN-AH model accurately identified the optimal AH location with 99.41% accuracy (95% CI 99.11–99.62%) with a ROC with micro and macro AUCs of 1.ConclusionDeep CNN models demonstrate powerful potential in accurately identifying key landmarks on oocytes and cleavage stage embryos for micromanipulation. These findings are novel, essential stepping stones in the automation of micromanipulation procedures.