Right ventricular strain and volume analyses through deep learning-based fully automatic segmentation based on radial long-axis reconstruction of short-axis cine magnetic resonance images
Right ventricular strain and volume analyses through deep learning-based fully automatic segmentation based on radial long-axis reconstruction of short-axis cine magnetic resonance images
复制标题
基于短轴电影磁共振图像径向长轴重建的深度学习全自动分割进行右心室应变和体积分析
DOI：
10.1007/s10334-022-01017-3
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Kadokami Toshiaki
中科院分区：
文献类型：
--
作者：
Kawakubo Masateru;Moriyama Daichi;Yamasaki Yuzo;Abe Kohtaro;Hosokawa Kazuya;Moriyama Tetsuhiro;Triadyaksa Pandji;Wibowo Adi;Nagao Michinobu;Arai Hideo;Nishimura Hiroshi;Kadokami Toshiaki
目的提出一种基于深度学习的全自动右心室（RV）分割技术，该技术针对常规短轴（SA）心血管磁共振（CMR）图像中右心室区域中心的径向重构长轴（RLA）图像进行分割。因此，本研究的目的是在RV应变参数的测量方面，比较基于深度学习的RLA图像全自动分割的准确率与基于常规深度学习的SA方向分割的准确率。材料和方法比较了上述方法在右心室分割和用Dice相似系数（dsc）和相关系数测量右心室应变参数时的准确性。结果RLA方法的RV分割dsc值高于常规SA方法（0.84比0.61）。全自动RLA中手动RV应变测量的相关系数优于SA测量（0.5-0.7 vs. 0.1-0.2）。我们提出的RLA实现了从可用的CMR电影图像中准确的全自动提取整个RV区域，而无需任何额外的成像。我们的发现克服了CMR图像分析的复杂性，而没有超声心动图中RV可视化的限制。
ObjectiveWe propose a deep learning-based fully automatic right ventricle (RV) segmentation technique that targets radially reconstructed long-axis (RLA) images of the center of the RV region in routine short axis (SA) cardiovascular magnetic resonance (CMR) images. Accordingly, the purpose of this study is to compare the accuracy of deep learning-based fully automatic segmentation of RLA images with the accuracy of conventional deep learning-based segmentation in SA orientation in terms of the measurements of RV strain parameters.Materials and methodsWe compared the accuracies of the above-mentioned methods in RV segmentations and in measuring RV strain parameters by Dice similarity coefficients (DSCs) and correlation coefficients.ResultsDSC of RV segmentation of the RLA method exhibited a higher value than those of the conventional SA methods (0.84 vs. 0.61). Correlation coefficient with respect to manual RV strain measurements in the fully automatic RLA were superior to those in SA measurements (0.5–0.7 vs. 0.1–0.2).DiscussionOur proposed RLA realizes accurate fully automatic extraction of the entire RV region from an available CMR cine image without any additional imaging. Our findings overcome the complexity of image analysis in CMR without the limitations of the RV visualization in echocardiography.
登录
查看更多内容
使用深度学习对左心室和右心室进行心脏 MRI 图像分割
DOI：
--
发表时间：
2019
期刊：
arXiv.org
影响因子：
--
作者：
Bo;Daniel Mariano;John Beckfield;Vinay Madenur;Yuming Hu;Tony Reina;Marcus Bobar;M. H. Nguyen;I. Altintas
通讯作者：
I. Altintas
DOI：
10.1007/s10554-017-1199-7
发表时间：
2017-12
期刊：
The international journal of cardiovascular imaging
影响因子：
--
作者：
Satriano A;Heydari B;Narous M;Exner DV;Mikami Y;Attwood MM;Tyberg JV;Lydell CP;Howarth AG;Fine NM;White JA
通讯作者：
White JA
影响因子：
7.5
作者：
Ryo, Keiko;Goda, Akiko;Gorcsan, John, III
通讯作者：
Gorcsan, John, III
DOI：
10.1111/j.1475-097x.2011.01006.x
发表时间：
2011-05-01
影响因子：
1.8
作者：
Aneq, Meriam Astrom;Nylander, Eva;Engvall, Jan
通讯作者：
Engvall, Jan
日本东京
DOI：
--
发表时间：
2019
期刊：
The Statesman’s Yearbook Companion
影响因子：
--
作者：
H. Yoshida
通讯作者：
H. Yoshida