文献速递生殖医学

卵裂球计数变异「跳变值」在胚胎人工智能评估中的应用

[Application of the blastomere count variations "skip value" in the embryo AI assessment].
PubMed 文献 · Zhonghua Fu Chan Ke Za Zhi · 2024-01-01

本研究为自主研发AI胚胎评估软件的诊断性试验(临床数据AI再评估),回顾性分析2020年12月至2021年12月重庆医科大学附属妇女儿童医院1226例患者6545个胚胎,其中2869个行囊胚培养。结果显示受精后72小时卵裂球计数总跳变值与胚胎形态学指标及临床结局相关,预测着床能力与传统形态学评估相近,可能是胚胎体外评估及选择的有益补充。

要点

  • 受精后72小时卵裂球计数总跳变值与囊胚形成率、着床率呈负相关(OR=0.97、0.96)。
  • 总跳变值排序预测着床AUC为0.679,传统形态学标准AUC为0.620。
  • 活产与女性年龄、D3胚胎形态学评级及跳变值排序负相关,与获卵数及内膜厚度正相关。

核心结论

  • 跳变值及其排序是对体外胚胎卵裂期发育的系统量化,与胚胎发育质量及临床结局相关,可能是胚胎体外评估及选择的有益补充。

研究设计与样本

  • 本研究为自主研发AI胚胎评估软件的诊断性试验(临床数据AI再评估),为回顾性研究。
  • 收集2020年12月至2021年12月于重庆医科大学附属妇女儿童医院生殖医学中心行IVF的1226例患者共6545个胚胎,其中2869个胚胎进行囊胚培养。

主要发现

  • 受精后72小时卵裂球计数曲线提取的总跳变值与异常卵裂、囊胚形成率、D3胚胎形态学评级、D3胚胎细胞均一度、D3胚胎细胞碎片率均呈显著负相关(β分别为-0.268、-0.116、-0.213、-0.159、-0.222;P均<0.001),与D3胚胎细胞数呈显著正相关(β=0.034;P<0.001)。
  • 多因素logistic回归分析显示,胚胎总跳变值排序与囊胚形成(OR=0.97,95%CI 0.93~0.99;P=0.034)、胚胎着床(OR=0.96,95%CI 0.93~0.98;P=0.044)呈显著负相关。
  • ROC曲线分析显示,胚胎总跳变值排序预测胚胎着床能力的AUC为0.679,传统胚胎形态学评估方法AUC为0.620。
  • 多因素logistic回归分析显示,活产与患者年龄(OR=0.91,95%CI 0.88~0.93;P<0.001)、D3胚胎形态学评级(OR=0.77,95%CI 0.59~0.99;P=0.045)及胚胎总跳变值排序(OR=0.98,95%CI 0.96~0.99;P=0.038)呈显著负相关,而与获卵数(OR=1.08,95%CI 1.05~1.11;P<0.001)及移植日子宫内膜厚度(OR=1.09,95%CI 1.06~1.12;P<0.001)呈显著正相关。
  • ROC曲线分析显示,纳入建模的以上多个因素预测活产的AUC值为0.666。

