相关实验视频
Updated: May 23, 2025

11:13
Using Mouse Oocytes to Assess Human Gene Function During Meiosis I
Published on: April 10, 2018
8.8K
人工智能用于最佳的体外受精形态动力学形态动力学
Emily Frisch1, Anant Jain2, Chanel Fischetti3
1Obstetrics and Gynecology and Women's Health Institute, Cleveland Clinic, Cleveland, OH, United States.
概括
这项研究开发了一种使用深度学习的人工智能模型,以从时间缩短成像视频中分类人类胚胎阶段,实现高精度. 这种人工智能工具可以优化胚胎选择,以改善体外受精结果.
科学领域:
- 生殖医学 生殖医学
- 人工智能的人工智能
- 胚胎学 胚胎学
背景情况:
- 时间间隔成像 (TLI) 提供了对人类胚胎发育的持续监测.
- 精确评估胚胎形态动力学阶段对于成功的体外受精 (IVF) 是至关重要的.
- 手动注释TLI视频是耗时和资源密集的.
研究的目的:
- 开发和评估人工智能 (AI) 模型,使用TLI视频对人类胚胎形态动力学阶段进行自动分类.
- 利用深度学习,特别是EfficientNetB4,用于增强胚胎发育的图像分类.
主要方法:
- 利用公开可用的IVF数据集,包括716对夫妇的704个TLI视频 (240万张图像).
- 使用卷积神经网络 (CNN) 和EfficientNetB4架构进行模型训练.
- 使用精度,特异性,马修斯相关系数和AUC评估模型性能.
主要成果:
- 人工智能模型的整体精度为0.71,灵敏度为0.59和特异性为0.98.
- 证明了高的多类接收器运行特征曲线下面的区域 (AUC) 分数为0.96.
- 该模型有效地从TLI数据中区分和分类人类胚胎阶段.
结论:
- 卷积神经网络模型非常有效地从TLI分类人类胚胎阶段.
- 人工智能提供了一种有前途的方法来选择理想的胚胎发育阶段,超越时间学年龄.
- 人工智能可以优化大规模胚胎成像数据的处理,帮助胚胎学家,提高试管婴儿成功率.
相关概念视频
In Vitro Fertilization
178
In vitro fertilization (IVF) is a form of assisted reproductive technology where an egg is fertilized with sperm in a controlled laboratory environment before transferring the resulting embryo into the uterus. This process is designed to help individuals and couples experiencing difficulties conceiving.
The IVF process begins with ovarian stimulation, during which reproductive endocrinologists prescribe hormonal medications to stimulate the ovaries to produce multiple eggs instead of the single...
The IVF process begins with ovarian stimulation, during which reproductive endocrinologists prescribe hormonal medications to stimulate the ovaries to produce multiple eggs instead of the single...
178
In-vitro Mutagenesis
13.7K
To learn more about the function of a gene, researchers can observe what happens when the gene is inactivated or “knocked out,” by creating genetically engineered knockout animals. Knockout mice have been particularly useful as models for human diseases such as cancer, Parkinson’s disease, and diabetes.
13.7K

