• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

自动识别不同发育阶段的囊胚区域。

Automated identification of blastocyst regions at different development stages.

机构信息

IVF 2.0 Limited, Merseyside, UK.

New Hope Fertility Center, Mexico City, Mexico.

出版信息

Sci Rep. 2023 Jan 2;13(1):15. doi: 10.1038/s41598-022-26386-6.

DOI:10.1038/s41598-022-26386-6
PMID:36593239
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9807603/
Abstract

The selection of the best single blastocyst for transfer is typically based on the assessment of the morphological characteristics of the zona pellucida (ZP), trophectoderm (TE), blastocoel (BC), and inner cell-mass (ICM), using subjective and observer-dependent grading protocols. We propose the first automatic method for segmenting all morphological structures during the different developmental stages of the blastocyst (i.e., expansion, hatching, and hatched). Our database contains 592 original raw images that were augmented to 2132 for training and 55 for validation. The mean Dice similarity coefficient (DSC) was 0.87 for all pixels, and for the BC, BG (background), ICM, TE, and ZP was 0.85, 0.96, 0.54, 0.63, and 0.71, respectively. Additionally, we tested our method against a public repository of 249 images resulting in accuracies of 0.96 and 0.93 and DSC of 0.67 and 0.67 for ICM and TE, respectively. A sensitivity analysis demonstrated that our method is robust, especially for the BC, BG, TE, and ZP. It is concluded that our approach can automatically segment blastocysts from different laboratory settings and developmental phases of the blastocysts, all within a single pipeline. This approach could increase the knowledge base for embryo selection.

摘要

通常,选择最佳的单个囊胚进行移植是基于对透明带(ZP)、滋养层(TE)、囊胚腔(BC)和内细胞团(ICM)的形态特征进行评估,使用主观和依赖观察者的分级方案。我们提出了第一个自动分割囊胚在不同发育阶段(即扩张、孵化和孵化)的所有形态结构的方法。我们的数据库包含 592 张原始原始图像,经过扩充,用于训练的图像增加到 2132 张,用于验证的图像增加到 55 张。所有像素的平均 Dice 相似系数(DSC)为 0.87,BC、BG(背景)、ICM、TE 和 ZP 的 DSC 分别为 0.85、0.96、0.54、0.63 和 0.71。此外,我们还将我们的方法与 249 张图像的公共存储库进行了测试,结果显示 ICM 和 TE 的准确率分别为 0.96 和 0.93,DSC 分别为 0.67 和 0.67。敏感性分析表明,我们的方法是稳健的,特别是对于 BC、BG、TE 和 ZP。结论是,我们的方法可以自动分割来自不同实验室环境和囊胚发育阶段的囊胚,所有这些都在单个管道中完成。这种方法可以增加胚胎选择的知识库。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/ac2eb0b49b66/41598_2022_26386_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/927912a011a8/41598_2022_26386_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/f61fe6d24625/41598_2022_26386_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/cd6cb01f905b/41598_2022_26386_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/b62cb5eb8df5/41598_2022_26386_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/be678e56dfe1/41598_2022_26386_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/e6949777185f/41598_2022_26386_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/ac2eb0b49b66/41598_2022_26386_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/927912a011a8/41598_2022_26386_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/f61fe6d24625/41598_2022_26386_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/cd6cb01f905b/41598_2022_26386_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/b62cb5eb8df5/41598_2022_26386_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/be678e56dfe1/41598_2022_26386_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/e6949777185f/41598_2022_26386_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/41fc/9807603/ac2eb0b49b66/41598_2022_26386_Fig7_HTML.jpg

