盆腔超声提肌裂孔分割的MoUNets静态加权集成模型
本研究回顾性纳入186例接受经会阴超声的盆腔器官脱垂女性,构建多个UNet专家模型的静态加权集成MoUNets。在43例测试集中,最佳集成MoUNetsUNet&ACCUNet的DSC为0.9653、JI为0.9333。与UNet相比无统计学差异,但显著优于其他5个单一模型。
要点
- 提肌裂孔超声分割中,标准UNet在单一模型中表现最好。
- MoUNets集成可提升较弱模型的分割性能,对困难病例有价值。
- 最佳集成模型与标准UNet无显著差异,不可替代但可辅助。
核心结论
- MoUNets集成模型可整合不同专家模型的互补优势,显著提升较弱模型的分割性能,尤其在困难病例中具有明确临床价值。
研究设计与样本
- 随机分为训练集106例、验证集37例、测试集43例,采用Dice相似系数和Jaccard指数评价分割性能。
关键影像表现/征象
- 标准UNet在6个常规UNet模型中分割一致性最佳。
- MoUNets集成不同性能相近的专家模型,数值上高于各单一专家模型。
- 最佳集成MoUNetsUNet&ACCUNet取得DSC 0.9653和JI 0.9333。
诊断标准与关键数值
- 最佳集成模型MoUNetsUNet&ACCUNet的DSC为0.9653,JI为0.9333。
- 最佳集成模型与UNet比较无统计学显著差异,p=0.888。
- 最佳集成模型与其他5个单一模型比较均有统计学显著差异,所有p<0.01。
临床应用与阅片要点
- 在提肌裂孔超声图像分割中,标准UNet可作为基线模型。
- MoUNets集成策略可用于提升较弱分割模型的性能,适合困难病例辅助分割。
- 集成模型数值指标高于单一模型,但不应视为在标准UNet基础上产生显著提升。
局限性
- 回顾性单中心研究,样本量186例,测试集仅43例。
- 最佳集成模型与标准UNet比较无统计学显著差异,p=0.888。
英文原文(摘要)· 点击展开
OBJECTIVE: This study aimed to investigate whether a static weighted ensemble of multiple UNet-based expert models (MoUNets) can achieve more accurate segmentation of the levator hiatus in pelvic floor ultrasound images than any single expert model.
METHODS: This retrospective single-center study included women diagnosed with pelvic organ prolapse who underwent transperineal ultrasound examinations between July 2020 and November 2023. The cohort was randomly divided into the training (n = 106), validation (n = 37) and testing (n = 43) cohorts. Model performance was evaluated on the test set using the Dice similarity coefficient (DSC) and Jaccard index (JI) and compared across all competing architectures.
RESULTS: The study included 186 women (median age, 33.5 y [IQR, 30.0-48.8 y]). Comparative experiments on our in-house levator hiatus dataset confirmed that MoUNets is effective. Among the six conventional UNet models, the standard UNet achieved the best segmentation consistency. MoUNets, which combines different expert models of similar performance, showed higher numerical values than individual expert models. The best ensemble, MoUNetsUNet&ACCUNet, yielded a DSC of 0.9653 and a JI of 0.9333. However, paired t-tests revealed no statistically significant difference between the ensemble and the UNet (p = 0.888). In contrast, statistically significant differences were observed between the best ensemble model and each of the other five individual models (all p < 0.01).
CONCLUSION: The ensemble model leverages complementary advantages among different experts to significantly improve the segmentation performance of weaker models, particularly in difficult cases, demonstrating clear clinical value.
引用
- Ultrasound in Medicine and Biology:MoUNets: Static-Weighted Ensemble of UNet-Based Experts for Levator Hiatus Segmentation in Pelvic Floor Ultrasound
- Zhang, Wu, Lou, et al. MoUNets: Static-Weighted Ensemble of UNet-Based Experts for Levator Hiatus Segmentation in Pelvic Floor Ultrasound. Ultrasound Med Biol. 2026. PMID: 42731935. doi:10.1016/j.ultrasmedbio.2026.08.018
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。