文献速递骨软组织肉瘤与黑色素瘤

监测黑色素瘤风险患者:卷积神经网络能否替代连续数字皮肤镜策略

Monitoring patients at risk for melanoma: May convolutional neural networks replace the strategy of sequential digital dermoscopy?
PubMed 文献 · Eur J Cancer · 2021-11-25

该回顾性横断面研究纳入59例高危患者的236个病灶图像四联组,评估两种卷积神经网络(CNN)在基线和连续数字皮肤镜(SDD)随访时对黑色素瘤的分类能力。CNN在基线时正确分类的四联组数少于皮肤科医生,结论为所测试的CNN无法替代SDD策略,需要能整合动态变化信息的CNN。

要点

  • 所测试的CNN无法替代连续数字皮肤镜(SDD)策略。
  • 基线时CNN-1和CNN-2正确分类的四联组数分别为9/59和8/59。
  • 26名皮肤科医生平均正确分类24/59个基线四联组。

核心结论

  • 所测试的CNN无法替代SDD策略,需要能整合动态变化信息的CNN。

研究设计与样本

  • 回顾性横断面研究,使用59例高危患者的图像四联组,共236个病灶,每个四联组含一个经SDD动态变化诊断的黑色素瘤和三个痣。

主要发现

  • 基线时CNN-1正确分类9个(15.3%)四联组,CNN-2正确分类8个(13.6%)四联组(共59个)。
  • 基线图像中CNN-1灵敏度25.4%(16.1%-37.8%)、特异度92.7%(87.8%-95.7%),CNN-2灵敏度28.8%(18.8%-41.4%)、特异度75.7%(68.9%-81.4%)。
  • SDD随访后CNN灵敏度提高:CNN-1为44.1%(32.2%-56.7%),CNN-2为49.2%(36.8%-61.6%)。
  • 26名皮肤科医生被告知每个基线四联组含一个黑色素瘤,平均正确分类24个(22-27)四联组(共59个)。
  • 以四联组内最高恶性评分赋予黑色素瘤即视为正确分类时,CNN-1正确分类28个(47.5%)、CNN-2正确分类22个(37.3%)四联组(共59个)。

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: Sequential digital dermoscopy (SDD) is applied for early melanoma detection by uncovering dynamic changes of monitored lesions. Convolutional neural networks (CNN) are capable of high diagnostic accuracies similar to trained dermatologists. OBJECTIVES: To investigate the capability of CNN to correctly classify melanomas originally diagnosed by mere dynamic changes during SDD. METHODS: A retrospective cross-sectional study using image quartets of 59 high-risk patients each containing one melanoma diagnosed by dynamic changes during SDD and three nevi (236 lesions). Two validated CNN classified quartets at baseline or after SDD follow-up at the time of melanoma diagnosis. Moreover, baseline quartets were rated by 26 dermatologists. The main outcome was the number of quartets with correct classifications. RESULTS: CNN-1 correctly classified 9 (15.3%) and CNN-2 8 (13.6%) of 59 baseline quartets. In baseline images, CNN-1 attained a sensitivity of 25.4% (16.1%-37.8%) and specificity of 92.7% (87.8%-95.7%), whereas CNN-2 of 28.8% (18.8%-41.4%) and 75.7% (68.9%-81.4%). Expectedly, after SDD follow-up CNN more readily detected melanomas resulting in improved sensitivities (CNN-1: 44.1% [32.2%-56.7%]; CNN-2: 49.2% [36.8%-61.6%]). Dermatologists were told that each baseline quartet contained one melanoma, and on average, correctly classified 24 (22-27) of 59 quartets. Correspondingly, accepting a baseline quartet to be appropriately classified whenever the highest malignancy score was assigned to the melanoma within, CNN-1 and CNN-2 correctly classified 28 (47.5%) and 22 (37.3%) of 59 quartets, respectively. CONCLUSIONS: The tested CNN could not replace the strategy of SDD. There is a need for CNN capable of integrating information on dynamic changes into analyses.

来源:Eur J Cancer,查看原文。版权归原作者所有。

引用

  1. Winkler JK, Tschandl P, Toberer F, et al. Monitoring patients at risk for melanoma: May convolutional neural networks replace the strategy of sequential digital dermoscopy? Eur J Cancer. 2021. PMID: 34840028. doi:10.1016/j.ejca.2021.10.030

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。