Yang Yuling, Wang Fanghu, Han Xu, Xu Hui, Zhang Yangmei, Xu Weiping, Wang Shuxia, Lu Lijun
School of Biomedical Engineering, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China.
Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, 1023 Shatai Road, Guangzhou, 510515, China.
EJNMMI Phys. 2024 Aug 2;11(1):70. doi: 10.1186/s40658-024-00673-9.
Accurately redirecting reconstructed Positron emission tomography (PET) images into short-axis (SA) images shows great significance for subsequent clinical diagnosis. We developed a system for automatic redirection and quantitative analysis of myocardial PET images.
A total of 128 patients were enrolled for 18 F-FDG PET/CT myocardial metabolic images (MMIs), including 3 image classifications: without defects, with defects, and excess uptake. The automatic reorientation system includes five modules: regional division, myocardial segmentation, ellipsoid fitting, image rotation and quantitative analysis. First, the left ventricular geometry-based canny edge detection (LVG-CED) was developed and compared with the other 5 common region segmentation algorithms, the optimized partitioning was determined based on partition success rate. Then, 9 myocardial segmentation methods and 4 ellipsoid fitting methods were combined to derive 36 cross combinations for diagnostic performance in terms of Pearson correlation coefficient (PCC), Kendall correlation coefficient (KCC), Spearman correlation coefficient (SCC), and determination coefficient. Finally, the deflection angles were computed by ellipsoid fitting and the SA images were derived by affine transformation. Furthermore, the polar maps were used for quantitative analysis of SA images, and the redirection effects of 3 different image classifications were analyzed using correlation coefficients.
On the dataset, LVG-CED outperformed other methods in the regional division module with a 100% success rate. In 36 cross combinations, PSO-FCM and LLS-SVD performed the best in terms of correlation coefficient. The linear results indicate that our algorithm (LVG-CED, PSO-FCM, and LLS-SVD) has good consistency with the reference manual method. In quantitative analysis, the similarities between our method and the reference manual method were higher than 96% at 17 segments. Moreover, our method demonstrated excellent performance in all 3 image classifications.
Our algorithm system could realize accurate automatic reorientation and quantitative analysis of PET MMIs, which is also effective for images suffering from interference.
将重建后的正电子发射断层扫描（PET）图像准确重定向为短轴（SA）图像对后续临床诊断具有重要意义。我们开发了一种用于心肌PET图像自动重定向和定量分析的系统。
共纳入128例患者进行18F-FDG PET/CT心肌代谢图像（MMIs）检查，包括3种图像分类：无缺损、有缺损和摄取增加。自动重定向系统包括五个模块：区域划分、心肌分割、椭圆拟合、图像旋转和定量分析。首先，开发基于左心室几何形状的Canny边缘检测（LVG-CED）并与其他5种常用区域分割算法进行比较，根据分割成功率确定优化的分割方法。然后，将9种心肌分割方法和4种椭圆拟合方法进行组合，得出36种交叉组合，以Pearson相关系数（PCC）、Kendall相关系数（KCC）、Spearman相关系数（SCC）和决定系数来评估诊断性能。最后，通过椭圆拟合计算偏转角，并通过仿射变换得出SA图像。此外，使用极坐标图对SA图像进行定量分析，并使用相关系数分析3种不同图像分类的重定向效果。
在数据集中，LVG-CED在区域划分模块中表现优于其他方法，成功率为100%。在36种交叉组合中，PSO-FCM和LLS-SVD在相关系数方面表现最佳。线性结果表明，我们的算法（LVG-CED、PSO-FCM和LLS-SVD）与参考手动方法具有良好的一致性。在定量分析中，我们的方法与参考手动方法在17个节段处的相似度高于96%。此外，我们的方法在所有3种图像分类中均表现出色。
我们的算法系统能够实现PET MMIs的准确自动重定向和定量分析，对受干扰的图像也有效。
