文献速递生殖医学

用于囊胚期胚胎静态图像排序的人工智能模型的特性分析

Characterization of an artificial intelligence model for ranking static images of blastocyst stage embryos.
PubMed 文献 · Fertil Steril · 2022-01-05

本研究为回顾性研究,纳入美国11家辅助生殖技术中心的5923枚移植囊胚和2614枚未移植非整倍体囊胚的静态图像,评估人工智能模型预测临床妊娠的获益与局限。模型曲线下面积为0.6至0.7,整体及按中心均优于人工形态学评分;模拟研究预测各中心妊娠率可提高5%至12%,但使用低倍立体变焦显微镜的中心未见预测改善。AI评分差值≥0.1与妊娠率改善对应,而<0.1可能无临床意义。

要点

  • AI模型预测临床妊娠的AUC为0.6至0.7,整体及按中心均优于人工形态学评分。
  • 模拟研究预测使用AI较人工评分各中心妊娠率提高5%至12%,但低倍立体变焦显微镜中心未见改善。
  • AI评分差值≥0.1与妊娠率改善对应,<0.1可能无临床意义。

核心结论

  • 本研究展示AI用于囊胚期胚胎排序的潜力,并强调图像质量、偏倚和评分粒度相关的潜在局限。

研究设计与样本

  • 回顾性研究,设置于美国11家辅助生殖技术中心组成的联盟。
  • 纳入5923枚移植囊胚和2614枚未移植非整倍体囊胚的静态图像,无干预措施。

主要发现

  • AI模型预测临床妊娠(胎心)的曲线下面积范围为0.6至0.7,整体及按中心均优于人工形态学评分。
  • 模拟研究预测使用AI较使用倒置显微镜人工评分各中心妊娠率提高5%至12%。
  • 一个使用低倍立体变焦显微镜的中心未显示AI预测改善。
  • 可视化技术和归因算法显示AI模型学到的特征与人工评分系统特征 largely 重叠。
  • 识别并缓解了与显微镜类型和胚胎持握微 pipette 存在相关的两个偏倚来源。

局限性

  • 研究为回顾性设计。
  • 识别了与显微镜类型和胚胎持握微 pipette 存在相关的两个偏倚来源。
  • 存在与图像质量、偏倚和评分粒度相关的潜在局限。

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 perform a series of analyses characterizing an artificial intelligence (AI) model for ranking blastocyst-stage embryos. The primary objective was to evaluate the benefit of the model for predicting clinical pregnancy, whereas the secondary objective was to identify limitations that may impact clinical use. DESIGN: Retrospective study. SETTING: Consortium of 11 assisted reproductive technology centers in the United States. PATIENT(S): Static images of 5,923 transferred blastocysts and 2,614 nontransferred aneuploid blastocysts. INTERVENTION(S): None. MAIN OUTCOME MEASURE(S): Prediction of clinical pregnancy (fetal heartbeat). RESULT(S): The area under the curve of the AI model ranged from 0.6 to 0.7 and outperformed manual morphology grading overall and on a per-site basis. A bootstrapped study predicted improved pregnancy rates between +5% and +12% per site using AI compared with manual grading using an inverted microscope. One site that used a low-magnification stereo zoom microscope did not show predicted improvement with the AI. Visualization techniques and attribution algorithms revealed that the features learned by the AI model largely overlap with the features of manual grading systems. Two sources of bias relating to the type of microscope and presence of embryo holding micropipettes were identified and mitigated. The analysis of AI scores in relation to pregnancy rates showed that score differences of ≥0.1 (10%) correspond with improved pregnancy rates, whereas score differences of <0.1 may not be clinically meaningful. CONCLUSION(S): This study demonstrates the potential of AI for ranking blastocyst stage embryos and highlights potential limitations related to image quality, bias, and granularity of scores.

来源:Fertil Steril,查看原文。版权归原作者所有。

引用

  1. Loewke K, Cho JH, Brumar CD, et al. Characterization of an artificial intelligence model for ranking static images of blastocyst stage embryos. Fertil Steril. 2022. PMID: 34998577. doi:10.1016/j.fertnstert.2021.11.022

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。