文献速递皮肤肿瘤

基于皮肤镜图像评估黑色素瘤厚度:一项开放、基于网络的国际诊断研究

Assessment of melanoma thickness based on dermoscopy images: an open, web-based, international, diagnostic study.
PubMed 文献 · J Eur Acad Dermatol Venereol · 2022-07-26

该开放网络国际诊断读图研究纳入1456张黑色素瘤皮肤镜图像,由438名国际读者完成22314次判读,评估区分原位与侵袭性黑色素瘤及估计Breslow厚度的准确性,并与两种卷积神经网络比较。读者与CNN预测厚度准确性为一般至中等,读者对薄(≤1.0 mm含原位)与厚(>1.0 mm)黑色素瘤区分最准确;读者集体在区分原位与侵袭性黑色素瘤上优于从头训练的CNN但不优于预训练CNN。

要点

  • 438名国际读者对22314次读图判读黑色素瘤厚度总体准确性为56.4%(95%CI 55.7%-57.0%)。
  • 读者对≤1.0 mm黑色素瘤(含原位)厚度预测准确率为85.9%(95%CI 85.4%-86.4%)。
  • 读者集体区分原位与侵袭性黑色素瘤优于从头训练的CNN但不优于预训练CNN。

核心结论

  • 使用皮肤镜图像,读者和CNN预测黑色素瘤厚度的准确性为一般至中等。
  • 读者对薄(≤1.0 mm含原位)与厚(>1.0 mm)黑色素瘤的区分最准确。

研究设计与样本

  • 开放、基于网络、国际诊断读图研究,使用在线平台,在线挑战于2021年5月10日开放、2021年7月19日关闭(共71天)。
  • 纳入1456张黑色素瘤皮肤镜图像(788张原位黑色素瘤;474张≤1.0 mm黑色素瘤和194张>1.0 mm黑色素瘤)。
  • 测试集包含277张原位黑色素瘤和246张侵袭性黑色素瘤图像,用于比较读者与CNN。
  • 分析438名国际读者的22314次判读。

主要发现

  • 黑色素瘤厚度总体准确性为56.4%(95%CI 55.7%-57.0%)。
  • 原位黑色素瘤准确性为63.4%(95%CI 62.5%-64.2%),侵袭性黑色素瘤准确性为71.0%(95%CI 70.3%-72.1%)。
  • 读者对≤1.0 mm黑色素瘤(含原位)厚度预测准确率为85.9%(95%CI 85.4%-86.4%),对>1.0 mm黑色素瘤为70.8%(95%CI 69.2%-72.5%)。
  • 读者集体在区分原位与侵袭性黑色素瘤上优于从头训练的CNN,但不优于预训练CNN。

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

BACKGROUND: Preoperative assessment of whether a melanoma is invasive or in situ (MIS) is a common task that might have important implications for triage, prognosis and the selection of surgical margins. Several dermoscopic features suggestive of melanoma have been described, but only a few of these are useful in differentiating MIS from invasive melanoma. OBJECTIVE: The primary aim of this study was to evaluate how accurately a large number of international readers, individually as well as collectively, were able to discriminate between MIS and invasive melanomas as well as estimate the Breslow thickness of invasive melanomas based on dermoscopy images. The secondary aim was to compare the accuracy of two machine learning convolutional neural networks (CNNs) and the collective reader response. METHODS: We conducted an open, web-based, international, diagnostic reader study using an online platform. The online challenge opened on 10 May 2021 and closed on 19 July 2021 (71 days) and was advertised through several social media channels. The investigation included, 1456 dermoscopy images of melanomas (788 MIS; 474 melanomas ≤1.0 mm and 194 >1.0 mm). A test set comprising 277 MIS and 246 invasive melanomas was used to compare readers and CNNs. RESULTS: We analysed 22 314 readings by 438 international readers. The overall accuracy (95% confidence interval) for melanoma thickness was 56.4% (55.7%-57.0%), 63.4% (62.5%-64.2%) for MIS and 71.0% (70.3%-72.1%) for invasive melanoma. Readers accurately predicted the thickness in 85.9% (85.4%-86.4%) of melanomas ≤1.0 mm (including MIS) and in 70.8% (69.2%-72.5%) of melanomas >1.0 mm. The reader collective outperformed a de novo CNN but not a pretrained CNN in differentiating MIS from invasive melanoma. CONCLUSIONS: Using dermoscopy images, readers and CNNs predict melanoma thickness with fair to moderate accuracy. Readers most accurately discriminated between thin (≤1.0 mm including MIS) and thick melanomas (>1.0 mm).

来源:J Eur Acad Dermatol Venereol,查看原文。版权归原作者所有。

引用

  1. Polesie S, Gillstedt M, Kittler H, et al. Assessment of melanoma thickness based on dermoscopy images: an open, web-based, international, diagnostic study. J Eur Acad Dermatol Venereol. 2022. PMID: 35841304. doi:10.1111/jdv.18436

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。