基于SPECT/CT衰减图的深度学习冠状动脉钙化评分可改善主要不良心脏事件预测
研究用2个中心6608例检查训练卷积长短期记忆深度学习模型,从SPECT/CT低剂量非门控CT衰减校正扫描自动量化冠状动脉钙化,并在另一中心2271例无已知冠心病患者中外部验证;深度学习钙化评分与专家标注一致性优秀(加权κ=0.80),且各钙化分级均为主要不良心脏事件的独立危险因素,风险分层能力与专家标注相近。
要点
- 深度学习钙化评分与专家标注分级一致性优秀,线性加权κ=0.80。
- 深度学习钙化评分获得时间不足2秒,专家标注约2.5分钟。
- 钙化1-100、101-400、>400相对钙化为0的主要不良心脏事件风险比分别为2.20、4.58、5.92。
核心结论
- 深度学习从SPECT/CT衰减图得到的冠状动脉钙化评分与专家标注一致性良好,提供相似的风险分层并可自动获得。
- 与单独SPECT心肌灌注相比,深度学习钙化评分改善了相当比例患者的分类。
研究设计与样本
- 研究训练卷积长短期记忆深度学习模型在CT衰减校正扫描上自动量化冠状动脉钙化,训练集为2个中心6608例检查。
- 模型在另一中心2271例无已知冠状动脉疾病患者组成的外部队列中评估。
- 比较深度学习与专家标注钙化评分的一致性,并用多变量Cox模型(校正年龄、性别、既往病史、灌注和射血分数)及净重分类指数评估主要不良心脏事件与钙化分级(0、1-100、101-400、>400)的关联。
主要发现
- 外部测试人群中,深度学习钙化评分为0者908例(40.0%)、1-100者596例(26.2%)、101-400者354例(15.6%)、>400者413例(18.2%)。
- 深度学习钙化与专家标注的钙化分级一致性优秀(线性加权κ=0.80)。
- 深度学习钙化获得时间不足2秒,专家钙化标注约2.5分钟。
- 以钙化为0为参照,钙化1-100的主要不良心脏事件风险比2.20(95%CI 1.54-3.14,P<0.001),101-400为4.58(95%CI 3.23-6.48,P<0.001),>400为5.92(95%CI 4.27-8.22,P<0.001)。
- 深度学习钙化总体净重分类指数为0.494,与专家标注钙化(0.503)相近。
关键数值与推荐
- 钙化分级采用0、1-100、101-400、>400四类。
- 深度学习与专家标注钙化分级的一致性为线性加权κ=0.80。
- 深度学习钙化总体净重分类指数0.494,专家标注钙化0.503。
临床怎么用
- 原文结论认为深度学习钙化评分与专家标注一致性良好、提供相似风险分层且可自动获得,并可改善相当比例患者相较单独SPECT心肌灌注的分类。
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
Low-dose ungated CT attenuation correction (CTAC) scans are commonly obtained with SPECT/CT myocardial perfusion imaging. Despite the characteristically low image quality of CTAC, deep learning (DL) can potentially quantify coronary artery calcium (CAC) from these scans in an automatic manner. We evaluated CAC quantification derived with a DL model, including correlation with expert annotations and associations with major adverse cardiovascular events (MACE). Methods: We trained a convolutional long short-term memory DL model to automatically quantify CAC on CTAC scans using 6,608 studies (2 centers) and evaluated the model in an external cohort of patients without known coronary artery disease (n = 2,271) obtained in a separate center. We assessed agreement between DL and expert annotated CAC scores. We also assessed associations between MACE (death, revascularization, myocardial infarction, or unstable angina) and CAC categories (0, 1-100, 101-400, or >400) for scores manually derived by experienced readers and scores obtained fully automatically by DL using multivariable Cox models (adjusted for age, sex, past medical history, perfusion, and ejection fraction) and net reclassification index. Results: In the external testing population, DL CAC was 0 in 908 patients (40.0%), 1-100 in 596 (26.2%), 100-400 in 354 (15.6%), and >400 in 413 (18.2%). Agreement in CAC category by DL CAC and expert annotation was excellent (linear weighted κ, 0.80), but DL CAC was obtained automatically in less than 2 s compared with about 2.5 min for expert CAC. DL CAC category was an independent risk factor for MACE with hazard ratios in comparison to a CAC of zero: CAC of 1-100 (2.20; 95% CI, 1.54-3.14; P < 0.001), CAC of 101-400 (4.58; 95% CI, 3.23-6.48; P < 0.001), and CAC of more than 400 (5.92; 95% CI, 4.27-8.22; P < 0.001). Overall, the net reclassification index was 0.494 for DL CAC, which was similar to expert annotated CAC (0.503). Conclusion: DL CAC from SPECT/CT attenuation maps agrees well with expert CAC annotations and provides a similar risk stratification but can be obtained automatically. DL CAC scores improved classification of a significant proportion of patients as compared with SPECT myocardial perfusion alone.
引用
- Miller RJH, Pieszko K, Shanbhag A, et al. Deep Learning Coronary Artery Calcium Scores from SPECT/CT Attenuation Maps Improve Prediction of Major Adverse Cardiac Events. J Nucl Med. 2022. PMID: 36207138. doi:10.2967/jnumed.122.264423
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。