Mayo Graduate School, Mayo Clinic, Rochester, Minnesota 55902, USA.
J Magn Reson Imaging. 2013 Aug;38(2):371-9. doi: 10.1002/jmri.23980. Epub 2012 Dec 19.
To provide a fully automated algorithm for obtaining stiffness measurements from hepatic magnetic resonance elastography (MRE) images that are consistent with measurements performed by expert readers.
An initial liver contour was found using an adaptive threshold and expanded using an active contour to select a homogeneous area of the liver. The confidence map generated during the stiffness calculation was used to select a region of reliable wave propagation. The average stiffness within the automatically generated region of interest (ROI) was compared to measurements by two trained readers in a set of 88 clinical test cases ranging from healthy to severely fibrotic.
The stiffness measurements reported by the readers differed by -6.76% ± 22.8% (95% confidence) and had an intraclass correlation coefficient (ICC) of 0.972 (P < 0.05). The algorithm and the more experienced reader differed by 4.32% ± 14.9 with an ICC of 0.987.
The automated algorithm performed reliably, even though MRE acquisitions often have motion artifacts present. The correlation between the automated measurements and those from the trained readers was superior to the correlation between the readers.
提供一种完全自动化的算法，用于从肝脏磁共振弹性成像（MRE）图像中获取与专家读者进行的测量一致的弹性测量值。
使用自适应阈值找到初始肝轮廓，并使用主动轮廓进行扩展，以选择肝脏的均匀区域。在计算弹性时生成的置信度图用于选择可靠波传播的区域。在从健康到严重纤维化的 88 例临床测试病例集中，将自动生成的感兴趣区域（ROI）内的平均刚度与两名经过培训的读者的测量值进行比较。
读者报告的刚度测量值差异为-6.76%±22.8%（95%置信区间），组内相关系数（ICC）为 0.972（P<0.05）。该算法和更有经验的读者之间的差异为 4.32%±14.9，ICC 为 0.987。
即使 MRE 采集经常存在运动伪影，自动算法也能可靠地执行。自动测量值与经过培训的读者之间的相关性优于读者之间的相关性。
