人工智能辅助CT引导的18F-FDG心脏PET/CT全自动全心脏活性定量用于检测心脏结节病
本研究纳入连续69例疑似心脏结节病患者,采用深度学习在CT衰减图上分割心脏各腔室并自动定量18F-FDG PET活性。心脏代谢活性(CMA)预测性能最高(AUC 0.919),异常CMA(≥1)对心脏结节病的敏感性100%、特异性65%。基于CT衰减图的全自动容积定量可行、快速且预测性能高。
要点
- 深度学习可在CT衰减图上自动分割左心房、左心室、右心房、右心室、主动脉、左心室心肌和肺。
- CMA预测性能最高(AUC 0.919,95%CI 0.858-0.980),其次为VOI(AUC 0.903)、TBR(AUC 0.891)和SUVmax(AUC 0.812)。
- 异常CMA(≥1)对心脏结节病的敏感性100%、特异性65%。
核心结论
- 基于CT衰减图的全自动18F-FDG PET容积定量用于心脏结节病可行、快速且预测性能高,可提供心脏炎症的客观测量并统一心肌与背景区域的定义。
研究设计与样本
- 纳入连续接受18F-FDG PET/CT检查的疑似心脏结节病患者,共69例,平均年龄56.1±13.4岁,其中心脏结节病29例(42%)。
- 采用深度学习在CT衰减图上分割左心房、左心室、右心房、右心室、主动脉、左心室心肌和肺,并将CT定义的解剖区域自动应用于18F-FDG PET图像进行定量。
- 定量指标包括靶本比(TBR)、炎症体积(VOI)和心脏代谢活性(CMA),分别使用完整尺寸和缩小尺寸的分割进行评估。
主要发现
- CMA预测心脏结节病的AUC为0.919(95%CI 0.858-0.980),VOI为0.903(95%CI 0.834-0.971),TBR为0.891(95%CI 0.819-0.964),SUVmax为0.812(95%CI 0.701-0.923)。
- 异常CMA(≥1)对心脏结节病的敏感性为100%、特异性为65%。
- 肺部定量能够识别存在肺部异常的患者。
关键数值与推荐
- 异常CMA定义为≥1时,诊断心脏结节病的敏感性100%、特异性65%。
临床怎么用
- 原文未据此给出临床推荐。
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: [18F]-fluorodeoxyglucose ([18F]FDG) positron emission tomography (PET) plays a central role in diagnosing and managing cardiac sarcoidosis. We propose a fully automated pipeline for quantification of [18F]FDG PET activity using deep learning (DL) segmentation of cardiac chambers on computed tomography (CT) attenuation maps and evaluate quantitative approaches based on this framework. METHODS: We included consecutive patients undergoing [18F]FDG PET/CT for suspected cardiac sarcoidosis. DL segmented left atrium, left ventricle (LV), right atrium, right ventricle, aorta, LV myocardium, and lungs from CT attenuation scans. CT-defined anatomical regions were applied to [18F]FDG PET images automatically to quantify target to background ratio (TBR), volume of inflammation (VOI) and cardiometabolic activity (CMA) using full sized and shrunk segmentations. RESULTS: A total of 69 patients were included, with mean age of 56.1 ± 13.4 and cardiac sarcoidosis present in 29 (42 %). CMA had highest prediction performance (area under the receiver operating characteristic curve [AUC] .919, 95 % confidence interval [CI] .858 - .980) followed by VOI (AUC .903, 95 % CI .834 - .971), TBR (AUC .891, 95 % CI .819 - .964), and maximum standardized uptake value (AUC .812, 95 % CI .701 - .923). Abnormal CMA (≥1) had a sensitivity of 100 % and specificity 65 % for cardiac sarcoidosis. Lung quantification was able to identify patients with pulmonary abnormalities. CONCLUSION: We demonstrate that fully automated volumetric quantification of [18F]FDG PET for cardiac sarcoidosis based on CT attenuation map-derived volumetry is feasible, rapid, and has high prediction performance. This approach provides objective measurements of cardiac inflammation with consistent definition of myocardium and background region.
引用
- Miller RJ, Shanbhag A, Marcinkiewicz AM, et al. AI-enabled CT-guided end-to-end quantification of total cardiac activity in 18FDG cardiac PET/CT for detection of cardiac sarcoidosis. J Nucl Cardiol. 2025. PMID: 40127777. doi:10.1016/j.nuclcard.2025.102195
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。