CMMCSegNet: Cross-Modality Multicascade Indirect LGE Segmentation on Multimodal Cardiac MR.
CMMCSegNet: Cross-Modality Multicascade Indirect LGE Segmentation on Multimodal Cardiac MR.
复制标题
CMMCSegNet：多模态心脏 MR 上的跨模态多级联间接 LGE 分割
DOI：
10.1155/2021/9942149
复制
发表时间：
2021
影响因子：
--
通讯作者：
Zhang J
中科院分区：
文献类型：
--
作者：
Wang Y;Zhang J
由于心脏磁共振（CMR）晚期钆增强（LGE）可以显示心肌梗死，而平衡-稳态自由进动（bSSFP）序列可以捕捉心脏运动并呈现清晰的边界；多模态CMR分割在心肌活力评估和临床诊断中发挥了重要作用，但由于标记的LGE数据非常少，且LGE的对比度相对较低，自动准确的CMR分割仍然具有挑战性。我们工作的主要目的是通过使用提出的跨模态多级框架：跨模态翻译网络和自动分割网络，学习真实/虚假的bSSFP模态，从而间接分割心脏MR的LGE模态。在分割阶段，设计了一种新的多级pix2pix网络来分割从跨模态翻译网络获得的伪bSSFP序列。此外，我们提出了在分割阶段从预训练的vgg网络中提取的地面真值和预测值之间的感知损失测量特征。我们评估了所提出的方法在多模态CMR数据集上的性能，并验证了其在不同网络结构和不同类型的对抗损失下在测试中的骰子准确性方面优于其他最先进的方法。因此，该网络在心脏LGE间接分割方面具有较好的临床应用前景。
Since Late-Gadolinium Enhancement (LGE) of cardiac magnetic resonance (CMR) visualizes myocardial infarction, and the balanced-Steady State Free Precession (bSSFP) cine sequence can capture cardiac motions and present clear boundaries; multimodal CMR segmentation has played an important role in the assessment of myocardial viability and clinical diagnosis, while automatic and accurate CMR segmentation still remains challenging due to a very small amount of labeled LGE data and the relatively low contrasts of LGE. The main purpose of our work is to learn the real/fake bSSFP modality with ground truths to indirectly segment the LGE modality of cardiac MR by using a proposed cross-modality multicascade framework: cross-modality translation network and automatic segmentation network, respectively. In the segmentation stage, a novel multicascade pix2pix network is designed to segment the fake bSSFP sequence obtained from a cross-modality translation network. Moreover, we propose perceptual loss measuring features between ground truth and prediction, which are extracted from the pretrained vgg network in the segmentation stage. We evaluate the performance of the proposed method on the multimodal CMR dataset and verify its superiority over other state-of-the-art approaches under different network structures and different types of adversarial losses in terms of dice accuracy in testing. Therefore, the proposed network is promising for Indirect Cardiac LGE Segmentation in clinical applications.
登录
查看更多内容
影响因子：
10.9
作者：
Havaei, Mohammad;Davy, Axel;Larochelle, Hugo
通讯作者：
Larochelle, Hugo
DOI：
10.1007/s10334-018-0718-4
发表时间：
2019-04-01
影响因子：
2.3
作者：
Moccia, Sara;Banali, Riccardo;Caiani, Enrico Gianluca
通讯作者：
Caiani, Enrico Gianluca
影响因子：
6.1
作者：
Qin, Zhiwei;Liu, Zhao;Xue, Yongbo
通讯作者：
Xue, Yongbo
DOI：
10.1016/j.compmedimag.2019.101684
发表时间：
2020-01-01
影响因子：
5.7
作者：
Armanious, Karim;Jiang, Chenming;Yang, Bin
通讯作者：
Yang, Bin
影响因子：
7.7
作者：
Nishio, Mizuho;Muramatsu, Chisako;Fujita, Hiroshi
通讯作者：
Fujita, Hiroshi