利用深度学习框架分析人类胚胎时间延时视频中的细胞质弦
Cytoplasmic Strings Analysis in Human Embryo Time-Lapse Videos using Deep Learning Framework
AI总结：
本文提出首个利用深度学习框架分析人类胚胎细胞质弦的计算方法，通过人机协作标注和两阶段深度学习模型，提升对细长低对比度结构的检测性能。
摘要：
不孕症是全球重大的健康问题，尽管体外受精已改善了治疗结果，但胚胎选择仍然是关键瓶颈。时间延时成像能够实现胚胎发育的连续非侵入式监测，但大多数自动化评估方法仅依赖传统形态动力学特征，忽略了新兴生物标记物。细胞质弦是连接内细胞团和滋养外胚层的细长丝状结构，在扩展的 blastocysts 中已被关联到更快的 blastocyst 形成、更高的 blastocyst 等级和改善的存活率。然而，CS 评估目前依赖于手动视觉检查，这耗费人力、主观性强且严重受检测和细微视觉外观影响。在本工作中，我们提出，据我们所知，第一个用于人类 IVF 胚胎 CS 分析的计算框架。我们首先设计了一个人机协作的标注流程，以从 TLI 视频中整理出生物验证的 CS 数据集，包含 13,568 帧，其中 CS 阳性实例高度稀疏。基于此数据集，我们提出了一个两阶段深度学习框架，其 (i) 在帧级别分类 CS 的存在情况，并 (ii) 在阳性案例中定位 CS 区域。为解决严重的不平衡和特征不确定性，我们引入了新颖的不确定性感知压缩嵌入 (NUCE) 损失，该损失将置信度感知再加权与嵌入压缩项相结合，以形成紧凑、良好分离的类别簇。NUCE 在五个 transformer backbones 上一致地提高了 F1 分数，而基于 RF-DETR 的定位实现了对细长、低对比度 CS 结构的最佳检测性能。源代码将在：https://github.com/HamadYA/CS_Detection 上公开。
英文摘要：
Infertility is a major global health issue, and while in-vitro fertilization has improved treatment outcomes, embryo selection remains a critical bottleneck. Time-lapse imaging enables continuous, non-invasive monitoring of embryo development, yet most automated assessment methods rely solely on conventional morphokinetic features and overlook emerging biomarkers. Cytoplasmic Strings, thin filamentous structures connecting the inner cell mass and trophectoderm in expanded blastocysts, have been associated with faster blastocyst formation, higher blastocyst grades, and improved viability. However, CS assessment currently depends on manual visual inspection, which is labor-intensive, subjective, and severely affected by detection and subtle visual appearance. In this work, we present, to the best of our knowledge, the first computational framework for CS analysis in human IVF embryos. We first design a human-in-the-loop annotation pipeline to curate a biologically validated CS dataset from TLI videos, comprising 13,568 frames with highly sparse CS-positive instances. Building on this dataset, we propose a two-stage deep learning framework that (i) classifies CS presence at the frame level and (ii) localizes CS regions in positive cases. To address severe imbalance and feature uncertainty, we introduce the Novel Uncertainty-aware Contractive Embedding (NUCE) loss, which couples confidence-aware reweighting with an embedding contraction term to form compact, well-separated class clusters. NUCE consistently improves F1-score across five transformer backbones, while RF-DETR-based localization achieves state-of-the-art (SOTA) detection performance for thin, low-contrast CS structures. The source code will be made publicly available at: https://github.com/HamadYA/CS_Detection.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
