Department of Anatomy with Radiology, University of Auckland, New Zealand.
Med Image Anal. 2014 Jan;18(1):50-62. doi: 10.1016/j.media.2013.09.001. Epub 2013 Sep 13.
A collaborative framework was initiated to establish a community resource of ground truth segmentations from cardiac MRI. Multi-site, multi-vendor cardiac MRI datasets comprising 95 patients (73 men, 22 women; mean age 62.73±11.24years) with coronary artery disease and prior myocardial infarction, were randomly selected from data made available by the Cardiac Atlas Project (Fonseca et al., 2011). Three semi- and two fully-automated raters segmented the left ventricular myocardium from short-axis cardiac MR images as part of a challenge introduced at the STACOM 2011 MICCAI workshop (Suinesiaputra et al., 2012). Consensus myocardium images were generated based on the Expectation-Maximization principle implemented by the STAPLE algorithm (Warfield et al., 2004). The mean sensitivity, specificity, positive predictive and negative predictive values ranged between 0.63 and 0.85, 0.60 and 0.98, 0.56 and 0.94, and 0.83 and 0.92, respectively, against the STAPLE consensus. Spatial and temporal agreement varied in different amounts for each rater. STAPLE produced high quality consensus images if the region of interest was limited to the area of discrepancy between raters. To maintain the quality of the consensus, an objective measure based on the candidate automated rater performance distribution is proposed. The consensus segmentation based on a combination of manual and automated raters were more consistent than any particular rater, even those with manual input. The consensus is expected to improve with the addition of new automated contributions. This resource is open for future contributions, and is available as a test bed for the evaluation of new segmentation algorithms, through the Cardiac Atlas Project (www.cardiacatlas.org).
建立了一个协作框架，以建立一个来自心脏 MRI 的地面真实分割的社区资源。从心脏图谱项目（Fonseca 等人，2011 年）提供的数据中随机选择了 95 名患有冠状动脉疾病和先前心肌梗死的患者（73 名男性，22 名女性；平均年龄 62.73±11.24 岁）的多站点、多供应商心脏 MRI 数据集。三名半自动和两名全自动评估员从短轴心脏 MR 图像中分割左心室心肌，这是 2011 年 MICCAI 研讨会 STACOM 引入的挑战的一部分（Suinesiaputra 等人，2012 年）。基于由 STAPLE 算法（Warfield 等人，2004 年）实现的期望最大化原理生成共识心肌图像。平均灵敏度、特异性、阳性预测值和阴性预测值分别在 0.63 到 0.85、0.60 到 0.98、0.56 到 0.94 和 0.83 到 0.92 之间，分别与 STAPLE 共识相比。每个评估员的空间和时间一致性差异不同。如果感兴趣区域仅限于评估员之间差异的区域，则 STAPLE 会生成高质量的共识图像。为了保持共识的质量，提出了一种基于候选自动评估员性能分布的客观度量。基于手动和自动评估员的组合的共识分割比任何特定的评估员都更一致，即使是那些具有手动输入的评估员。随着新的自动贡献的增加，共识有望得到改善。该资源可供未来使用，并可作为通过心脏图谱项目（www.cardiacatlas.org）评估新分割算法的测试平台。
