文献速递生殖医学

人工智能工具通过新鲜成熟卵母细胞的静态图像预测囊胚发育

An artificial intelligence tool predicts blastocyst development from static images of fresh mature oocytes.
PubMed 文献 · Reprod Biomed Online · 2024-01-18

该研究利用来自八个生育诊所(六个国家)的37133张卵母细胞静态图像及实验室结局开发深度学习模型,并在7807张测试集及两个诊所12357张外部数据上验证。测试集AUC为0.64,外部验证AUC为0.63,模型评分与囊胚发育及优质囊胚形成可能性相关。

要点

  • 深度学习模型基于卵母细胞静态图像预测囊胚发育,测试集AUC为0.64。
  • 外部验证AUC为0.63,显示模型具有一定泛化性。
  • 模型转换评分越高,与囊胚发育及优质囊胚形成可能性越高相关。

核心结论

  • 深度学习模型在评估卵母细胞发育为囊胚的能力方面表现出良好性能,预测转换评分与囊胚质量相关,是卵母细胞评估应用于科学与临床的重要第一步。

研究设计与样本

  • 利用来自八个生育诊所(六个国家)的37133张卵母细胞静态图像及实验室结局开发深度学习模型,其中7807张用于测试模型性能。
  • 使用来自两个生育诊所(两个国家)的12357张新数据进行外部验证以评估泛化性和稳健性。
  • 通过计算曲线下面积(AUC)、平衡准确度、特异度和敏感度评估性能,并在测试集上按年龄组、男方因素和诊所地理位置进行亚组分析。

主要发现

  • 测试集上模型AUC为0.64,平衡准确度为0.60,特异度为0.55,敏感度为0.65。
  • 亚组分析显示年龄组38-39岁性能最高(AUC 0.68),男方因素影响可忽略,模型在不同地理位置间泛化性良好。
  • 外部数据验证确认模型性能:AUC为0.63,平衡准确度为0.58,特异度为0.57,敏感度为0.59。
  • 评分量表分析显示,评分越高的卵母细胞与囊胚发育及优质囊胚形成的可能性越高相关。

关键数值与推荐

  • 测试集AUC 0.64,平衡准确度0.60,特异度0.55,敏感度0.65。
  • 外部验证AUC 0.63,平衡准确度0.58,特异度0.57,敏感度0.59。
  • 年龄组38-39岁亚组AUC 0.68。

临床怎么用

  • 原文未据此给出推荐。

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

RESEARCH QUESTION: Can a deep learning image analysis model be developed to assess oocyte quality by predicting blastocyst development from images of denuded mature oocytes? DESIGN: A deep learning model was developed utilizing 37,133 static oocyte images with associated laboratory outcomes from eight fertility clinics (six countries). A subset of data (n = 7807) was allocated to test model performance. External model validation was conducted to assess generalizability and robustness on new data (n = 12,357) from two fertility clinics (two countries). Performance was assessed by calculating area under the curve (AUC), balanced accuracy, specificity and sensitivity. Subgroup analyses were performed on the test dataset for age group, male factor and geographical location of the clinic. Model probabilities of the external dataset were converted to a 0-10 scoring scale to facilitate analysis of correlation with blastocyst development and quality. RESULTS: The deep learning model demonstrated AUC of 0.64, balanced accuracy of 0.60, specificity of 0.55 and sensitivity of 0.65 on the test dataset. Subgroup analyses displayed the highest performance for age group 38-39 years (AUC 0.68), a negligible impact of male factor, and good model generalizability across geographical locations. Model performance was confirmed on external data: AUC of 0.63, balanced accuracy of 0.58, specificity of 0.57 and sensitivity of 0.59. Analysis of the scoring scale revealed that higher scoring oocytes correlated with higher likelihood of blastocyst development and good-quality blastocyst formation. CONCLUSION: The deep learning model showed a favourable performance for the evaluation of oocytes in terms of competence to develop into a blastocyst, and when the predictions were converted into scores, they correlated with blastocyst quality. This represents a significant first step in oocyte evaluation for scientific and clinical applications.

来源:Reprod Biomed Online,查看原文。版权归原作者所有。

引用

  1. Fjeldstad J, Qi W, Mercuri N, et al. An artificial intelligence tool predicts blastocyst development from static images of fresh mature oocytes. Reprod Biomed Online. 2024. PMID: 38552566. doi:10.1016/j.rbmo.2024.103842

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。