通过注意力引导深度学习进行可解释的精子形态分类

男性不育是夫妻不育的主要原因, 通常与精子形态异常有关。虽然深度学习模型提供自动化分析,，但大多数缺乏可解释性, 限制了它们的临床采用。本研究提出了一种用于精子形态分类的注意力引导深度学习框架。我们将预训练的 EfficientNet-B0 与卷积块注意力模块 (CBAM) 结合起来，重点关注精子头部, 的关键区域，提高准确性和可解释性。在 SMIDS 和 HuSHem 公共数据集, 上进行评估，我们的模型实现了 90.2% 和 93.9% ( 宏观 F1 分数 0.913 和 0.948), 的准确率，优于 SimpleCNN 和标准 EfficientNet-B0。此外,我们使用Grad-CAM++可视化来突出显示影响模型'决策的特征。结果表明，这种准确、透明的框架是生育诊所自动精子分析的实用工具。

Male infertility is a major cause of couple infertility, often linked to abnormal sperm morphology. While deep learning models offer automated analysis, most lack interpretability, limiting their clinical adoption. This study proposes an attention-guided deep learning framework for sperm morphology classification. We combine a pretrained EfficientNet-B0 with a Convolutional Block Attention Module (CBAM) to focus on key areas of the sperm head, improving both accuracy and interpretability. Evaluated on the SMIDS and HuSHem public datasets, our model achieves accuracies of 90.2% and 93.9% (macro F1 scores of 0.913 and 0.948), outperforming SimpleCNN and standard EfficientNet-B0. Furthermore, we use Grad-CAM++ visualizations to highlight features influencing the model的 decisions. The results demonstrate that this accurate and transparent framework is a practical tool for automated sperm analysis in fertility clinics.

科目:人工智能(cs.AI)

Subjects: Artificial Intelligence (cs.AI)