论文标题
通过无监督的解剖特征蒸馏改善人类精子头形态分类
Improving Human Sperm Head Morphology Classification with Unsupervised Anatomical Feature Distillation
论文作者
论文摘要
随着男性不育症的增加，精子头形态分类对于准确及时的临床诊断至关重要。最近的深度学习（DL）形态分析方法可以实现有希望的基准结果，但是通过依靠有限的噪声类标签来使表现和稳健性在桌子上留下了稳健性。为了解决这个问题，我们引入了一个新的DL训练框架，该培训框架利用人类精子显微镜作物的解剖学和图像先验来提取有用的功能而无需额外的标签成本。我们的核心思想是用可靠生成的伪面罩和无监督的空间预测任务提炼精子头信息。然后，利用此蒸馏步骤中的预测前景掩膜，以在调整阶段正规化和降低图像和标记噪声。我们在两个公共精子数据集上评估了我们的新方法并实现最先进的表现（例如，SCIAN准确性为65.9％，精度为96.5％）。
With rising male infertility, sperm head morphology classification becomes critical for accurate and timely clinical diagnosis. Recent deep learning (DL) morphology analysis methods achieve promising benchmark results, but leave performance and robustness on the table by relying on limited and possibly noisy class labels. To address this, we introduce a new DL training framework that leverages anatomical and image priors from human sperm microscopy crops to extract useful features without additional labeling cost. Our core idea is to distill sperm head information with reliably-generated pseudo-masks and unsupervised spatial prediction tasks. The predicted foreground masks from this distillation step are then leveraged to regularize and reduce image and label noise in the tuning stage. We evaluate our new approach on two public sperm datasets and achieve state-of-the-art performances (e.g. 65.9% SCIAN accuracy and 96.5% HuSHeM accuracy).
