文献速递神经技术与安全USMR

基于超声信号引导的两阶段弱监督网络用于裸鼠模型术中胶质瘤定位与浸润边界识别

An Ultrasound Signal-Guided Two-Stage Weakly Supervised Network for Intraoperative Glioma Localization and Infiltration Boundary Recognition Using a Nude Mouse Model.
PubMed 文献 · Ultrasound Med Biol · 2025-07-07

研究提出一种超声信号引导的两阶段时空特征弱监督网络,以裸鼠病理标注为参考标准,在3400帧术中超声上训练、680帧测试。肿瘤/正常帧判别准确率0.985、AUC 0.990、敏感度1.000、特异度0.975;边界识别Dice 0.814、IoU 0.690、Hausdorff距离25.088、平均表面距离8.359,定位与边界和病理金标准接近并优于术前MRI。

要点

  • 肿瘤/正常帧判别准确率0.985、AUC 0.990、敏感度1.000、特异度0.975。
  • 边界识别Dice 0.814、IoU 0.690,与组织病理学参考标准比较。
  • 方法定位与边界和病理金标准接近,原文称优于术前MRI。

核心结论

  • 该方法实现了准确的肿瘤定位及浸润边界与肿瘤大小识别,与病理金标准接近,原文称优于术前MRI,为术中超声辅助肿瘤定位提供可靠方案并为临床验证奠定基础。

研究设计与样本

  • 研究论文,提出超声信号引导的两阶段时空特征感知弱监督网络,以裸鼠病理标注为参考标准;训练集3400帧术中超声(1400肿瘤/2000正常),测试集680帧裸鼠帧(280肿瘤/400正常),采用帧级信号标签。

关键影像表现/征象

  • 第一阶段时空特征提取模块通过多约束学习生成伪边界掩膜,将超声射频信号转化为解剖上合理的边界概率分布。
  • 第二阶段以伪边界掩膜作为动态解剖先验,在端到端架构中建立肿瘤分类与边界细化之间的跨任务强化。

诊断标准与关键数值

  • 肿瘤/正常帧判别:准确率0.985、AUC 0.990、敏感度1.000、特异度0.975。
  • 边界识别(对照组织病理学):Dice系数0.814、交并比0.690、Hausdorff距离25.088、平均表面距离8.359。

临床应用与阅片要点

  • 作者认为该方法为术中超声辅助肿瘤定位提供了可靠方案,并为临床验证奠定基础。
  • 原文指出该方法定位与浸润边界及肿瘤大小与病理金标准接近,并称优于术前MRI。

局限性

  • 原文结论指出该方法为临床验证奠定基础,尚未进行临床验证。
  • 研究基于裸鼠模型,原文未报告人体临床数据。

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: Surgical resection is the standard treatment for glioma. While gross tumor regions can be identified, microscopic infiltration is often elusive without histopathology. Developing real-time techniques to approximate gold-standard boundaries intraoperatively is crucial for surgical accuracy and patient outcomes.

METHODS: We propose a ultrasound signal-guided two-stage spatiotemporal feature-aware weak supervision network for glioma infiltration boundaries, utilizing nude mouse pathological annotations as reference standards. In Stage 1, a spatio-temporal feature extraction module generates pseudo-boundary masks through multi-constraint learning, effectively translating the ultrasound radio frequency signal into anatomically plausible boundary probability distributions. Building upon these masks as dynamic anatomical priors, Stage 2 establishes cross-task reinforcement between tumor classification and boundary refinement in an end-to-end architecture. This cross-task synergy enhances localization accuracy with limited labels, enabling annotation-efficient and real-time intraoperative localization.

RESULTS: Trained on 3400 intraoperative ultrasound frames (1400 tumor/2000 normal) with frame-level signal labels, the model was evaluated on a test set comprising 680 nude mouse frames (280 tumor/400 normal) using pathological annotations. For tumor/normal frame differentiation, the model achieved an accuracy of 0.985, AUC of 0.990, sensitivity of 1.000, and specificity of 0.975. Boundary recognition yielded a Dice coefficient of 0.814, intersection over union of 0.690, Hausdorff distance of 25.088, and average surface distance of 8.359 against histopathology.

CONCLUSION: Our method enabled accurate tumor localization with infiltration boundaries and tumor sizes closely matching the pathological gold standard, outperforming preoperative MRI. This approach offers a reliable solution for intraoperative ultrasound-assisted tumor localization, laying the foundation for clinical validation.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Xie X, Yang Z, Zhao C, et al. An Ultrasound Signal-Guided Two-Stage Weakly Supervised Network for Intraoperative Glioma Localization and Infiltration Boundary Recognition Using a Nude Mouse Model. Ultrasound Med Biol. 2025. PMID: 40628602. doi:10.1016/j.ultrasmedbio.2025.05.026

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。