Center for Computational Imaging and Simulation Technologies in Biomedicine, Information and Communication Technologies Department, Universitat Pompeu Fabra, Barcelona, Spain.
Phys Med Biol. 2012 Jul 7;57(13):4155-74. doi: 10.1088/0031-9155/57/13/4155. Epub 2012 Jun 8.
Training active shape models requires collecting manual ground-truth meshes in a large image database. While shape information can be reused across multiple imaging modalities, intensity information needs to be imaging modality and protocol specific. In this context, this study has two main purposes: (1) to test the potential of using intensity models learned from MRI simulated datasets and (2) to test the potential of including a measure of reliability during the matching process to increase robustness. We used a population of 400 virtual subjects (XCAT phantom), and two clinical populations of 40 and 45 subjects. Virtual subjects were used to generate simulated datasets (MRISIM simulator). Intensity models were trained both on simulated and real datasets. The trained models were used to segment the left ventricle (LV) and right ventricle (RV) from real datasets. Segmentations were also obtained with and without reliability information. Performance was evaluated with point-to-surface and volume errors. Simulated intensity models obtained average accuracy comparable to inter-observer variability for LV segmentation. The inclusion of reliability information reduced volume errors in hypertrophic patients (EF errors from 17 ± 57% to 10 ± 18%; LV MASS errors from -27 ± 22 g to -14 ± 25 g), and in heart failure patients (EF errors from -8 ± 42% to -5 ± 14%). The RV model of the simulated images needs further improvement to better resemble image intensities around the myocardial edges. Both for real and simulated models, reliability information increased segmentation robustness without penalizing accuracy.
训练主动形状模型需要在大型图像数据库中收集手动地面真实网格。虽然形状信息可以跨多种成像模式重复使用，但强度信息需要针对成像模式和协议进行特定处理。在这种情况下，本研究有两个主要目的：（1）测试使用从 MRI 模拟数据集学习到的强度模型的潜力，以及（2）测试在匹配过程中包含可靠性度量的潜力，以提高鲁棒性。我们使用了 400 个虚拟受试者（XCAT 体模）和 40 名和 45 名临床受试者的两个临床群体。虚拟受试者用于生成模拟数据集（MRISIM 模拟器）。强度模型既在模拟数据集上又在真实数据集上进行训练。训练后的模型用于从真实数据集分割左心室（LV）和右心室（RV）。分割也在有无可靠性信息的情况下进行。使用点到面和体积误差来评估性能。模拟强度模型获得的平均准确性与 LV 分割的观察者间变异性相当。包含可靠性信息减少了肥厚型患者（EF 误差从 17±57%减少到 10±18%；LV MASS 误差从-27±22 克减少到-14±25 克）和心力衰竭患者（EF 误差从-8±42%减少到-5±14%）的体积误差。模拟图像的 RV 模型需要进一步改进，以更好地模拟心肌边缘周围的图像强度。对于真实和模拟模型，可靠性信息都提高了分割的鲁棒性，而不会影响准确性。
