Kalatehjari Maryam, Ghasemi Younes, Mahmoudiandehkordi Shaghayegh, Afrazeh Fatemeh, Abbasi Hossein, Ghasemi Fariba
Reproductive Sciences and Sexual Health Research Center, Isfahan University of Medical Sciences, Isfahan, Iran.
Tehran Medical Branch, Islamic Azad University, Tehran, Iran.
J Obstet Gynaecol India. 2025 Jun;75(3):227-232. doi: 10.1007/s13224-025-02109-5. Epub 2025 Apr 26.
Embryo quality assessment plays a pivotal role in assisted reproductive technology (ART) for selecting viable embryos for implantation. Accurate evaluation is essential for improving success rates in fertility treatments. Traditional assessment methods rely on subjective visual grading by embryologists, which can lead to inconsistencies. The application of deep learning in this domain offers the potential for objective and reproducible assessments.
This study investigates the use of deep learning models to classify embryo images as good or not good at the day-3 and day-5 stages. A dataset obtained from Hung Vuong Hospital in Ho Chi Minh City was used to train and evaluate four convolutional neural network (CNN) architectures: VGG-19, ResNet-50, InceptionV3, and EfficientNetV2. Performance metrics, including accuracy, precision, and recall, were used to assess model effectiveness.
Among the tested models, EfficientNetV2 demonstrated superior performance, achieving an accuracy of 95.26%, a precision of 96.30%, and a recall of 97.25%. These results indicate that deep learning models, particularly EfficientNetV2, can provide highly accurate and consistent assessments of embryo quality.
The high classification accuracy of EfficientNetV2 underscores its potential as a valuable tool for fertility specialists. By offering objective and consistent evaluations, this approach can enhance fertility treatment efficiency and support prospective parents in their reproductive journey.
胚胎质量评估在辅助生殖技术（ART）中起着关键作用，用于选择可植入的有活力胚胎。准确评估对于提高生育治疗成功率至关重要。传统评估方法依赖胚胎学家的主观视觉分级，这可能导致不一致性。深度学习在该领域的应用为客观且可重复的评估提供了潜力。
本研究调查了使用深度学习模型在第3天和第5天阶段将胚胎图像分类为优质或非优质的情况。从胡志明市洪旺医院获得的数据集用于训练和评估四种卷积神经网络（CNN）架构：VGG - 19、ResNet - 50、InceptionV3和EfficientNetV2。使用包括准确率、精确率和召回率在内的性能指标来评估模型有效性。
在测试的模型中，EfficientNetV2表现出卓越性能，准确率达到95.26%，精确率为96.30%，召回率为97.25%。这些结果表明深度学习模型，尤其是EfficientNetV2，能够对胚胎质量提供高度准确且一致的评估。
EfficientNetV2的高分类准确率突显了其作为生育专家宝贵工具的潜力。通过提供客观且一致的评估，这种方法可以提高生育治疗效率，并在生育过程中为准父母提供支持。
