文献速递心脏核医学

可解释深度学习改善医生对心肌灌注显像的判读

Explainable Deep Learning Improves Physician Interpretation of Myocardial Perfusion Imaging.
PubMed 文献 · J Nucl Med · 2022-05-05

本研究纳入240例接受心肌灌注显像(MPI)并有侵入性冠状动脉造影参考的患者,评估可解释深度学习模型(CAD-DL)辅助对医生判读的影响。医生借助CAD-DL判读的诊断准确率(AUC 0.779)显著高于无CAD-DL辅助(AUC 0.747,P=0.003)。可解释深度学习预测可实质改善医生判读,但改善幅度因判读者而异。

要点

  • 医生借助CAD-DL判读的AUC为0.779,显著高于无辅助的0.747(P=0.003)。
  • CAD-DL辅助判读的净重分类改善为17.2%(95%CI 9.2%-24.4%,P<0.001)。
  • 所有判读者借助CAD-DL均有数值上更高的准确率,AUC改善0.02-0.05。

核心结论

  • 可解释深度学习预测可使医生判读获得有意义的改善,但改善幅度因判读者而异,反映对该新技术的接受程度不同。
  • 该技术可作为医生诊断的辅助手段实施,以提高MPI的诊断准确率。

研究设计与样本

  • 选取接受MPI并以侵入性冠状动脉造影为参考的代表性患者队列,半数患者存在阻塞性冠状动脉疾病(左主干狭窄≥50%或其他冠状动脉节段狭窄≥70%)。
  • 使用先前在来自不同中心的不同人群中开发的可解释深度学习模型(CAD-DL)。
  • 3名医生先依据临床病史、负荷试验和定量灌注判读,再结合全部数据加DL结果判读,以受试者工作特征曲线下面积(AUC)评估诊断准确率。

主要发现

  • 共纳入240例患者,中位年龄65岁(四分位距58-73)。
  • 医生借助CAD-DL判读的诊断准确率(AUC 0.779)显著高于无CAD-DL辅助的判读(AUC 0.747,P=0.003),也显著高于负荷总灌注缺损(AUC 0.718,P<0.001)。
  • 在匹配特异度下,CAD-DL自主运行的敏感度高于无DL结果的判读者(P<0.001),但与借助DL结果判读的判读者相比无显著差异(P=0.122)。
  • 所有判读者借助CAD-DL均有数值上更高的准确率,AUC改善0.02-0.05,借助DL判读的总体净重分类改善为17.2%(95%CI 9.2%-24.4%,P<0.001)。

临床怎么用

  • 作者认为可解释深度学习预测可实质改善医生判读,该技术可作为医生诊断的辅助手段实施,以提高MPI的诊断准确率。

局限性

  • 改善幅度因判读者而异,反映对该新技术的接受程度不同。

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

Artificial intelligence may improve accuracy of myocardial perfusion imaging (MPI) but will likely be implemented as an aid to physician interpretation rather than an autonomous tool. Deep learning (DL) has high standalone diagnostic accuracy for obstructive coronary artery disease (CAD), but its influence on physician interpretation is unknown. We assessed whether access to explainable DL predictions improves physician interpretation of MPI. Methods: We selected a representative cohort of patients who underwent MPI with reference invasive coronary angiography. Obstructive CAD, defined as stenosis ≥50% in the left main artery or ≥70% in other coronary segments, was present in half of the patients. We used an explainable DL model (CAD-DL), which was previously developed in a separate population from different sites. Three physicians interpreted studies first with clinical history, stress, and quantitative perfusion, then with all the data plus the DL results. Diagnostic accuracy was assessed using area under the receiver-operating-characteristic curve (AUC). Results: In total, 240 patients with a median age of 65 y (interquartile range 58-73) were included. The diagnostic accuracy of physician interpretation with CAD-DL (AUC 0.779) was significantly higher than that of physician interpretation without CAD-DL (AUC 0.747, P = 0.003) and stress total perfusion deficit (AUC 0.718, P < 0.001). With matched specificity, CAD-DL had higher sensitivity when operating autonomously compared with readers without DL results (P < 0.001), but not compared with readers interpreting with DL results (P = 0.122). All readers had numerically higher accuracy with CAD-DL, with AUC improvement 0.02-0.05, and interpretation with DL resulted in overall net reclassification improvement of 17.2% (95% CI 9.2%-24.4%, P < 0.001). Conclusion: Explainable DL predictions lead to meaningful improvements in physician interpretation; however, the improvement varied across the readers, reflecting the acceptance of this new technology. This technique could be implemented as an aid to physician diagnosis, improving the diagnostic accuracy of MPI.

来源:J Nucl Med,查看原文。版权归原作者所有。

引用

  1. Miller RJH, Kuronuma K, Singh A, et al. Explainable Deep Learning Improves Physician Interpretation of Myocardial Perfusion Imaging. J Nucl Med. 2022. PMID: 35512997. doi:10.2967/jnumed.121.263686

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。