Pearlman Paul C, Tagare Hemant D, Lin Ben A, Sinusas Albert J, Duncan James S
Department of Electrical Engineering, Yale University, New Haven, CT, USA.
Inf Process Med Imaging. 2011;22:37-48. doi: 10.1007/978-3-642-22092-0_4.
We present an approach for segmenting left ventricular endocardial boundaries from RF ultrasound. Segmentation is achieved jointly using an independent identically distributed (i.i.d.) spatial model for RF intensity and a multiframe conditional model. The conditional model relates neighboring frames in the image sequence by means of a computationally efficient linear predictor that exploits spatio-temporal coherence in the data. Segmentation using the RF data overcomes problems due to image inhomogeneities often amplified in B-mode segmentation and provides geometric constraints for RF phase-based speckle tracking. The incorporation of multiple frames in the conditional model significantly increases the robustness and accuracy of the algorithm. Results are generated using between 2 and 5 frames of RF data for each segmentation and are validated by comparison with manual tracings and automated B-mode boundary detection using standard (Chan and Vese-based) level sets on echocardiographic images from 27 3D sequences acquired from 6 canine studies.
我们提出了一种从射频超声中分割左心室心内膜边界的方法。分割是通过联合使用用于射频强度的独立同分布（i.i.d.）空间模型和多帧条件模型来实现的。条件模型借助计算效率高的线性预测器将图像序列中的相邻帧联系起来，该预测器利用了数据中的时空相干性。使用射频数据进行分割克服了由于图像不均匀性导致的问题，这些问题在B模式分割中常常被放大，并且为基于射频相位的散斑跟踪提供了几何约束。在条件模型中纳入多帧显著提高了算法的鲁棒性和准确性。每次分割使用2至5帧射频数据生成结果，并通过与手动追踪以及使用基于标准（Chan和Vese）水平集的自动B模式边界检测进行比较来验证，这些数据来自从6项犬类研究中获取的27个三维序列的超声心动图图像。
