提出可解释的胚胎碎片化分级模型，提升准确率与分割质量。
AttnRegDeepLab: A Two-Stage Decoupled Framework for Interpretable Embryo Fragmentation Grading
- 分两阶段解耦训练，用注意力门过滤细胞质噪声
- 分割Dice系数达0.729，避免轮廓完整与评分精度的权衡
- 适合辅助生殖临床医生进行客观、可解释的胚胎评估
评估胚胎碎片化对预测体外受精成功率至关重要，但人工评分易受主观影响，现有AI模型在临床可解释性与分割准确性方面表现不佳。本文提出AttnRegDeepLab，一种多任务学习框架，通过在DeepLabV3+解码器中引入注意力门，有效过滤细胞质噪声并保留清晰轮廓细节；同时设计多尺度回归头与特征注入机制，利用全局评分先验指导分割过程，消除系统性面积估计偏差。基于两阶段解耦训练策略与针对弱标签数据的范围损失函数，有效缓解多任务学习中的梯度冲突。实验表明，该方法在保证高分级精度的同时实现优异分割效果（Dice系数=0.729），克服了传统联合优化下轮廓完整性与评分准确性之间的权衡问题，提供了一种兼具视觉与定量准确性的临床可解释工具。
原文摘要 · Abstract (English)
Assessing embryo fragmentation is crucial for predicting IVF success, yet manual grading is prone to subjectivity, and existing AI models struggle with clinical interpretability and segmentation errors. We propose AttnRegDeepLab, a Multi-Task Learning (MTL) framework designed to solve these challenges. The model enhances a DeepLabV3+ decoder with Attention Gates to filter out cytoplasmic noise and retain sharp contour details. It also introduces a Multi-Scale Regression Head with Feature Injection, guiding the segmentation process with global grading priors to eliminate systematic area estimation errors. Based on a two-stage decoupled training strategy and a range-based loss for weakly labeled data, our method resolves MTL gradient conflicts. AttnRegDeepLab yields high grading precision and excellent segmentation quality (Dice coefficient = 0.729), avoiding the trade-off between contour integrity and grading accuracy seen under standard joint optimization. This provides a reliable, clinically interpretable tool balancing visual and quantitative accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。