基于学习的门控心肌灌注SPECT左心室自动分割与定量方法可行性研究
本研究提出一种基于端到端全卷积神经网络的左心室心肌自动分割方法,用于门控心肌灌注SPECT成像,无需人工干预。回顾性纳入32例正常和24例异常患者,自动分割轮廓与医生勾画的真实轮廓对比显示良好一致性,左心室心肌体积相关系数为0.910 ± 0.061(P < 0.001),平均相对误差为-1.09 ± 3.66%。结果表明该方法在准确量化心动周期中心肌体积变化方面具有可行性。
要点
- 全卷积神经网络可自动分割门控MPS左心室心肌,无需手动调整。
- 自动分割轮廓与医生勾画真实轮廓的平均DSC大于0.900,Hausdorff距离小于1 cm。
- 左心室心肌体积相关系数为0.910 ± 0.061(P < 0.001),平均相对误差-1.09 ± 3.66%。
核心结论
- 基于学习的自动分割方法在门控MPS左心室心肌分割和体积定量中与医生勾画真实轮廓高度一致,具有临床可行性。
研究设计与样本
- 回顾性研究,纳入32例正常患者和24例异常患者,使用端到端全卷积神经网络分割左心室心肌心内膜和心外膜表面。
主要发现
- 自动分割轮廓与真实轮廓在所有32+24例患者所有相位的平均DSC大于0.900,Hausdorff距离小于1 cm。
- 左心室心肌体积与真实值的相关系数为0.910 ± 0.061(P < 0.001),平均相对误差为-1.09 ± 3.66%。
关键数值与推荐
- 平均DSC大于0.900,Hausdorff距离小于1 cm,心肌体积相关系数0.910 ± 0.061(P < 0.001),平均相对误差-1.09 ± 3.66%。
临床怎么用
- 该方法可自动分割左心室心肌并量化其体积,有望减少人工调整的主观性和繁琐性,辅助门控MPS心功能评估。
局限性
- 原文未报告局限性相关内容。
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: The performance of left ventricular (LV) functional assessment using gated myocardial perfusion SPECT (MPS) relies on the accuracy of segmentation. Current methods require manual adjustments that are tedious and subjective. We propose a novel machine-learning-based method to automatically segment LV myocardium and measure its volume in gated MPS imaging without human intervention. METHODS: We used an end-to-end fully convolutional neural network to segment LV myocardium by delineating its endocardial and epicardial surface. A novel compound loss function, which encourages similarity and penalizes discrepancy between prediction and training dataset, is utilized in training stage to achieve excellent performance. We retrospectively investigated 32 normal patients and 24 abnormal patients, whose LV myocardial contours automatically segmented by our method were compared with those delineated by physicians as the ground truth. RESULTS: The results of our method demonstrated very good agreement with the ground truth. The average DSC metrics and Hausdorff distance of the contours delineated by our method are larger than 0.900 and less than 1 cm, respectively, among all 32 + 24 patients of all phases. The correlation coefficient of the LV myocardium volume between ground truth and our results is 0.910 ± 0.061 (P < 0.001), and the mean relative error of LV myocardium volume is - 1.09 ± 3.66%. CONCLUSION: These results strongly indicate the feasibility of our method in accurately quantifying LV myocardium volume change over the cardiac cycle. The learning-based segmentation method in gated MPS imaging has great promise for clinical use.
引用
- Wang T, Lei Y, Tang H, et al. A learning-based automatic segmentation and quantification method on left ventricle in gated myocardial perfusion SPECT imaging: A feasibility study. J Nucl Cardiol. 2019. PMID: 30693428. doi:10.1007/s12350-019-01594-2
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。