Automated Measurements of Key Morphological Features of Human Embryos for IVF.
Automated Measurements of Key Morphological Features of Human Embryos for IVF.
复制标题
DOI：
10.1007/978-3-030-59722-1_3
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Needleman D
中科院分区：
文献类型：
--
作者：
Leahy BD;Jang WD;Yang HY;Struyven R;Wei D;Sun Z;Lee KR;Royston C;Cam L;Kalma Y;Azem F;Ben-Yosef D;Pfister H;Needleman D
临床体外受精（IVF）的一个主要挑战是选择最高质量的胚胎移植给患者以期实现怀孕。延时显微镜为临床医生提供了选择胚胎的丰富信息。然而，目前所得到的胚胎视频是手动分析的，这既耗时又主观。在这里，我们通过五个卷积神经网络 (CNN) 的机器学习管道自动提取人类胚胎延时显微镜的特征。我们的流程包括（1）胚胎区域的语义分割，（2）片段严重性的回归预测，（3）发育阶段的分类，以及（4）细胞和（5）原核的对象实例分割。我们的方法极大地加快了定量、生物学相关特征的测量，这可能有助于胚胎选择。
A major challenge in clinical In-Vitro Fertilization (IVF) is selecting the highest quality embryo to transfer to the patient in the hopes of achieving a pregnancy. Time-lapse microscopy provides clinicians with a wealth of information for selecting embryos. However, the resulting movies of embryos are currently analyzed manually, which is time consuming and subjective. Here, we automate feature extraction of time-lapse microscopy of human embryos with a machine-learning pipeline of five convolutional neural networks (CNNs). Our pipeline consists of (1) semantic segmentation of the regions of the embryo, (2) regression predictions of fragment severity, (3) classification of the developmental stage, and object instance segmentation of (4) cells and (5) pronuclei. Our approach greatly speeds up the measurement of quantitative, biologically relevant features that may aid in embryo selection.