基于图像的自动跟踪加多填充气球式导管用于MRI引导的心脏导管,使用深度学习
Alexander Paul Neofytou1, Grzegorz Tomasz Kowalik1, Rohini Vidya Shankar1
1School of Biomedical Engineering and Imaging Sciences, Faculty of Life Sciences and Medicine, King's College London, London, United Kingdom.
Frontiers in cardiovascular medicine
|September 25, 2023
概括
这项研究引入了一种深度学习方法,用于在MRI引导的心脏导管过程中自动检测导管气球. 这种实时跟踪可以改善可视化和导航,提高程序效率.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 心血管干预 心血管干预
背景情况:
- 磁共振成像 (MRI) 与X射线光学相比,在心脏导管治疗中具有优势,包括优越的软组织可视化和缺乏电离辐射.
- 目前的MRI指导程序依赖于导管尖端的手动跟踪,这是耗时和复杂的.
- 自动导管气球检测可以显著改善这些程序期间的导航和可视化.
研究的目的:
- 开发和评估基于深度学习的管道,用于实时,自动检测和跟踪MRI导向心脏导管治疗中的导管气球.
- 评估拟议方法的准确性,特异性,灵敏性和计算效率.
主要方法:
- 用于导管气球细分,采用了带有ResNet-34编码器的U-Net架构.
- 开发了一个无参数的深度学习管道,用于后处理和独特的尖端坐标估计.
- 该方法在7名接受右心导管治疗的患者的MRI数据上进行了回顾性评估,使用在训练期间未见的方向获得的图像.
主要成果:
- 自动导管跟踪实现了高的整体精度 (98.4% ± 2.0%),特异性 (99.9% ± 0.2%),和灵敏度 (95.4% ± 5.5%).
- 深度学习细分步骤证明了实时兼容性,每个图像的计算时间约为10ms.
- 该系统提供了准确的导管尖位置定位,即使在看不见的图像方向.
结论:
- 基于深度学习的导管气球跟踪是一种可行且准确的MRI导向心脏导管技术.
- 开发的方法是无参数的,在实时约束范围内运行,提供了简化程序的潜力.
- 建议在更大的患者队列和在线整合中进行进一步的验证,以确认临床益处.
更多相关视频
11:27Magnetically-Assisted Remote Controlled Microcatheter Tip Deflection under Magnetic Resonance Imaging
Published on: April 4, 2013
12.5K
06:57Author Spotlight: Advancing Cardiovascular Imaging - Introducing the Spatially Weighted Calcium Score for Early Disease Detection
Published on: September 22, 2023
1.0K
相关概念视频
Imaging Studies for Cardiovascular System IV: CMRI
49
Cardiovascular magnetic resonance imaging, or CMRI, is a non-invasive diagnostic test that employs a magnetic field and radiofrequency waves to create precise images of the heart and arteries. It provides comprehensive information about cardiac anatomy, function, perfusion, and tissue characterization without ionizing radiation.IndicationsCMRI diagnoses various heart conditions, including tissue damage from heart attacks, ischemic heart disease, myocarditis, aortic issues (tears, aneurysms,...
49
Imaging Studies for Cardiovascular System V: CT
31
Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...
31
