通过超声波成像检测血栓和风险评估的深度学习方法:一个范围审查
Maria Didaskalou1, George Ioannakis2, Eleni Kaldoudi3
1School of Medicine, Democritus University of Thrace, Alexandroupoli, Greece.
Ultrasound in medicine & biology
|October 24, 2025
概括
深度学习 (DL) 增强超声波 (US) 以检测血栓,提高静脉,动脉和心脏诊断的准确性. 这次审查强调了DL的重点.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 心血管医学 心血管医学
背景情况:
- 血栓形成,或血栓形成,具有重要的健康风险,如肺栓塞.
- 超声波 (US) 影像是一种关键的诊断工具,但其有效性可能受到操作者依赖的限制.
- 深度学习 (DL) 在美国的血栓形成评估中提供了克服这些局限性的潜力.
研究的目的:
- 审查深度学习 (DL) 技术的应用,以提高使用超声波 (US) 影像的血栓检测和风险评估.
- 探索DL在静脉,动脉和心脏环境中的作用,以诊断血栓症.
- 确定常见的DL模型及其在美国的血栓形成研究中的表现.
主要方法:
- 对PubMed和Scopus的文献进行了全面的范围审查.
- 包括使用DL模型进行血栓检测,分类,细分或风险预测的研究.
- PRISMA-ScR方法指导了文献搜索和选择过程.
主要成果:
- 22项研究符合资格标准,主要使用卷积神经网络 (CNN),U-Net,ResNet和人工神经网络 (ANN).
- DL模型在深静脉血栓症 (DVT) 诊断,动脉斑块细分和心脏血栓分化方面表现有前途.
- 报告了高灵敏度,特异性,准确性和AUC,尽管数据集可变,但经常超过传统方法.
结论:
- 深度学习增强的超声波成像显示出在血栓治疗中改善诊断精度的巨大潜力.
- 在静脉,动脉和心脏血栓的诊断中,DL的应用是有前途的,有助于临床决策.
- 未来的研究应该侧重于模型的解释性,现实世界的整合和标准化数据集.
相关概念视频
Venous Thrombosis II: Clinical Manifestations and Diagnostic Studies
286
The key difference between Superficial Vein Thrombosis (SVT) and Deep Vein Thrombosis (DVT) lies in their location and severity.Clinical ManifestationsSVT typically presents with localized pain, tenderness, and redness along the course of a superficial vein, often accompanied by a palpable, cord-like structure under the skin. This condition is usually less dangerous than DVT but can be uncomfortable and may lead to complications such as cellulitis or, rarely, a clot extension into the deep...
286
Venous Thrombosis III: Interprofessional Care
278
Venous thrombosis requires effective prevention and treatment strategies to improve patient outcomes and reduce potential complications.Prevention StrategiesHealthcare providers must prioritize preventing venous thromboembolism (VTE) for all adult patients upon admission. Interventions depend on bleeding and thrombosis risk, medical history, current medications, diagnoses, planned procedures, and patient preferences. Patients on bed rest should change positions every two hours and, if not...
278


