文献速递乳腺MR

Kaiser评分联合ADC与机器学习建模在乳腺病变MRI鉴别诊断中的评估

Assessment of breast lesions by the Kaiser score for differential diagnosis on MRI: the added value of ADC and machine learning modeling.
PubMed 文献 · Eur Radiol · 2022-06-21

研究纳入402个恶性与257个良性乳腺病变,由两名放射科医师赋Kaiser评分(KS)。将KS>4且ADC>1.4×10⁻³ mm²/s的病变KS减4分为KS+。以ADC二分类修正KS可提高特异度至68.5%,但敏感度降至95.5%。机器学习模型AUC与KS相当, logistic回归模型在维持敏感度97.3%时特异度达65.3%。

要点

  • KS+较KS特异度提升9.4%–9.7%,但敏感度下降1.5%–1.8%。
  • 机器学习模型AUC与KS相当,均显著高于ADC单独使用。
  • KS+在同等敏感度下未能提高特异度,原始KS仍是稳健方法。

核心结论

  • 使用二分类ADC修正KS为KS+可提高特异度,但以降低敏感度为代价。
  • 机器学习算法可将ADC作为连续变量建模,构建更准确的诊断模型。
  • 在相同敏感度水平下,KS+与原KS特异度相当,KS+的实际帮助可能有限,原始KS仍为优秀的稳健诊断方法。

研究设计与样本

  • 研究纳入402个恶性病变和257个良性病变的数据集。
  • 由两名放射科医师赋Kaiser评分(KS)。
  • 若KS>4的病变ADC>1.4×10⁻³ mm²/s,则KS减4分成为KS+。
  • 使用5种机器学习算法以KS和ADC值训练诊断模型。
  • 采用ROC分析评估性能,并用DeLong检验比较。

诊断标准与关键数值

  • KS的敏感度为97.3%,特异度为59.1%。
  • KS+的敏感度为95.5%,特异度显著提高至68.5%(p<0.0001)。
  • ADC≤1.4×10⁻³ mm²/s时,AUC为0.837,显著低于KS、KS+及所有ML模型的AUC(0.883–0.921,p<0.0001)。
  • 逻辑回归模型在敏感度97.3%时特异度为65.3%,较KS避免16个假阳性(p=0.0015)。
  • KS+较KS特异度提高9.4%–9.7%,敏感度降低1.5%–1.8%,准确率提高2.6%–2.9%。

临床应用与阅片要点

  • 作者认为,使用二分类ADC修正KS为KS+可提高特异度,但以降低敏感度为代价。
  • 作者认为,机器学习算法可将ADC作为连续变量建模以构建更准确的诊断模型。
  • 作者认为,在相同敏感度水平下KS+与原KS特异度相当,KS+的实际帮助可能有限,原始KS仍为优秀的稳健诊断方法。

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)。

英文原文(摘要)· 点击展开

OBJECTIVES: To evaluate the diagnostic performance of Kaiser score (KS) adjusted with the apparent diffusion coefficient (ADC) (KS+) and machine learning (ML) modeling.

METHODS: A dataset of 402 malignant and 257 benign lesions was identified. Two radiologists assigned the KS. If a lesion with KS > 4 had ADC > 1.4 × 10-3 mm2/s, the KS was reduced by 4 to become KS+. In order to consider the full spectrum of ADC as a continuous variable, the KS and ADC values were used to train diagnostic models using 5 ML algorithms. The performance was evaluated using the ROC analysis, compared by the DeLong test. The sensitivity, specificity, and accuracy achieved using the threshold of KS > 4, KS+ > 4, and ADC ≤ 1.4 × 10-3 mm2/s were obtained and compared by the McNemar test.

RESULTS: The ROC curves of KS, KS+, and all ML models had comparable AUC in the range of 0.883-0.921, significantly higher than that of ADC (0.837, p < 0.0001). The KS had sensitivity = 97.3% and specificity = 59.1%; and the KS+ had sensitivity = 95.5% with significantly improved specificity to 68.5% (p < 0.0001). However, when setting at the same sensitivity of 97.3%, KS+ could not improve specificity. In ML analysis, the logistic regression model had the best performance. At sensitivity = 97.3% and specificity = 65.3%, i.e., compared to KS, 16 false-positives may be avoided without affecting true cancer diagnosis (p = 0.0015).

CONCLUSION: Using dichotomized ADC to modify KS to KS+ can improve specificity, but at the price of lowered sensitivity. Machine learning algorithms may be applied to consider the ADC as a continuous variable to build more accurate diagnostic models.

KEY POINTS: • When using ADC to modify the Kaiser score to KS+, the diagnostic specificity according to the results of two independent readers was improved by 9.4-9.7%, at the price of slightly degraded sensitivity by 1.5-1.8%, and overall had improved accuracy by 2.6-2.9%. • When the KS and the continuous ADC values were combined to train models by machine learning algorithms, the diagnostic specificity achieved by the logistic regression model could be significantly improved from 59.1 to 65.3% (p = 0.0015), while maintaining at the high sensitivity of KS = 97.3%, and thus, the results demonstrated the potential of ML modeling to further evaluate the contribution of ADC. • When setting the sensitivity at the same levels, the modified KS+ and the original KS have comparable specificity; therefore, KS+ with consideration of ADC may not offer much practical help, and the original KS without ADC remains as an excellent robust diagnostic method.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Chen, Zhao, Liu, et al. Assessment of breast lesions by the Kaiser score for differential diagnosis on MRI: the added value of ADC and machine learning modeling. Eur Radiol. 2022. PMID: 35726099. doi:10.1007/s00330-022-08899-w

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。