相似文献

1
Automated identification of blastocyst regions at different development stages.自动识别不同发育阶段的囊胚区域。
Sci Rep. 2023 Jan 2;13(1):15. doi: 10.1038/s41598-022-26386-6.
2
The bovine embryo hatches from the zona pellucida through either the embryonic or abembryonic pole.牛胚胎通过胚胎极或反胚胎极从透明带中孵化出来。
J Assist Reprod Genet. 2017 Jun;34(6):725-731. doi: 10.1007/s10815-017-0933-3. Epub 2017 May 3.
3
A method for semi-automatic grading of human blastocyst microscope images.一种人类囊胚显微镜图像半自动评分的方法。
Hum Reprod. 2012 Sep;27(9):2641-8. doi: 10.1093/humrep/des219. Epub 2012 Jun 26.
4
Definition and validation of a custom protocol to detect miRNAs in the spent media after blastocyst culture: searching for biomarkers of implantation.定义并验证一种用于检测囊胚培养后废弃培养液中 miRNAs 的定制方案:寻找着床生物标志物。
Hum Reprod. 2019 Sep 29;34(9):1746-1761. doi: 10.1093/humrep/dez119.
5
Failure of complete hatching of ICSI-derived human blastocyst by cell herniation via small slit and insufficient expansion despite ongoing cell proliferation.尽管细胞仍在不断增殖,但通过小裂缝导致的细胞疝出和扩张不足,导致 ICSI 来源的人类囊胚完全孵化失败。
J Assist Reprod Genet. 2019 Aug;36(8):1579-1589. doi: 10.1007/s10815-019-01521-x. Epub 2019 Jul 18.
6
Bovine blastocyst diameter as a morphological tool to predict embryo cell counts, embryo sex, hatching ability and developmental characteristics after transfer to recipients.牛囊胚直径作为一种形态学工具,用于预测胚胎细胞数量、胚胎性别、孵化能力以及移植到受体后的发育特征。
Reprod Fertil Dev. 2006;18(5):551-7. doi: 10.1071/rd05149.
7
Correlation between aneuploidy, standard morphology evaluation and morphokinetic development in 1730 biopsied blastocysts: a consecutive case series study.1730个活检囊胚的非整倍体、标准形态学评估与胚胎发育动力学之间的相关性:一项连续性病例系列研究
Hum Reprod. 2016 Oct;31(10):2245-54. doi: 10.1093/humrep/dew183. Epub 2016 Sep 2.
8
In vivo hatching phenomenon of mouse blastocysts during implantation.小鼠囊胚在着床期间的体内孵化现象。
J Assist Reprod Genet. 2001 Jun;18(6):341-5. doi: 10.1023/a:1016640923269.
9
Morphological development, cell number, and allocation of cells to trophectoderm and inner cell mass of in vitro fertilized and parthenogenetically developed buffalo embryos: the effect of IGF-I.体外受精和孤雌发育的水牛胚胎的形态发育、细胞数量以及细胞向滋养外胚层和内细胞团的分配:胰岛素样生长因子-I的作用
Mol Reprod Dev. 1996 Jul;44(3):343-51. doi: 10.1002/(SICI)1098-2795(199607)44:3<343::AID-MRD8>3.0.CO;2-M.
10
FISH reanalysis of inner cell mass and trophectoderm samples of previously array-CGH screened blastocysts shows high accuracy of diagnosis and no major diagnostic impact of mosaicism at the blastocyst stage.对先前经过 array-CGH 筛选的囊胚的内细胞团和滋养外胚层样本进行 FISH 重新分析,结果显示诊断的准确性很高,囊胚阶段的嵌合体对诊断没有重大影响。
Hum Reprod. 2013 Aug;28(8):2298-307. doi: 10.1093/humrep/det245. Epub 2013 Jun 5.

引用本文的文献

1
Beyond the Inner Cell Mass: Evaluating the Impact of Inner Cell Mass Visibility on Implantation Prediction in Static Blastocyst Images - A Retrospective Cohort Study.超越内细胞团:评估静态囊胚图像中内细胞团可见性对植入预测的影响——一项回顾性队列研究。
J Hum Reprod Sci. 2025 Apr-Jun;18(2):80-88. doi: 10.4103/jhrs.jhrs_63_25. Epub 2025 Jun 28.
2
The role of light in regulating plant growth, development and sugar metabolism: a review.光在调节植物生长、发育和糖代谢中的作用:综述
Front Plant Sci. 2025 Jan 7;15:1507628. doi: 10.3389/fpls.2024.1507628. eCollection 2024.
3
A brief history of artificial intelligence embryo selection: from black-box to glass-box.