临床怎么用

  • 原文结论认为跳变值及其排序可能是胚胎体外评估及选择的有益补充参数。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Objective: To explore the correlation between blastomere count variations "skip value" which extracted from by time-lapse technology (TLT) combined with artificial intelligence (AI) and morphological features of in vitro fertilization (IVF) embryo, and to test its feasibility in clinical applications. Methods: This study was a diagnostic experiment (AI reassessment of embryo transferred patients), a total of 6 545 embryos from 1 226 patients who underwent IVF at the Women and Children's Hospital of Chongqing Medical University from December 2020 to December 2021 were retrospectively analyzed, of which 2 869 embryos were attempted to cultured to blastocyst stage by TLT. The embryo dynamic map (EDM) was drawn by Embryo Viewer, a TLT recording software, based on embryo developmental kinetics. The self-developed AI embryo evaluation software identified and recorded the number of cleavages in real time during embryonic development, and compared with the EDM, the correlation between the skip value formed by the change of cleavage sphere counts and the outcomes of the embryos was analyzed. The correlation among skip value, morphological score of embryo, implantation rate and live birth rate were performed by Spearman and step-up logistic regression. The receiver operating characteristic (ROC) curve was selected for reporting there relationship of skip value and morphology. Finally, predicting power of skip value for implantation and live birth rate were performed by ROC analysis. Results: The total skip values extracted from the blastomere count of embryos (72 hours post-fertilization) were negatively correlated with abnormal cleavage, blastocyst formation rate, day 3 (D3)-cell score, uneven size and fragmentation (the β values were -0.268, -0.116, -0.213, -0.159 and -0.222, respectively; all P<0.001); positively correlated with D3-cell number (β=0.034; P<0.001); negatively correlated with blastocyst formation rate and implantation rate (OR=0.97, 95%CI: 0.93-0.99, P=0.034; OR=0.96, 95%CI: 0.93-0.98, P=0.044). The power of predicting implantation were similar between the order selection of skip values and traditional morphology criteria [area under curve (AUC): 0.679 vs 0.620]. Live birth rate were negatively correlated with female age (OR=0.91, 95%CI: 0.88-0.93; P<0.001), D3 general score (OR=0.77, 95%CI: 0.59-0.99; P=0.045) and order selection of skip values (OR=0.98, 95%CI: 0.96-0.99; P=0.038), while positively correlated with retrieved oocyte number and endometrial thickness in embryo transferred (OR=1.08, 95%CI:1.05-1.11, P<0.001; OR=1.09, 95%CI:1.06-0.12, P<0.001, respectively) from multivariate regression analysis, and the power of predicting live birth was 0.666 for AUC. Conclusions: The skip value and its order form is a systematic quantification of embryo development, correlated with embryo developmental quality and clinical outcome. It could be an addition parameter for embryo culture and selection. 目的: 通过胚胎时差成像技术(TLT)结合人工智能(AI)探索体外胚胎发育曲线(EDM)中的卵裂球计数曲线“跳变值”与胚胎形态学特征的相关性,并探讨其在体外受精(IVF)胚胎评估中应用的可行性。 方法: 本研究为自主研发的AI胚胎评估软件的诊断性试验,即临床数据AI再评估,为回顾性研究。收集2020年12月至2021年12月于重庆医科大学附属妇女儿童医院生殖医学中心行IVF的1 226例患者共6 545个胚胎,其中2 869个胚胎进行囊胚培养。所有胚胎通过TLT培养并进行观察,由TLT记录软件Embryo Viewer依据胚胎发育动力学绘制EDM。本课题组自主研发的AI胚胎评估软件对胚胎发育过程中的卵裂球数目进行实时识别、记录,并与EDM进行比较,分析由卵裂球计数变化而形成的跳变值与胚胎结局的相关性。采用Spearman相关性及logistic回归分析跳变值与胚胎形态学评估、胚胎着床及活产的相关性,使用受试者工作特征(ROC)曲线评估各指标对胚胎着床、活产的预测价值。 结果: Spearman相关性分析显示,受精卵受精后72 h卵裂球计数曲线提取的总跳变值与卵裂模式、囊胚形成、培养至第3天胚胎(D3胚胎)的形态学评级、D3胚胎的细胞均一度、D3胚胎的细胞碎片率均呈显著负相关(β值分别为-0.268、-0.116、-0.213、-0.159、-0.222;P均<0.001),与D3胚胎的细胞数呈显著正相关(β=0.034;P<0.001)。多因素logistic回归分析显示,胚胎总跳变值排序与囊胚形成(OR=0.97,95%CI为0.93~0.99;P=0.034)、胚胎着床(OR=0.96,95%CI为0.93~0.98;P=0.044)呈显著负相关;ROC曲线分析显示,胚胎总跳变值排序预测胚胎着床能力与传统胚胎形态学评估方法相近[其曲线下面积(AUC)分别为0.679、0.620]。多因素logistic回归分析显示,活产与患者年龄(OR=0.91,95%CI为0.88~0.93;P<0.001)、D3胚胎形态学评级(OR=0.77,95%CI为0.59~0.99;P=0.045)及胚胎总跳变值排序(OR=0.98,95%CI为0.96~0.99;P=0.038)呈显著负相关,而与获卵数(OR=1.08,95%CI为1.05~1.11;P<0.001)及移植日子宫内膜厚度(OR=1.09,95%CI为1.06~1.12;P<0.001)呈显著正相关;ROC曲线分析显示,纳入建模的以上多个因素预测活产的AUC值为0.666。 结论: 跳变值及其排序是对体外胚胎卵裂期发育的系统量化,其与胚胎发育质量及临床结局相关,可能是胚胎体外评估及选择的有益补充。.

来源:Zhonghua Fu Chan Ke Za Zhi,查看原文。版权归原作者所有。

引用

  1. Yang JW, Han W, Liu WW, et al. [Application of the blastomere count variations "skip value" in the embryo AI assessment]. Zhonghua Fu Chan Ke Za Zhi. 2024. PMID: 39056132. doi:10.3760/cma.j.cn112141-20240108-00023

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。