4D流MRI的细分:4D深度学习和基于速度的水平集之间的比较
Armando Barrera-Naranjo1, Diana M Marin-Castrillon2, Thomas Decourselle1
1CASIS-Cardiac Simulation & Imaging Software, 21800 Quetigny, France.
Journal of imaging
|June 27, 2023
概括
深度学习U-Net方法在4D流MRI中提供了胸前大动脉的优越自动细分,与水平集相比. 这提高了在大动脉动脉瘤研究中计算重要生物标志物的准确性,例如壁剪应力.
科学领域:
- 医疗成像医学成像
- 心血管成像 - 心血管成像
- 生物医学工程 生物医学工程
背景情况:
- 胸前动脉动脉瘤 (TAA) 是对主动脉的危及生命的扩张,手术决定通常依赖于最大直径,这是一个以其局限性而闻名的指标.
- 四维 (4D) 流磁共振成像 (MRI) 能够进行新的生物标志物计算,例如墙壁剪切应力 (WSS),这对于TAA评估至关重要.
- 对于可靠的WSS计算而言,对整个心脏循环中大动脉的准确细分至关重要,这构成了重大的技术挑战.
研究的目的:
- 为了比较使用4D流MRI数据的两个自动胸前大动脉细分方法的性能.
- 评估基于水平集的方法,利用速度场和U-Net深度学习方法应用于大小图像.
- 评估细分精度对缩期壁切削应力 (WSS) 生物标志物计算对细分精度的影响.
主要方法:
- 两种自动细分技术进行了比较:一个水平设置框架和一个类似U-Net的卷积神经网络.
- 这些方法应用于36名患者的4D流MRI数据,重点关注缩阶段的现有基底真相.
- 用子相似系数 (DSC) 和豪斯多夫距离 (HD) 来量化细分精度; WSS 也被计算和比较.
主要成果:
- 在统计学上,U-Net方法表现出优异的细分性能,在整个大动脉中实现了更高的DSC (0.92±0.02对比0.86±0.5) 和更低的HD (21.49±24.8mm对比35.79±31.33mm)
- 虽然水平设置方法显示最大WSS与地面真相相比的绝对差异略小,但这种差异在统计学上并不显著.
- 由于U-Net方法的细分精度提高,这表明它有可能在TAA患者中进行更可靠的WSS评估.
结论:
- 基于深度学习的细分,特别是U-Net方法,在4D流MRI中为准确的胸腔大动脉细分提供了显著的优势.
- 对所有心脏时间步骤进行准确的细分对于可靠评估大动脉疾病中WSS等血液动力学生物标志物至关重要.
- 这些发现支持在TAA管理中考虑深度学习方法来全面分析4D流MRI数据.
相关概念视频
01:18Uniform Depth Channel Flow: Problem Solving
92
To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
92
01:27Uniform Depth Channel Flow
99
Uniform depth channel flow keeps fluid depth consistent along channels such as irrigation canals. In natural channels, such as rivers, approximate uniform flow is often assumed. This condition occurs when the channel’s bottom slope matches the energy slope, balancing potential energy lost from gravity with head loss due to shear stress. This balance prevents depth changes along the channel length, resulting in a steady, uniform flow.Uniform flow in open channels with a constant cross-section...
99
01:24Magnetic Resonance Imaging
5.3K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
5.3K