本文引用的文献

1
Embryo Ranking Intelligent Classification Algorithm (ERICA): artificial intelligence clinical assistant predicting embryo ploidy and implantation.胚胎分级智能分类算法(ERICA):人工智能临床助手预测胚胎倍性和着床。
Reprod Biomed Online. 2020 Oct;41(4):585-593. doi: 10.1016/j.rbmo.2020.07.003. Epub 2020 Jul 5.
2
Development of an artificial intelligence-based assessment model for prediction of embryo viability using static images captured by optical light microscopy during IVF.开发一种基于人工智能的评估模型,用于通过体外受精期间光学显微镜拍摄的静态图像预测胚胎活力。
Hum Reprod. 2020 Apr 28;35(4):770-784. doi: 10.1093/humrep/deaa013.
3
人工智能胚胎选择的简史:从黑箱到玻璃箱。
Hum Reprod. 2024 Feb 1;39(2):285-292. doi: 10.1093/humrep/dead254.
4
An artificial intelligence algorithm for automated blastocyst morphometric parameters demonstrates a positive association with implantation potential.一种用于自动胚胎形态参数分析的人工智能算法显示与着床潜能呈正相关。
Sci Rep. 2023 Sep 5;13(1):14617. doi: 10.1038/s41598-023-40923-x.
Consistency and objectivity of automated embryo assessments using deep neural networks.
使用深度神经网络进行胚胎自动评估的一致性和客观性。
Fertil Steril. 2020 Apr;113(4):781-787.e1. doi: 10.1016/j.fertnstert.2019.12.004.
4
Predicting pregnancy test results after embryo transfer by image feature extraction and analysis using machine learning.利用机器学习进行图像特征提取和分析,预测胚胎移植后的妊娠试验结果。
Sci Rep. 2020 Mar 10;10(1):4394. doi: 10.1038/s41598-020-61357-9.
5
Trophectoderm segmentation in human embryo images via inceptioned U-Net.通过 inceptioned U-Net 对人类胚胎图像的滋养层分割。
Med Image Anal. 2020 May;62:101612. doi: 10.1016/j.media.2019.101612. Epub 2020 Feb 19.
6
Predicting Human Embryos' Implantation Outcome from a Single Blastocyst Image.从单个囊胚图像预测人类胚胎的着床结果。
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:920-924. doi: 10.1109/EMBC.2019.8857002.
7
Automatic Identification of Human Blastocyst Components via Texture.基于纹理的人类囊胚自动识别。
IEEE Trans Biomed Eng. 2017 Dec;64(12):2968-2978. doi: 10.1109/TBME.2017.2759665. Epub 2017 Oct 5.
8
A Method Based on Artificial Intelligence To Fully Automatize The Evaluation of Bovine Blastocyst Images.一种基于人工智能的方法,可完全实现牛囊胚图像的自动评估。
Sci Rep. 2017 Aug 9;7(1):7659. doi: 10.1038/s41598-017-08104-9.
9
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning.用于计算机辅助检测的深度卷积神经网络:卷积神经网络架构、数据集特征与迁移学习
IEEE Trans Med Imaging. 2016 May;35(5):1285-98. doi: 10.1109/TMI.2016.2528162. Epub 2016 Feb 11.
10
Minimal stimulation IVF vs conventional IVF: a randomized controlled trial.轻度刺激体外受精与传统体外受精:一项随机对照试验。
Am J Obstet Gynecol. 2016 Jan;214(1):96.e1-8. doi: 10.1016/j.ajog.2015.08.009. Epub 2015 Aug 8.