Yang Fan, He Yan, Hussain Mubashir, Xie Hong, Lei Pinggui
School of Biology & Engineering, Guizhou Medical University, Guiyang, Guizhou Province, China.
State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing, Jiangsu Province, China.
Comput Math Methods Med. 2017;2017:1640835. doi: 10.1155/2017/1640835. Epub 2017 Jul 26.
Free-breathing cardiac magnetic resonance (CMR) imaging has short examination time with high reproducibility. Detection of the end-diastole and the end-systole frames of the free-breathing cardiac magnetic resonance, supplemented by visual identification, is time consuming and laborious. We propose a novel method for automatic identification of both the end-diastole and the end-systole frames, in the free-breathing CMR imaging. The proposed technique utilizes the convolutional neural network to locate the left ventricle and to obtain the end-diastole and the end-systole frames from the respiratory motion signal. The proposed procedure works successfully on our free-breathing CMR data, and the results demonstrate a high degree of accuracy and stability. Convolutional neural network improves the postprocessing efficiency greatly and facilitates the clinical application of the free-breathing CMR imaging.
自由呼吸心脏磁共振成像（CMR）检查时间短且重复性高。在自由呼吸心脏磁共振成像中，通过视觉识别辅助检测舒张末期和收缩末期帧既耗时又费力。我们提出了一种在自由呼吸CMR成像中自动识别舒张末期和收缩末期帧的新方法。所提出的技术利用卷积神经网络定位左心室，并从呼吸运动信号中获取舒张末期和收缩末期帧。所提出的程序在我们的自由呼吸CMR数据上成功运行，结果显示出高度的准确性和稳定性。卷积神经网络大大提高了后处理效率，促进了自由呼吸CMR成像的临床应用。
