IEEE Trans Biomed Eng. 2022 May;69(5):1595-1607. doi: 10.1109/TBME.2021.3123612. Epub 2022 Apr 21.
We present a user-initialized, automated left ventricle (LV) segmentation method for use with echocardiograms (echo). The method uses an iterative Dijkstra's algorithm, strategic node selection, and novel cost matrix formulation based on intensity peak prominence and is termed the "Prominence Iterative Dijkstra's" algorithm, or ProID. ProID is initialized with three user-input clicks per time-series scan. ProID was tested using artificial echos representing five different systems. Results showed accurate LV contours and volume estimations as compared to the ground-truth for all systems. Using the CAMUS dataset, we demonstrate ProID maintained similar Dice similarity scores (DSS) to other automated methods. ProID was then used to analyze a clinical cohort of 66 pediatric patients, including normal and diseased hearts. Output segmentations, LV volume, and ejection fraction were compared against manual segmentations from two expert readers. ProID maintained an average DSS of 0.93 when comparing against manual segmentation. Comparing the two expert readers, the manual segmentations maintained a DSS of 0.93 which increased to 0.95 when they used ProID. Thus, ProID reduced inter-operator variability across the expert readers. Overall, this work demonstrates ProID yields accurate boundaries across age groups, disease states, and echo platforms with low computational cost and no need for training data.
我们提出了一种用户初始化的、自动化的左心室（LV）分割方法，用于超声心动图（echo）。该方法使用迭代的 Dijkstra 算法、策略性节点选择和基于强度峰值突出的新代价矩阵公式，称为“突出迭代 Dijkstra 算法”或 ProID。ProID 每次时间序列扫描用三个用户输入点击初始化。ProID 在代表五个不同系统的人工 echo 上进行了测试。结果表明，与所有系统的真实值相比，ProID 能够准确地估计 LV 轮廓和体积。使用 CAMUS 数据集，我们证明了 ProID 与其他自动方法相比保持了相似的骰子相似性得分（DSS）。然后，我们使用 ProID 分析了 66 名儿科患者的临床队列，包括正常和患病的心脏。输出分割、LV 体积和射血分数与来自两位专家读者的手动分割进行了比较。ProID 在与手动分割进行比较时平均 DSS 为 0.93。比较两位专家读者，手动分割的 DSS 为 0.93，当他们使用 ProID 时增加到 0.95。因此，ProID 降低了专家读者之间的操作员间变异性。总体而言，这项工作表明 ProID 在不同年龄段、疾病状态和超声心动图平台上都能产生准确的边界，具有低计算成本，无需训练数据。
