文献速递骨软组织肉瘤与黑色素瘤

深度学习卷积神经网络识别黑色素瘤在不同亚型与部位的性能

Melanoma recognition by a deep learning convolutional neural network-Performance in different melanoma subtypes and localisations.
PubMed 文献 · Eur J Cancer · 2020-01-20

该研究评估了获批欧洲市场的CNN(Moleanalyzer-Pro®)在六组皮肤镜图像中对不同黑色素瘤亚型与部位的分类性能。结果显示,SSM、LMM和NM组敏感性>93.3%、特异性>65%、ROC-AUC>0.926,而黏膜和甲下黑色素瘤性能有限,甲下敏感性仅53.3%、ROC-AUC 0.621。

要点

  • CNN对SSM、LMM和NM分类性能高,敏感性>93.3%、特异性>65%、ROC-AUC>0.926。
  • 肢端皮肤黑色素瘤敏感性较低(83.3%)但特异性高(91.0%),ROC-AUC 0.928。
  • 黏膜和甲下黑色素瘤诊断性能有限,甲下敏感性53.3%、ROC-AUC 0.621。

核心结论

  • CNN可部分弥补医师诊断准确性的不足,但医师需注意其在黏膜和甲下病变中的诊断性能有限。

研究设计与样本

  • 使用获批欧洲市场的CNN(Moleanalyzer-Pro®)在六组皮肤镜图像集中进行恶性/良性分类,每组含30例黑色素瘤和100例相关良性病变。

主要发现

  • set-SSM、set-NM和set-LMM组敏感性>93.3%、特异性>65%、ROC-AUC>0.926。
  • set-AMskin组敏感性83.3%、特异性91.0%、ROC-AUC 0.928。
  • set-Mucosa组敏感性93.3%、特异性38.0%、ROC-AUC 0.754。
  • set-AMnail组敏感性53.3%、特异性68.0%、ROC-AUC 0.621。

临床怎么用

  • CNN可用于辅助黑色素瘤诊断,尤其在SSM、LMM和NM中性能较高。
  • 对黏膜和甲下病变,应谨慎解读CNN结果,不可完全依赖。

局限性

  • 黏膜和甲下部位训练图像不足可能限制CNN性能,需额外训练图像改进。

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: Deep learning convolutional neural networks (CNNs) show great potential for melanoma diagnosis. Melanoma thickness at diagnosis among others depends on melanoma localisation and subtype (e.g. advanced thickness in acrolentiginous or nodular melanomas). The question whether CNN may counterbalance physicians' diagnostic difficulties in these melanomas has not been addressed. We aimed to investigate the diagnostic performance of a CNN with approval for the European market across different melanoma localisations and subtypes. METHODS: The current market version of a CNN (Moleanalyzer-Pro®, FotoFinder Systems GmbH, Bad Birnbach, Germany) was used for classifications (malignant/benign) in six dermoscopic image sets. Each set included 30 melanomas and 100 benign lesions of related localisations and morphology (set-SSM: superficial spreading melanomas and macular nevi; set-LMM: lentigo maligna melanomas and facial solar lentigines/seborrhoeic keratoses/nevi; set-NM: nodular melanomas and papillomatous/dermal/blue nevi; set-Mucosa: mucosal melanomas and mucosal melanoses/macules/nevi; set-AMskin: acrolentiginous melanomas and acral (congenital) nevi; set-AMnail: subungual melanomas and subungual (congenital) nevi/lentigines/ethnical type pigmentations). RESULTS: The CNN showed a high-level performance in set-SSM, set-NM and set-LMM (sensitivities >93.3%, specificities >65%, receiver operating characteristics-area under the curve [ROC-AUC] >0.926). In set-AMskin, the sensitivity was lower (83.3%) at a high specificity (91.0%) and ROC-AUC (0.928). A limited performance was found in set-mucosa (sensitivity 93.3%, specificity 38.0%, ROC-AUC 0.754) and set-AMnail (sensitivity 53.3%, specificity 68.0%, ROC-AUC 0.621). CONCLUSIONS: The CNN may help to partly counterbalance reduced human accuracies. However, physicians need to be aware of the CNN's limited diagnostic performance in mucosal and subungual lesions. Improvements may be expected from additional training images of mucosal and subungual sites.

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. Melanoma recognition by a deep learning convolutional neural network-Performance in different melanoma subtypes and localisations. Eur J Cancer. 2020. PMID: 31972395. doi:10.1016/j.ejca.2019.11.020

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。