1 Department of Radiology, The University of Chicago, Chicago, IL.
AJR Am J Roentgenol. 2014 Jan;202(1):152-9. doi: 10.2214/AJR.13.10812.
Our purpose was to develop an accurate automated 3D liver segmentation scheme for measuring liver volumes on MRI.
Our scheme for MRI liver volumetry consisted of three main stages. First, the preprocessing stage was applied to T1-weighted MRI of the liver in the portal venous phase to reduce noise and produce the boundary-enhanced image. This boundary-enhanced image was used as a speed function for a 3D fast-marching algorithm to generate an initial surface that roughly approximated the shape of the liver. A 3D geodesic-active-contour segmentation algorithm refined the initial surface to precisely determine the liver boundaries. The liver volumes determined by our scheme were compared with those manually traced by a radiologist, used as the reference standard.
The two volumetric methods reached excellent agreement (intraclass correlation coefficient, 0.98) without statistical significance (p = 0.42). The average (± SD) accuracy was 99.4% ± 0.14%, and the average Dice overlap coefficient was 93.6% ± 1.7%. The mean processing time for our automated scheme was 1.03 ± 0.13 minutes, whereas that for manual volumetry was 24.0 ± 4.4 minutes (p < 0.001).
The MRI liver volumetry based on our automated scheme agreed excellently with reference-standard volumetry, and it required substantially less completion time.
我们旨在开发一种准确的自动 3D 肝脏分割方案，用于测量 MRI 上的肝脏体积。
我们的 MRI 肝脏体积测量方案由三个主要阶段组成。首先，应用于门静脉期的肝脏 T1 加权 MRI 的预处理阶段，以减少噪声并生成边界增强图像。该边界增强图像用作 3D 快速行进算法的速度函数，以生成大致近似肝脏形状的初始表面。3D 测地线主动轮廓分割算法对初始表面进行细化，以精确确定肝脏边界。我们的方案确定的肝脏体积与由放射科医生手动追踪的体积进行比较，用作参考标准。
两种体积测量方法的一致性非常好（组内相关系数，0.98），没有统计学意义（p = 0.42）。平均（±SD）准确度为 99.4%±0.14%，平均 Dice 重叠系数为 93.6%±1.7%。我们的自动方案的平均处理时间为 1.03±0.13 分钟，而手动体积测量的时间为 24.0±4.4 分钟（p<0.001）。
基于我们的自动方案的 MRI 肝脏体积测量与参考标准体积测量非常吻合，并且需要的完成时间大大减少。
