文献速递皮肤肿瘤

皮肤镜逆向方法显著提升黑素瘤原位癌诊断准确率

The dermoscopic inverse approach significantly improves the accuracy of human readers for lentigo maligna diagnosis.
PubMed 文献 · J Am Acad Dermatol · 2020-06-24

研究比较了经典模式分析与逆向方法训练对早期黑素瘤原位癌诊断准确率的影响。结果显示逆向方法训练后平均敏感度从51.5%提升至83.6%,正确率从62.1%提升至78.5%,且超过卷积神经网络表现读者比例从6.4%增至53.9%。

要点

  • 逆向方法基于缺乏色素性日光性角化病和日光性黑子/扁平脂溢性角化病优势模式来诊断早期黑素瘤原位癌
  • 训练后平均敏感度从51.5%升至83.6%,正确率从62.1%升至78.5%
  • 逆向方法训练后53.9%读者表现优于卷积神经网络

核心结论

  • 在经典模式分析基础上增加逆向方法可显著提高读者对早期黑素瘤原位癌的诊断敏感度

研究设计与样本

  • 采用组织病理学确诊的黑素瘤原位癌、色素性日光性角化病和日光性黑子/扁平脂溢性角化病的临床和皮肤镜图像
  • 皮肤镜大师班参与者在基线、模式分析训练后和逆向方法训练后三个时间点对病变进行分类
  • 比较三个时间点的诊断性能并与训练过的卷积神经网络比较

主要发现

  • 未训练时黑素瘤原位癌平均敏感度为51.5%,模式分析训练后升至56.7%,逆向方法学习后升至83.6%
  • 三个时间点平均正确率分别为62.1%、65.5%和78.5%
  • 表现优于卷积神经网络的读者比例分别为6.4%、15.4%和53.9%

关键数值与推荐

  • 逆向方法基于缺乏色素性日光性角化病和日光性黑子/扁平脂溢性角化病的优势模式来诊断早期黑素瘤原位癌

临床怎么用

  • 在经典模式分析基础上增加逆向方法训练可提升临床医生对早期黑素瘤原位癌的诊断敏感度

局限性

  • 实验设置限制
  • 仅纳入组织病理学确诊的病变

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: A recently introduced dermoscopic method for the diagnosis of early lentigo maligna (LM) is based on the absence of prevalent patterns of pigmented actinic keratosis and solar lentigo/flat seborrheic keratosis. We term this the inverse approach. OBJECTIVE: To determine whether training on the inverse approach increases the diagnostic accuracy of readers compared to classic pattern analysis. METHODS: We used clinical and dermoscopic images of histopathologically diagnosed LMs, pigmented actinic keratoses, and solar lentigo/flat seborrheic keratoses. Participants in a dermoscopy masterclass classified the lesions at baseline and after training on pattern analysis and the inverse approach. We compared their diagnostic performance among the 3 timepoints and to that of a trained convolutional neural network. RESULTS: The mean sensitivity for LM without training was 51.5%; after training on pattern analysis, it increased to 56.7%; and after learning the inverse approach, it increased to 83.6%. The mean proportions of correct answers at the 3 timepoints were 62.1%, 65.5, and 78.5%. The percentages of readers outperforming the convolutional neural network were 6.4%, 15.4%, and 53.9%, respectively. LIMITATIONS: The experimental setting and the inclusion of histopathologically diagnosed lesions only. CONCLUSIONS: The inverse approach, added to the classic pattern analysis, significantly improves the sensitivity of human readers for early LM diagnosis.

来源:J Am Acad Dermatol,查看原文。版权归原作者所有。

引用

  1. Lallas A, Lallas K, Tschandl P, et al. The dermoscopic inverse approach significantly improves the accuracy of human readers for lentigo maligna diagnosis. J Am Acad Dermatol. 2020. PMID: 32592885. doi:10.1016/j.jaad.2020.06.085

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。