文献速递胸部DR

胸部X线摄影深度学习自动检测算法的重测可重复性

Test-retest reproducibility of a deep learning-based automatic detection algorithm for the chest radiograph.
PubMed 文献 · Eur Radiol · 2020-01-03

本回顾性研究纳入2017年因肺结节行切除术的患者169例,利用短期间隔内无变化的术前胸部X线片分析基于深度学习的自动检测算法(DLAD)的重测可重复性。结果显示异常分数中位差异为1-2%,组内相关系数(ICC)为0.83-0.90,95%一致性界限约±30%;重测变异与实性部分大小和结节清晰度呈负相关。DLAD对模拟位置变化稳健,但对后处理相对不稳健,不清晰结节可能导致模型输出波动和误分类。

要点

  • DLAD在胸部X线片重测中总体稳健,异常分数中位差异1-2%,ICC 0.83-0.90。
  • 重测变异与实性部分大小(β=-0.50)和结节清晰度(β=-0.94)负相关。
  • 高特异度阈值46%下,8.9%(15/169)病例出现分类不一致(p=0.04)。

核心结论

  • DLAD对重测变异总体稳健,但不清晰结节可能导致模型输出波动和后续误分类。

研究设计与样本

  • 回顾性研究纳入2017年因肺结节行切除术的患者169例(中位年龄65岁,男性91例),使用短期间隔内无变化的术前胸部X线片,分析DLAD的重测可重复性。

诊断标准与关键数值

  • 异常分数中位差异为1-2%,ICC范围为0.83-0.90,95%一致性界限约±30%。

临床应用与阅片要点

  • 高特异度阈值46%下,重测胸片间分类不一致率为8.9%(15/169;p=0.04)。

局限性

  • 回顾性研究。
  • 不清晰结节可能导致模型输出波动和后续误分类。

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)。

英文原文(摘要)· 点击展开

OBJECTIVES: To perform test-retest reproducibility analyses for deep learning-based automatic detection algorithm (DLAD) using two stationary chest radiographs (CRs) with short-term intervals, to analyze influential factors on test-retest variations, and to investigate the robustness of DLAD to simulated post-processing and positional changes.

METHODS: This retrospective study included patients with pulmonary nodules resected in 2017. Preoperative CRs without interval changes were used. Test-retest reproducibility was analyzed in terms of median differences of abnormality scores, intraclass correlation coefficients (ICC), and 95% limits of agreement (LoA). Factors associated with test-retest variation were investigated using univariable and multivariable analyses. Shifts in classification between the two CRs were analyzed using pre-determined cutoffs. Radiograph post-processing (blurring and sharpening) and positional changes (translations in x- and y-axes, rotation, and shearing) were simulated and agreement of abnormality scores between the original and simulated CRs was investigated.

RESULTS: Our study analyzed 169 patients (median age, 65 years; 91 men). The median difference of abnormality scores was 1-2% and ICC ranged from 0.83 to 0.90. The 95% LoA was approximately ± 30%. Test-retest variation was negatively associated with solid portion size (β, - 0.50; p = 0.008) and good nodule conspicuity (β, - 0.94; p < 0.001). A small fraction (15/169) showed discordant classifications when the high-specificity cutoff (46%) was applied to the model outputs (p = 0.04). DLAD was robust to the simulated positional change (ICC, 0.984, 0.996), but relatively less robust to post-processing (ICC, 0.872, 0.968).

CONCLUSIONS: DLAD was robust to the test-retest variation. However, inconspicuous nodules may cause fluctuations of the model output and subsequent misclassifications.

KEY POINTS: • The deep learning-based automatic detection algorithm was robust to the test-retest variation of the chest radiographs in general. • The test-retest variation was negatively associated with solid portion size and good nodule conspicuity. • High-specificity cutoff (46%) resulted in discordant classifications of 8.9% (15/169; p = 0.04) between the test-retest radiographs.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Kim H, Park CM, Goo JM, et al. Test-retest reproducibility of a deep learning-based automatic detection algorithm for the chest radiograph. Eur Radiol. 2020. PMID: 31900698. doi:10.1007/s00330-019-06589-8

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。