Shanbhag Aakash D, Miller Robert J H, Lemley Mark, Kavanagh Paul, Liang Joanna X, Marcinkiewicz Anna M, Builoff Valerie, Van Kriekinge Serge, Ruddy Terrence D, Fish Mathews B, Einstein Andrew J, Martins Monica, Halcox Julian P, Kaufmann Philipp A, Buckley Christopher, Bateman Timothy M, Berman Daniel S, Dey Damini, Slomka Piotr J
Division of Artificial Intelligence in Medicine, Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, California, USA; Department of Imaging, Cedars-Sinai Medical Center, Los Angeles, California, USA; Department of Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California, USA; Signal and Image Processing Institute, Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, California, USA.
Department of Cardiac Sciences, University of Calgary, Calgary, Alberta, Canada.
JACC Cardiovasc Imaging. 2025 Aug 1. doi: 10.1016/j.jcmg.2025.06.010.
Single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) uses computed tomography (CT)-based attenuation correction (AC) to improve diagnostic accuracy. Deep learning (DL) has the potential to generate synthetic AC images, as an alternative to CT-based AC.
This study evaluated whether DL-generated synthetic SPECT images could enhance accuracy of conventional SPECT MPI.
Study investigators developed a DL model in a multicenter cohort of 4,894 patients from 4 sites to generate simulated SPECT AC images (DeepAC). The model was externally validated in 746 patients from 72 sites in a clinical trial (A Phase 3 Multicenter Study to Assess PET Imaging of Flurpiridaz F 18 Injection in Patients With CAD; NCT01347710) and in 320 patients from another external site. In the first external cohort, the study assessed the diagnostic accuracy for obstructive coronary artery disease (CAD)-defined as left main coronary artery stenosis ≥50% or ≥70% in other vessels-for total perfusion deficit (TPD). In the latter, the study completed change analysis and compared quantitative scores for AC, DeepAC, and nonattenuation correction (NC) with clinical scores.
In the first external cohort (mean age, 63 ± 9.5 years; 69.0% male), 206 patients (27.6%) had obstructive CAD. The area under the receiver-operating characteristic curve (AUC) of DeepAC TPD (0.77; 95% CI: 0.73-0.81) was higher than the NC TPD (AUC: 0.73; 95% CI: 0.69-0.77; P < 0.001). In the second external cohort, DeepAC quantitative scores had closer agreement with actual AC scores compared with NC.
In a multicenter external cohort, DeepAC improved prediction performance for obstructive CAD. This approach could enhance diagnostic accuracy in facilities using conventional SPECT systems without requiring additional equipment, imaging time, or radiation exposure.
单光子发射计算机断层扫描（SPECT）心肌灌注成像（MPI）使用基于计算机断层扫描（CT）的衰减校正（AC）来提高诊断准确性。深度学习（DL）有潜力生成合成AC图像，作为基于CT的AC的替代方法。
本研究评估DL生成的合成SPECT图像是否能提高传统SPECT MPI的准确性。
研究人员在来自4个地点的4894例患者的多中心队列中开发了一个DL模型，以生成模拟SPECT AC图像（DeepAC）。该模型在一项临床试验（一项评估氟吡达唑F 18注射液在CAD患者中的PET成像的3期多中心研究；NCT01347710）中来自72个地点的746例患者以及另一个外部地点的320例患者中进行了外部验证。在第一个外部队列中，研究评估了阻塞性冠状动脉疾病（CAD）（定义为左主干冠状动脉狭窄≥50%或其他血管狭窄≥70%）的总灌注缺损（TPD）的诊断准确性。在后者中，研究完成了变化分析，并将AC、DeepAC和无衰减校正（NC）的定量评分与临床评分进行了比较。
在第一个外部队列（平均年龄，63±9.5岁；69.0%为男性）中，206例患者（27.6%）患有阻塞性CAD。DeepAC TPD的受试者操作特征曲线下面积（AUC）（0.77；95%CI：0.73 - 0.81）高于NC TPD（AUC：（0.73；95%CI：0.69 - 0.77；P < 0.001）。在第二个外部队列中，与NC相比，DeepAC定量评分与实际AC评分的一致性更高。
在多中心外部队列中，DeepAC提高了阻塞性CAD的预测性能。这种方法可以在不使用额外设备、成像时间或辐射暴露的情况下，提高使用传统SPECT系统的机构的诊断准确性。
