孕周条件多任务网络用于产科超声胎儿生长分类
本研究基于多中心回顾性产科超声数据,开发并验证孕周条件多任务网络GA-MTNet,同步检测腹部解剖标志并分类五种胎儿生长状况。内部宏AUC为0.863,外部AUC为0.841。结果显示孕周嵌入、多任务学习与持续学习机制可改善孕中晚期超声图像模式识别。
要点
- 该模型可同时检测腹部标志并分类IUGR、GDM、子痫前期、正常生长与羊水异常。
- 外部测试AUC为0.841,显示跨机构泛化能力较好。
- 模型校准良好,ECE为0.047,临床应用相关性评分为3.2/4。
核心结论
- 孕周条件建模可改善孕中晚期产科超声的声像图模式识别与腹部标志检测。
- 持续学习机制使模型在部署后具备进一步安全更新的可能。
研究设计与样本
- 回顾性多中心研究,共纳入2712例孕妇的9046张B型超声图像,孕周18至34周。
- 来自三个中心,A和B中心6750张图像2278例用于5折交叉验证,C中心1296张图像434例作为外部测试集。
- 采用Swin Transformer V1骨干,通过FiLM构建孕周嵌入模块动态调整图像特征。
关键影像表现/征象
- 任务头检测四个腹部解剖标志并分类五种胎儿生长相关声像图模式。
- 可解释性分析采用SHAP与Grad-CAM++,由两名胎儿医学专家盲法评分。
诊断标准与关键数值
- 内部宏AUC为0.863,准确率为84.7%,宏F1为0.821,标志检测mAP@0.5为0.791。
- 外部宏AUC为0.841,准确率为82.3%,F1为0.798,AUC较内部下降2.2个百分点。
- 各类别AUC范围为0.803至0.921。
- 消融研究显示孕周条件、多任务学习与持续学习对性能贡献有统计学意义。
临床应用与阅片要点
- 该框架可用于辅助识别产科超声中与IUGR、GDM、子痫前期、正常生长和羊水异常相关的声像图模式。
- 腹部标志检测可与生长相关分类任务联动,适合嵌入常规产科超声报告流程。
- 临床相关性评分较高,提示结果与胎儿医学专科医生判断有较好符合度。
局限性
- 研究为回顾性设计,图像来源为B型超声单一模态。
- 纳入孕周为18至34周,未覆盖早孕期及34周以后表现。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: This study presents GA-MTNet (Gestational-Age-Conditioned Multi-Task Network), a deep learning framework that integrates gestational age conditioning into a multi-task architecture to simultaneously perform abdominal landmark detection and classify five sonographic patterns linked to fetal growth conditions in prenatal ultrasound.
MATERIALS AND METHODS: A retrospective multi-center dataset of 9,046 B-mode ultrasound images from 2,712 pregnant women (18-34 weeks) was collected across three institutions. Data from Centers A and B (6,750 images, 2,278 patients) were used for model development via patient-stratified 5-fold cross-validation, while Center C (1,296 images, 434 patients) served as an external test set. GA-MTNet employs a Swin Transformer V1 backbone with a Gestational Age Embedding Module based on Feature-wise Linear Modulation (FiLM), enabling dynamic adaptation of image features to fetal developmental stage. Three task heads handle: (1) detection of four abdominal landmarks, (2) five-class classification of fetal growth conditions (IUGR, GDM, pre-eclampsia, normal growth, amniotic fluid abnormalities), and (3) biometric regression. Post-deployment adaptability is supported through uncertainty-guided continual learning combining Monte Carlo Dropout, Elastic Weight Consolidation, and Low-Rank Adaptation. Interpretability was assessed via SHAP and Grad-CAM++, scored by two blinded fetal medicine specialists.
RESULTS: Internally, GA-MTNet achieved a macro-AUC of 0.863, accuracy of 84.7%, macro-F1 of 0.821, and landmark detection mAP@0.5 of 0.791. Externally, performance remained strong (AUC 0.841, accuracy 82.3%, F1 0.798), with only a 2.2-point AUC drop. Per-class AUC ranged from 0.803 to 0.921. Ablation studies confirmed significant contributions from gestational age conditioning (+ 3.1 pp, p = 0.003), multi-task learning (+ 1.0 pp, p = 0.011), and continual learning (+ 1.0 pp, p = 0.014). Calibration was excellent (ECE = 0.047), and clinical relevance scored 3.2/4.
CONCLUSIONS: GA-MTNet demonstrates that gestational age conditioning meaningfully improves sonographic pattern recognition and landmark detection across the second and third trimesters, while its continual learning mechanism enables safe, practical post-deployment model refinement.
引用
- Tong, Gu, Lyu, et al. Abdominal landmark detection and classification of fetal growth conditions on obstetric ultrasound: a gestational age-conditioned multi-task network. Abdom Radiol (NY). 2026. PMID: 42720764. doi:10.1007/s00261-026-05771-z
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。