Imaging Informatics Lab, 2500 University Drive NW, Calgary, AB T2N 1N4, Canada.
Comput Methods Programs Biomed. 2013 Aug;111(2):480-7. doi: 10.1016/j.cmpb.2013.04.011. Epub 2013 May 18.
Precision and accuracy are sometimes sacrificed to ensure that medical image processing is rapid. To address this, our lab had developed a novel level set segmentation algorithm that is 16× faster and >96% accurate on realistic brain phantoms.
This study reports speed, precision and estimated accuracy of our algorithm when measuring MRIs of meningioma brain tumors and compares it to manual tracing and modified MacDonald (MM) ellipsoid criteria. A repeated-measures study allowed us to determine measurement precisions (MPs) - clinically relevant thresholds for statistically significant change.
Speed: the level set, MM, and trace methods required 1:20, 1:35, and 9:35 (mm:ss) respectively on average to complete a volume measurement (p<0.05). Accuracy: the level set was not statistically different to the estimated true lesion volumes (p>0.05). Precision: the MM's within-operator and between-operator MPs were significantly higher (worse) than the other methods (p<0.05). The observed difference in MP between the level set and trace methods did not reach statistical significance (p>0.05).
Our level set is faster on average than MM, yet has accuracy and precision comparable to manual tracing.
为了确保医学图像处理的速度，有时会牺牲精度和准确性。为了解决这个问题，我们实验室开发了一种新的水平集分割算法，该算法在真实的脑模型上的速度提高了 16 倍，准确性超过 96%。
本研究报告了我们的算法在测量脑膜瘤脑肿瘤 MRI 时的速度、精度和估计准确性，并将其与手动跟踪和改良 MacDonald（MM）椭圆体标准进行了比较。重复测量研究允许我们确定测量精度（MP）——统计学上显著变化的临床相关阈值。
速度：水平集、MM 和跟踪方法平均分别需要 1:20、1:35 和 9:35（mm:ss）来完成体积测量（p<0.05）。准确性：水平集与估计的真实病变体积无统计学差异（p>0.05）。精度：MM 的操作者内和操作者间 MP 明显高于其他方法（p<0.05）。水平集和跟踪方法之间观察到的 MP 差异没有达到统计学意义（p>0.05）。
我们的水平集平均速度比 MM 快，但准确性和精度与手动跟踪相当。
