文献速递骨软组织肉瘤与黑色素瘤

皮肤镜图像比例尺与黑色素瘤CNN诊断准确性关联

Association between different scale bars in dermoscopic images and diagnostic performance of a market-approved deep learning convolutional neural network for melanoma recognition.
PubMed 文献 · Eur J Cancer · 2021-01-16

该横断面分析评估市场批准的CNN(Moleanalyzer-pro®)对同一130个黑素细胞病变(107痣、23黑色素瘤)的七组皮肤镜图像(含不同厂商比例尺或不含比例尺)的诊断表现。结果显示比例尺未显著改变敏感度,但四种比例尺降低特异度,两种比例尺降低ROC AUC,提示比例尺可能增加假阳性。

要点

  • 比例尺未显著改变CNN敏感度,但可降低特异度并增加假阳性。
  • 部分比例尺显著降低ROC AUC,影响整体诊断准确性。
  • 建议避免在供CNN分析的图像中使用比例尺,除非有抵消措施。

核心结论

  • 皮肤镜图像中叠加的比例尺可能损害CNN诊断准确性,主要通过增加假阳性诊断率。
  • 建议避免在供CNN分析的图像中使用比例尺,除非实施特定抵消措施。

研究设计与样本

  • 横断面分析,使用市场批准的CNN(Moleanalyzer-pro®)分析同一130个黑素细胞病变(107痣、23黑色素瘤)的七组皮肤镜图像。
  • 图像包括六组含不同厂商比例尺和一组无比例尺对照,共910张图像。

主要发现

  • 无比例尺图像中,CNN敏感度为87.0%[67.9%-95.5%],特异度为87.9%[80.3%-92.8%],ROC AUC为0.953[0.914-0.992]。
  • 比例尺未显著改变敏感度(范围87%-95.7%,所有p≥1.0)。
  • 四种比例尺导致特异度下降(范围0%-43.9%,所有p<0.001)。
  • 两种比例尺显著降低ROC AUC(范围0.520-0.848,均p≤0.042)。

临床怎么用

  • 临床使用CNN分析皮肤镜图像时,应避免叠加比例尺,除非有抵消措施。

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: Studies systematically unravelling possible causes for false diagnoses of deep learning convolutional neural networks (CNNs) are scarce, yet needed before broader application. OBJECTIVES: The objective of the study was to investigate whether scale bars in dermoscopic images are associated with the diagnostic accuracy of a market-approved CNN. METHODS: This cross-sectional analysis applied a CNN trained with more than 150,000 images (Moleanalyzer-pro®, FotoFinder Systems Inc., Bad Birnbach, Germany) to investigate seven dermoscopic image sets depicting the same 130 melanocytic lesions (107 nevi, 23 melanomas) without or with digitally superimposed scale bars of different manufacturers. Sensitivity, specificity and area under the curve (AUC) of receiver operating characteristics (ROC) for the CNN's binary classification of images with or without superimposed scale bars were assessed. RESULTS: Six dermoscopic image sets with different scale bars and one control set without scale bars (overall 910 images) were submitted to CNN analysis. In images without scale bars, the CNN attained a sensitivity [95% confidence interval] of 87.0% [67.9%-95.5%] and a specificity of 87.9% [80.3%-92.8%]. ROC AUC was 0.953 [0.914-0.992]. Scale bars were not associated with significant changes in sensitivity (range 87%-95.7%, all p ≥ 1.0). However, four scale bars induced a decrease of the CNN's specificity (range 0%-43.9%, all p < 0.001). Moreover, ROC AUC was significantly reduced by two scale bars (range 0.520-0.848, both p ≤ 0.042). CONCLUSIONS: Superimposed scale bars in dermoscopic images may impair the CNN's diagnostic accuracy, mostly by increasing the rate of the false-positive diagnoses. We recommend avoiding scale bars in images intended for CNN analysis unless specific measures counteracting effects are implemented. CLINICAL TRIAL NUMBER: This study was registered at the German Clinical Trial Register (DRKS-Study-ID: DRKS00013570; URL: https://www.drks.de/drks_web/).

来源:Eur J Cancer,查看原文。版权归原作者所有。

引用

  1. Winkler JK, Sies K, Fink C, et al. Association between different scale bars in dermoscopic images and diagnostic performance of a market-approved deep learning convolutional neural network for melanoma recognition. Eur J Cancer. 2021. PMID: 33465706. doi:10.1016/j.ejca.2020.12.010

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。