ImViA EA 7535 Laboratory, University of Burgundy, 21078 Dijon, France.
National Engineering School of Sousse, University of Sousse, Sousse 4054, Tunisia.
Sensors (Basel). 2022 Mar 8;22(6):2084. doi: 10.3390/s22062084.
Accurate segmentation of the myocardial scar may supply relevant advancements in predicting and controlling deadly ventricular arrhythmias in subjects with cardiovascular disease. In this paper, we propose the architecture of inclusion and classification of prior information U-Net (ICPIU-Net) to efficiently segment the left ventricle (LV) myocardium, myocardial infarction (MI), and microvascular-obstructed (MVO) tissues from late gadolinium enhancement magnetic resonance (LGE-MR) images. Our approach was developed using two subnets cascaded to first segment the LV cavity and myocardium. Then, we used inclusion and classification constraint networks to improve the resulting segmentation of the diseased regions within the pre-segmented LV myocardium. This network incorporates the inclusion and classification information of the LGE-MRI to maintain topological constraints of pathological areas. In the testing stage, the outputs of each segmentation network obtained with specific estimated parameters from training were fused using the majority voting technique for the final label prediction of each voxel in the LGE-MR image. The proposed method was validated by comparing its results to manual drawings by experts from 50 LGE-MR images. Importantly, compared to various deep learning-based methods participating in the EMIDEC challenge, the results of our approach have a more significant agreement with manual contouring in segmenting myocardial diseases.
准确的心肌瘢痕分割可为心血管疾病患者预测和控制致命性室性心律失常提供相关进展。在本文中，我们提出了包含和分类先验信息的 U-Net（ICPIU-Net）的架构，以有效地从钆延迟增强磁共振（LGE-MR）图像中分割左心室（LV）心肌、心肌梗死（MI）和微血管阻塞（MVO）组织。我们的方法是使用两个级联的子网开发的，首先分割 LV 腔和心肌。然后，我们使用包含和分类约束网络来改进在预分割 LV 心肌内分割病变区域的结果。该网络结合了 LGE-MRI 的包含和分类信息，以保持病理区域的拓扑约束。在测试阶段，使用从训练中获得的特定估计参数对每个分割网络的输出进行融合，使用多数投票技术对 LGE-MR 图像中的每个体素进行最终标签预测。通过将 50 张 LGE-MR 图像的专家手动绘图结果与该方法的结果进行比较，验证了该方法的有效性。重要的是，与参与 EMIDEC 挑战赛的各种基于深度学习的方法相比，我们的方法在分割心肌疾病方面与手动轮廓的结果具有更显著的一致性。
