「虚拟」衰减校正:利用深度学习改善负荷心肌灌注SPECT成像
该研究回顾性纳入11532例SPECT心肌灌注显像(MPI)检查,开发卷积神经网络深度学习算法,仅从非衰减校正(NAC)极图预测虚拟深度学习衰减校正(DLAC)极图,并与CT衰减校正(CTAC)比较总灌注缺损(TPD)。DLAC与CTAC的TPD线性相关性(R²=0.85)优于NAC与CTAC(R²=0.68),诊断阻塞性冠心病的AUC为DLAC 0.827 vs NAC 0.780(p=0.012),DLAC与CTAC的AUC无统计学显著差异。
要点
- DLAC极图TPD与CTAC的线性相关性R²=0.85,优于NAC与CTAC的R²=0.68。
- 诊断阻塞性冠心病AUC:DLAC 0.827 vs NAC 0.780(p=0.012),DLAC与CTAC无统计学显著差异。
- 在88%敏感度下,特异度DLAC提高18.9%,CTAC提高25.6%。
核心结论
- 所提出的深度学习算法无需额外扫描即可提供与CTAC相当的衰减校正,DLAC较传统NAC灌注成像显著改善诊断准确性。
研究设计与样本
- 回顾性识别11532例SPECT MPI检查,均具有配对的NAC与CTAC图像。
- 开发基于卷积神经网络的深度学习算法,在一半人群中训练,从NAC极图预测DLAC极图。
- 对所有极图评估总灌注缺损(TPD),以线性回归比较NAC与DLAC的TPD和CTAC TPD。
- 对NAC、CTAC与DLAC的TPD行受试者工作特征分析,以有创冠状动脉造影诊断的阻塞性冠心病为参考标准。
主要发现
- DLAC TPD与CTAC的线性相关性(R²=0.85)较NAC与CTAC(R²=0.68)显著改善(p<0.001)。
- 诊断阻塞性冠心病的AUC:DLAC 0.827 vs NAC 0.780(p=0.012),DLAC与CTAC的AUC无统计学显著差异。
- 在88%敏感度下,特异度DLAC提高18.9%,CTAC提高25.6%。
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
PURPOSE: Myocardial perfusion imaging (MPI) using single-photon emission computed tomography (SPECT) is widely used for coronary artery disease (CAD) evaluation. Although attenuation correction is recommended to diminish image artifacts and improve diagnostic accuracy, approximately 3/4ths of clinical MPI worldwide remains non-attenuation-corrected (NAC). In this work, we propose a novel deep learning (DL) algorithm to provide "virtual" DL attenuation-corrected (DLAC) perfusion polar maps solely from NAC data without concurrent computed tomography (CT) imaging or additional scans. METHODS: SPECT MPI studies (N = 11,532) with paired NAC and CTAC images were retrospectively identified. A convolutional neural network-based DL algorithm was developed and trained on half of the population to predict DLAC polar maps from NAC polar maps. Total perfusion deficit (TPD) was evaluated for all polar maps. TPDs from NAC and DLAC polar maps were compared to CTAC TPDs in linear regression analysis. Moreover, receiver-operating characteristic analysis was performed on NAC, CTAC, and DLAC TPDs to predict obstructive CAD as diagnosed from invasive coronary angiography. RESULTS: DLAC TPDs exhibited significantly improved linear correlation (p < 0.001) with CTAC (R2 = 0.85) compared to NAC vs. CTAC (R2 = 0.68). The diagnostic performance of TPD was also improved with DLAC compared to NAC with an area under the curve (AUC) of 0.827 vs. 0.780 (p = 0.012) with no statistically significant difference between AUC for CTAC and DLAC. At 88% sensitivity, specificity was improved by 18.9% for DLAC and 25.6% for CTAC. CONCLUSIONS: The proposed DL algorithm provided attenuation correction comparable to CTAC without the need for additional scans. Compared to conventional NAC perfusion imaging, DLAC significantly improved diagnostic accuracy.
引用
- Hagio T, Poitrasson-Rivière A, Moody JB, et al. "Virtual" attenuation correction: improving stress myocardial perfusion SPECT imaging using deep learning. Eur J Nucl Med Mol Imaging. 2022. PMID: 35312837. doi:10.1007/s00259-022-05735-7
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。