深度学习自动分割疑似心脏淀粉样变性患者骨显像SPECT/CT中的心肌
研究利用深度学习在99mTc-PYP或HDP SPECT/CT上自动分割心肌并检测转甲状腺素蛋白心脏淀粉样心肌病(ATTR-CM)的心肌骨摄取。在Brigham and Women's Hospital的77例主要队列和University of Pennsylvania的93例验证队列中,模型分割与人工勾画相当(p=0.63),主要队列自动定量平均HBP比值阳性组3.1±1.4 vs 阴性组1.4±0.2(p<0.01),模型准确率主要队列100%、验证队列98%。作者认为已开发出高精度自动分割并识别提示ATTR-CM心肌摄取的诊断工具。
要点
- 深度学习自动分割与人工勾画相当(p=0.63)。
- 主要队列阳性摄取平均HBP比值3.1±1.4 vs 阴性1.4±0.2(p<0.01)。
- 模型准确率主要队列100%、验证队列98%。
核心结论
- 作者认为已开发出高精度自动分割并识别提示ATTR-CM心肌摄取的诊断工具。
研究设计与样本
- 在Brigham and Women's Hospital识别77例主要队列、在University of Pennsylvania连续纳入93例验证队列,分别行99mTc-PYP和HDP SPECT/CT评估ATTR-CM。
- 在CT轴位切片上从心室尖到隆突勾画全局心脏感兴趣区(ROI),心肌图像视觉评分为0级(无摄取)、1级(摄取低于肋骨)、2级(摄取等于肋骨)、3级(摄取高于肋骨)。
- 采用2D U-net架构开发CT扫描的全心脏分割,摄取通过计算心脏与血池(HBP)比值确定,即总心脏区域最大计数值与最上层ROI最大计数值之比。
主要发现
- 深度学习与真实分割相当(p=0.63)。
- 42例(55%)患者视觉评估存在异常心肌摄取。
- 主要队列自动定量平均HBP比值:阳性心肌摄取患者3.1±1.4 vs 阴性患者1.4±0.2(p<0.01)。
- 模型准确率主要队列100%、验证队列98%。
关键数值与推荐
- 心肌摄取视觉评分0级为无摄取、1级为摄取低于肋骨、2级为摄取等于肋骨、3级为摄取高于肋骨。
- HBP比值为总心脏区域最大计数值与最上层ROI最大计数值之比。
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: We employed deep learning to automatically detect myocardial bone-seeking uptake as a marker of transthyretin cardiac amyloid cardiomyopathy (ATTR-CM) in patients undergoing 99mTc-pyrophosphate (PYP) or hydroxydiphosphonate (HDP) single-photon emission computed tomography (SPECT)/computed tomography (CT). METHODS: We identified a primary cohort of 77 subjects at Brigham and Women's Hospital and a validation cohort of 93 consecutive patients imaged at the University of Pennsylvania who underwent SPECT/CT with PYP and HDP, respectively, for evaluation of ATTR-CM. Global heart regions of interest (ROIs) were traced on CT axial slices from the apex of the ventricle to the carina. Myocardial images were visually scored as grade 0 (no uptake), 1 (uptake<ribs), 2 (uptake=ribs), and 3 (uptake>ribs). A 2D U-net architecture was used to develop whole-heart segmentations for CT scans. Uptake was determined by calculating a heart-to-blood pool (HBP) ratio between the maximal counts value of the total heart region and the maximal counts value of the most superior ROI. RESULTS: Deep learning and ground truth segmentations were comparable (p=0.63). A total of 42 (55%) patients had abnormal myocardial uptake on visual assessment. Automated quantification of the mean HBP ratio in the primary cohort was 3.1±1.4 versus 1.4±0.2 (p<0.01) for patients with positive and negative cardiac uptake, respectively. The model had 100% accuracy in the primary cohort and 98% in the validation cohort. CONCLUSION: We have developed a highly accurate diagnostic tool for automatically segmenting and identifying myocardial uptake suggestive of ATTR-CM.
引用
- Bhattaru A, Rojulpote C, Vidula M, et al. Deep learning approach for automated segmentation of myocardium using bone scintigraphy single-photon emission computed tomography/computed tomography in patients with suspected cardiac amyloidosis. J Nucl Cardiol. 2024. PMID: 38307160. doi:10.1016/j.nuclcard.2024.101809
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。