文献速递腹部介入技术与安全US

基于判别相关滤波网络的常规超声不显眼局灶性肝脏病灶实时跟踪初步探索

Preliminary Exploration of Discriminative Correlation Filter Network for Real-time Tracking of Inconspicuous Focal Liver Lesions on Conventional Ultrasound.
PubMed 文献 · Ultrasound Med Biol · 2025-12-24

本研究探索基于判别相关滤波网络(DCFNet)算法通过跟踪周围解剖标志实现常规超声上不显眼局灶性肝脏病灶实时定位的可行性。在20个超声可见体模中,跟踪准确率93.2%、精确率92.9%、平均定位误差0.7±0.4 mm;在20个超声不可见体模中,穿刺成功率94.3%、平均引导时间4(3-5)秒。作者认为该算法可作为定位和跟踪不显眼FLL的潜在方法,初步临床可行性有待进一步大规模验证。

要点

  • 在超声可见肝脏肿瘤体模中,DCFNet算法跟踪准确率达93.2%、精确率92.9%。
  • 在超声可见肝脏肿瘤体模中,平均肿瘤定位误差为0.7±0.4 mm。
  • 在超声不可见肝脏肿瘤体模中,穿刺成功率为94.3%,平均引导时间为4(3-5)秒。

核心结论

  • 基于DCFNet的算法可通过跟踪周围解剖标志实时定位和追踪常规超声上不显眼的局灶性肝脏病灶,具有初步临床可行性,但需进一步大规模验证。

研究设计与样本

  • 初步可行性研究,纳入20个超声可见肝脏肿瘤体模、20个超声不可见肝脏肿瘤体模及初始临床病例,使用基于DCFNet的算法在常规超声上实时跟踪周围解剖标志,以匹配准确率、精确率和定位误差评估算法性能,在超声不可见体模中以穿刺成功率和引导时间评估穿刺验证。

诊断标准与关键数值

  • 超声可见肝脏肿瘤体模中,DCFNet算法跟踪准确率为93.2%、精确率为92.9%。
  • 超声可见肝脏肿瘤体模中,平均肿瘤定位误差为0.7±0.4 mm。
  • 超声不可见肝脏肿瘤体模中,穿刺成功率为94.3%,平均引导时间为4(3-5)秒。

临床应用与阅片要点

  • 作者认为该算法可作为定位和跟踪常规超声上不显眼局灶性肝脏病灶的潜在方法,并可能进一步引导穿刺或消融。
  • 作者指出该算法具有初步临床可行性,但尚需进一步大规模验证。

局限性

  • 原文结论指出该算法的初步临床可行性尚需进一步大规模验证。

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 aimed to explore the feasibility of a discriminative correlation filter network (DCFNet)-based algorithm for positioning inconspicuous focal liver lesions (FLLs) on conventional US by tracking surrounding anatomical landmarks (SALs).

METHODS: We established an algorithm that exploits the relative position characteristics of SALs to achieve tracking of inconspicuous FLLs in real-time US. Multiple SALs were tracked simultaneously using DCFNet, a fast deep learning-based tracking framework. The proposed DCFNet-based algorithm could assist real-time FLLs tracking on US and further guide puncture or ablation. We designed US-visible and US-invisible liver tumor phantoms for tracking and puncture performance evaluation. Algorithm performance was evaluated via matching accuracy, precision and positional error. Puncture verification was assessed in terms of success rate and guidance time on US-invisible liver tumor phantoms.

RESULTS: A total of 20 US-visible phantoms, 20 US-invisible phantoms, and initial clinical cases were included. the algorithm achieved a tracking accuracy of 93.2%, precision of 92.9% and mean tumor localization error of 0.7 ± 0.4 mm in US-visible phantoms. For US-invisible phantoms, the puncture success rate was 94.3% with an average duration of 4 (3-5) s.

CONCLUSION: The DCFNet-based algorithm could be used as a potential approach for locating and tracking inconspicuous FLLs on US, with preliminary clinical feasibility that warrants further large-scale validation.

来源:Ultrasound Med Biol,查看原文。版权归原作者所有。

引用

  1. Yang J, Xu E, Wu S, et al. Preliminary Exploration of Discriminative Correlation Filter Network for Real-time Tracking of Inconspicuous Focal Liver Lesions on Conventional Ultrasound. Ultrasound Med Biol. 2025. PMID: 41448980. doi:10.1016/j.ultrasmedbio.2025.11.663

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。