摘要
Objectives: We aimed to propose an automatic segmentation method for left ventricular (LV) from 16 electrocardiogram (ECG)-gated 13N-NH3 PET/CT myocardial perfusion imaging (MPI) to improve the per-formance of LV function assessment.Methods: Ninety-six cases with confirmed or suspected obstructive coronary artery disease (CAD) were enrolled in this research. The LV myocardial contours were delineated by physicians as ground truth. We developed an automatic segmentation method, which introduces the self-attention mechanism into 3D U-Net to capture global information of images so as to achieve fine segmentation of LV. Three cross -validation tests were performed on each gate (64 vs. 32 for training vs. validation). The effectiveness was validated by quantitative metrics (modified hausdorff distance, MHD; dice ratio, DR; 3D MHD) as well as cardiac functional parameters (end-systolic volume, ESV; end-diastolic volume, EDV; ejection fraction, EF). Furthermore, the feasibility of the proposed method was also evaluated by intra-and inter-observers with DR and 3D-MHD.Results: Compared with backbone network, the proposed approach improved the average DR from 0.905 +/- 0.0193 to 0.9202 +/- 0.0164, and decreased the average 3D MHD from 0.4611 +/- 0.0349 to 0.4304 +/- 0.0339. The average relative error of LV volume between proposed method and ground truth is 1.09 +/- 3.66%, and the correlation coefficient is 0.992 +/- 0.007 ( P < 0.001). The EDV, ESV, EF deduced from the proposed approach were highly correlated with ground truth ( r >= 0.864, P < 0.001), and the correlation with commercial software is fair ( r >= 0.871, P < 0.001). DR and 3D MHD of contours and myocardium from two observers are higher than 0.899 and less than 0.5194. Conclusion: The proposed approach is highly feasible for automatic segmentation of the LV cavity and myocardium, with potential to benefit the precision of LV function assessment.
学科与关键词
- Left Ventricular Myocardium Segmentation in Coronary Computed Tomography Angiography using 3D Deep Attention U-NetHe, Xiuxiu; Guo, Bangjun; Lei, Yang; Harms, Joseph; Wang, Tonghe; Liu, Tian; Zhang, Longjiang; Yang, Xiaofeng*SPIE Medical Imaging Conference - Biomedical Applications in Molecular, Structural, and Functional Imaging, Houston, TX, 2020-02-15 To 2020-02-20.
- Automated Left Ventricular Myocardium Segmentation Using 3D Deeply Supervised Attention U-Net for Coronary Computed Tomography Angiography (vol 47, pg 1775, 2020)Zhang, Long JiangMedical Physics, 2021, 48(1): 534-534.
- Automatic detection of left and right ventricles from CTA enables efficient alignment of anatomy with myocardial perfusion dataPiccinelli, Marina*; Faber, Tracy L.; Arepalli, Chesnal D.; Appia, Vikram; Vinten-Johansen, Jakob; Schmarkey, Susan L.; Folks, Russell D.; Garcia, Ernest V.; Yezzi, AnthonyJournal of Nuclear Cardiology, 2014, 21(1): 96-108.被引 4
