发表机构
Academy of Advanced Interdisciplinary Studies, Wuhan University; School of Computer Science, Wuhan University; Guangzhou Women and Children’s Medical Center; Institute of Artificial Intelligence, School of Computer Science, Wuhan University（武汉大学高等研究院; 武汉大学计算机学院; 广州市妇女儿童医疗中心; 武汉大学计算机学院人工智能研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对胎儿肢体超声图像的分割与测量难题，构建FLB数据集并提出UniFLM框架，通过多个模块实现精准骨评估，性能优于现有模型。
AI 中文摘要
产前超声检查对评估胎儿肢体发育和检测先天性异常至关重要。然而，现有人工智能模型常因缺乏高质量标注数据和适用于多根长骨的统一框架，而忽略胎儿致死性骨骼发育不良问题。此外，通用分割模型难以应对超声图像中固有的噪声和语义差距。为解决这些挑战，我们构建了胎儿肢体骨骼（FLB）数据集，包含肱骨、股骨、胫腓骨、桡尺骨的高质量标注。此外，我们提出UniFLM，这是一个用于自动跨平面分割和测量的统一框架。UniFLM包含语义感知跳跃连接模块，用于弥合编码器与解码器特征间的语义差距；以及正采样策略，用于自适应过滤噪声并提取必要的语义信息。最后，引入点回归映射模块，以学习临床医生的标注模式，实现精确的骨长度测量。在FLB数据集上开展的大量实验表明，与当前最先进模型相比，所提出的UniFLM在胎儿长骨评估中实现了更优的精度和更强的泛化能力。
英文摘要
Prenatal ultrasound examination is crucial for assessing fetal limb development and detecting congenital anomalies. However, existing artificial intelligence models often overlook fetal lethal skeletal dysplasias due to the lack of high-quality annotated data and a unified framework for multiple long bones. Moreover, generic segmentation models struggle with the inherent noise and semantic gaps in ultrasound images. To address these challenges, we construct the Fetal Limb Bones (FLB) dataset, comprising high-quality annotations for the humerus, femur, tibia-fibula, and radius-ulna. Furthermore, we propose UniFLM (United Segmentation and Measurement on Fetal Limb Ultrasonic Image), a unified framework for automatic cross-plane segmentation and measurement. UniFLM incorporates a Semantic Alignment Skip Connection (SASC) module to bridge the semantic gap between encoder and decoder features, and a Positive Sampling (PoSamp) strategy to filter noise and extract essential semantic information. Finally, a Point Regression Mapping (PRM) module is introduced to learn clinician annotation patterns for precise bone length measurement. Extensive experiments conducted on the FLB dataset and the public FetalP5 benchmark demonstrate that UniFLM achieves competitive performance with consistent generalization across four bone categories and external multi-center data, supported by comprehensive statistical validation including Bland-Altman agreement analysis and bootstrap confidence intervals. The source code is publicly available at https://github.com/chosen1203/UniFLM.
CommentsPublished in Pattern Recognition, 2027
DOI：10.1016/j.patcog.2026.114787
