文献速递心脏核医学

深度学习解读SPECT室壁运动

Interpretation of SPECT wall motion with deep learning.
PubMed 文献 · J Nucl Cardiol · 2024-05-07

研究纳入1038例接受静息心电图门控SPECT和超声心动图的患者,以超声心动图为真值训练深度学习模型评估室壁运动。深度学习模型的AUC为.82(95%CI:.79-.85)、准确率.88,高于人工判读的AUC .77(95%CI:.73-.81)、准确率.82(P<.001)及定量参数的AUC .74(95%CI:.66-.81)、准确率.78(P<.05)。

要点

  • 深度学习模型诊断室壁运动的AUC .82、准确率.88,高于人工判读(AUC .77、准确率.82,P<.001)。
  • 深度学习模型AUC和准确率亦高于定量参数(AUC .74、准确率.78,P<.05)。
  • 深度学习模型可在30秒内生成结果并提供初步解读。

核心结论

  • 与当前人工判读和定量参数诊断相比,深度学习可用于改善静息SPECT室壁运动的解读。

研究设计与样本

  • 共纳入1038例接受静息心电图门控SPECT和超声心动图的患者,以超声心动图为真值。
  • 训练深度学习模型1预测室壁运动异常的概率;其中317例用于训练深度学习模型2评估区域室壁运动。
  • 采用10折交叉验证,将深度学习模型的诊断性能与人工判读及定量参数进行比较。

主要发现

  • 深度学习模型的AUC为.82(95%CI:.79-.85)、准确率为.88,高于人工判读的AUC .77(95%CI:.73-.81)、准确率.82(P<.001)。
  • 深度学习模型的AUC和准确率高于定量参数的AUC .74(95%CI:.66-.81)、准确率.78(P<.05)。
  • 净重分类指数(NRI)为7.7%。
  • 深度学习模型在每节段和每血管 Territory 诊断的AUC和准确率亦高于人工判读。
  • 深度学习模型在30秒内生成结果,具有可操作的图形用户界面(GUI),因此可提供初步解读。

关键数值与推荐

  • 深度学习模型1以超声心动图为真值训练预测室壁运动异常概率;模型2基于317例患者训练评估区域室壁运动。
  • 采用10折交叉验证评估模型性能。

临床怎么用

  • 原文未据此给出推荐。

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

OBJECTIVES: We sought to develop a novel deep learning (DL) workflow to interpret single-photon emission computed tomography (SPECT) wall motion. BACKGROUND: Wall motion assessment with SPECT is limited by image temporal and spatial resolution. Visual interpretation of wall motion can be subjective and prone to error. Artificial intelligence (AI) may improve accuracy of wall motion assessment. METHODS: A total of 1038 patients undergoing rest electrocardiogram (ECG)-gated SPECT and echocardiography were included. Using echocardiography as truth, a DL-model (DL-model 1) was trained to predict the probability of abnormal wall motion. Of the 1038 patients, 317 were used to train a DL-model (DL-model 2) to assess regional wall motion. A 10-fold cross-validation was adopted. Diagnostic performance of DL was compared with human readers and quantitative parameters. RESULTS: The area under the receiver operating characteristic curve (AUC) and accuracy (ACC) of DL model (AUC: .82 [95% CI: .79-.85]; ACC: .88) were higher than human (AUC: .77 [95% CI: .73-.81]; ACC: .82; P < .001) and quantitative parameter (AUC: .74 [95% CI: .66-.81]; ACC: .78; P < .05). The net reclassification index (NRI) was 7.7%. The AUC and accuracy of DL model for per-segment and per-vessel territory diagnosis were also higher than human reader. The DL model generated results within 30 seconds with operable guided user interface (GUI) and therefore could provide preliminary interpretation. CONCLUSIONS: DL can be used to improve interpretation of rest SPECT wall motion as compared with current human readers and quantitative parameter diagnosis.

来源:J Nucl Cardiol,查看原文。版权归原作者所有。

引用

  1. Zhang Y, Bos E, Clarkin O, et al. Interpretation of SPECT wall motion with deep learning. J Nucl Cardiol. 2024. PMID: 38723886. doi:10.1016/j.nuclcard.2024.101881

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。