基于AI框架的经阴道超声子宫内膜厚度精准测量临床应用
本研究基于5110例9850张经阴道超声图像回顾性训练并内部验证AI框架,另前瞻性收集300例356张图像进行外部验证,用于自动测量子宫内膜厚度。模型内部验证MAE为1.05、<±2 mm比例为87.40%;外部验证组AI-D1的MAE为0.89、ICC为0.90、<±2 mm为90.18%,AI测量临床可接受率为74.85%,测量耗时0.2秒。
要点
- AI框架自动测量子宫内膜厚度,外部验证组AI-D1与年长医师ICC达0.90,<±2 mm比例90.18%。
- AI测量临床可接受率74.85%,低于D1的87.37%、略高于D2的72.50%。
- 模型测量耗时0.2秒,比经验较少的超声医师快30倍。
核心结论
- 所提出的AI框架在自动测量子宫内膜厚度方面展现出较高的准确性、效率和临床可接受性,与不同经验水平的超声医师相当,具有较强临床应用潜力。
研究设计与样本
- 回顾性纳入深圳市光明区人民医院2019—2023年5110例9850张超声图像用于训练和内部验证,并前瞻性收集300例356张图像进行外部验证;图像由三名不同经验水平的超声医师(D1-D2-D3,高级-初级-专家)采集和标注;框架包括子宫体分割模型、子宫内膜分割模型和用于测量子宫内膜厚度的最大内切圆搜索算法;性能评估采用平均绝对误差(MAE)、组内相关系数(ICC)和误差在2 mm范围内(<±2 mm)的测量百分比。
诊断标准与关键数值
- 内部验证:MAE为1.05,<±2 mm比例为87.40%。
- 外部验证:AI-D1组MAE为0.89,AI-D2组MAE为1.01。
- 外部验证:AI-D1组ICC为0.90,<±2 mm比例为90.18%。
- AI测量临床可接受率为74.85%,D1为87.37%,D2为72.50%。
- 模型完成测量耗时0.2秒,比经验较少的超声医师快30倍。
临床应用与阅片要点
- AI框架可自动完成子宫内膜厚度测量,外部验证中与年长医师(D1)的一致性ICC为0.90。
- AI测量临床可接受率74.85%,低于D1的87.37%但略高于D2的72.50%。
- 模型测量速度0.2秒,比经验较少的超声医师快30倍。
局限性
- 原文未报告局限性。
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 aims to develop an AI-based framework for automatic endometrial thickness (ET) measurement in transvaginal ultrasound (TVUS) based on a large dataset and evaluate its performance from various clinical perspectives.
METHODS: A dataset of 9850 ultrasound images from 5110 cases at Shenzhen Guangming District People's Hospital (2019-2023) was retrospectively included for training and internal validation. For external validation, 356 images from 300 cases were prospectively collected. All images were acquired and annotated by three sonographers (D1-D2-D3, senior-junior-expert) with varying experience levels. The framework includes a uterine corpus segmentation model, an endometrial segmentation model and a maximum interior tangent circle search algorithm for ET measurement. Model performance was assessed using mean absolute error (MAE), intraclass correlation coefficient (ICC) and percentage of measurements within a 2 mm error range (<±2 mm). Clinical acceptability rate was also evaluated.
RESULTS: The model achieved a MAE of 1.05 and <±2 mm of 87.40% in the internal validation. For external validation, the MAE of groups AI-D1 and AI-D2 were 0.89 and 1.01. The ICC and <±2 mm for group AI-D1 were 0.90 and 90.18%, respectively. The clinical acceptability rate for AI measurements was 74.85%, lower than D1 (87.37%) but slightly higher than D2 (72.50%). The model completed measurements in 0.2 s, 30 times faster than less experienced human sonographers.
CONCLUSION: The proposed AI framework demonstrates strong potential for clinical application in automated ET measurement with high accuracy, efficiency and clinical acceptability, remaining comparable to experienced sonographers across various clinical perspective. To facilitate further research and clinical translation, the source code for the proposed framework has been made publicly available at https://github.com/bing4250/Endo_segmentation.git.
引用
- Wu YB, Ni QY, Chen JQ, et al. Clinical Application of an AI-Driven Framework for Accurate Endometrial Thickness Measurement in Transvaginal Ultrasound. Ultrasound Med Biol. 2025. PMID: 41261003. doi:10.1016/j.ultrasmedbio.2025.08.013
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。