文献速递心脏核医学

基于深度学习的自动重定向生成短轴SPECT心肌灌注图像

Automatic reorientation by deep learning to generate short-axis SPECT myocardial perfusion images.
PubMed 文献 · J Nucl Cardiol · 2023-03-01

研究纳入254例患者(226例负荷和247例静息SPECT心肌灌注图像),采用五折交叉验证训练卷积神经网络预测重定向参数,并在测试集中评估。模型预测与人工参考标准在平移距离和旋转角度上的Spearman决定系数为0.987至0.996,负荷和静息图像的功能参数决定系数分别为0.858和0.9。作者认为该方法能准确生成短轴图像,在临床应用中具有很大前景。

要点

  • 深度学习模型预测的平移和旋转参数与人工参考标准高度相关(Spearman决定系数0.987至0.996)。
  • 测试集负荷图像中,模型与参考标准的总灌注缺损百分比和总负荷评分的决定系数均为0.858。
  • 测试集静息图像中,总灌注缺损百分比和总静息评分的决定系数均为0.9。

核心结论

  • 基于深度学习的左心室重定向方法能够准确生成短轴图像。
  • 技术验证和后续临床参数评估表明该方法在临床应用中具有很大前景。

研究设计与样本

  • 研究纳入254例患者,包括226例负荷SPECT心肌灌注图像和247例静息SPECT心肌灌注图像。
  • 采用五折交叉验证,以180例负荷和201例静息图像进行训练和内部验证,其余图像用于测试。
  • 由经验丰富的核心脏病学医生标注人工重定向的刚性变换参数(平移和旋转)作为参考标准。
  • 设计卷积神经网络预测变换参数,并应用于空间变换网络的网格生成器和采样器以生成重定向图像。
  • 损失函数包含平移的平均绝对误差和旋转的均方误差,采用三阶段优化策略。

主要发现

  • 测试集中,模型预测与参考标准的平移距离Spearman决定系数在X轴为0.993、Y轴为0.992、Z轴为0.994。
  • 测试集中,模型预测与参考标准的旋转角度Spearman决定系数沿X轴为0.987、沿Y轴为0.990、沿Z轴为0.996。
  • 测试集46例负荷图像中,总灌注缺损百分比和总负荷评分的Spearman决定系数均为0.858。
  • 测试集46例静息图像中,总灌注缺损百分比和总静息评分的Spearman决定系数均为0.9。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Single photon emission computed tomography (SPECT) myocardial perfusion images (MPI) can be displayed both in traditional short-axis (SA) cardiac planes and polar maps for interpretation and quantification. It is essential to reorient the reconstructed transaxial SPECT MPI into standard SA slices. This study is aimed to develop a deep-learning-based approach for automatic reorientation of MPI. METHODS: A total of 254 patients were enrolled, including 226 stress SPECT MPIs and 247 rest SPECT MPIs. Fivefold cross-validation with 180 stress and 201 rest MPIs was used for training and internal validation; the remaining images were used for testing. The rigid transformation parameters (translation and rotation) from manual reorientation were annotated by an experienced nuclear cardiologist and used as the reference standard. A convolutional neural network (CNN) was designed to predict the transformation parameters. Then, the derived transform was applied to the grid generator and sampler in spatial transformer network (STN) to generate the reoriented image. A loss function containing mean absolute errors for translation and mean square errors for rotation was employed. A three-stage optimization strategy was adopted for model optimization: (1) optimize the translation parameters while fixing the rotation parameters; (2) optimize rotation parameters while fixing the translation parameters; (3) optimize both translation and rotation parameters together. RESULTS: In the test set, the Spearman determination coefficients of the translation distances and rotation angles between the model prediction and the reference standard were 0.993 in X axis, 0.992 in Y axis, 0.994 in Z axis, 0.987 along X axis, 0.990 along Y axis and 0.996 along Z axis, respectively. For the 46 stress MPIs in the test set, the Spearman determination coefficients were 0.858 in percentage of profusion defect (PPD) and 0.858 in summed stress score (SSS); for the 46 rest MPIs in the test set, the Spearman determination coefficients were 0.9 in PPD and 0.9 in summed rest score (SRS). CONCLUSIONS: Our deep learning-based LV reorientation method is able to accurately generate the SA images. Technical validations and subsequent evaluations of measured clinical parameters show that it has great promise for clinical use.

来源:J Nucl Cardiol,查看原文。版权归原作者所有。

引用

  1. Zhu F, Wang G, Zhao C, et al. Automatic reorientation by deep learning to generate short-axis SPECT myocardial perfusion images. J Nucl Cardiol. 2023. PMID: 36859594. doi:10.1007/s12350-023-03226-2

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。