文献速递骨软组织肉瘤与黑色素瘤

增强智能联合二维与三维全身摄影及卷积神经网络在高危黑色素瘤人群真实世界条件下的诊断性能:皮肤癌筛查的新纪元?

Diagnostic performance of augmented intelligence with 2D and 3D total body photography and convolutional neural networks in a high-risk population for melanoma under real-world conditions: A new era of skin cancer screening?
PubMed 文献 · Eur J Cancer · 2023-06-24

这项前瞻性研究纳入143例黑色素瘤高危患者共1690处黑素细胞性病变,评估皮肤科医生、二维FotoFinder-ATBM与三维Vectra WB360全身摄影联合卷积神经网络(CNN)的诊断性能。三维CNN与组织病理相比灵敏度90.0%、特异度64.6%、ROC-AUC 0.92(95%CI 0.85-1.00),皮肤科医生与增强智能灵敏度同为90%但特异度更高(分别为92.3%和86.2%);二维CNN灵敏度70%、特异度40%、ROC-AUC 0.68(95%CI 0.46-0.90),被三维CNN和皮肤科医生超越。作者结论强调在真实世界中验证CNN分类的重要性,三维CNN装置表现优于二维CNN且灵敏度与皮肤科医生相当,但CNN特异度低及缺乏自动计数目前限制增强智能在临床实践中的应用。

要点

  • 三维CNN与组织病理相比灵敏度90.0%、特异度64.6%、ROC-AUC 0.92(95%CI 0.85-1.00)。
  • 皮肤科医生与增强智能灵敏度同为90%,特异度分别为92.3%和86.2%,高于三维CNN。
  • 二维CNN灵敏度70%、特异度40%、ROC-AUC 0.68(95%CI 0.46-0.90),劣于三维CNN和皮肤科医生。

核心结论

  • 研究强调在真实生活中验证CNN分类的重要性。
  • 新型三维CNN装置表现优于二维CNN,灵敏度与皮肤科医生相当。
  • CNN特异度低及缺乏全身摄影痣的自动计数目前限制增强智能在临床实践中的应用。

研究设计与样本

  • 前瞻性研究,纳入143例符合黑色素瘤高危标准的患者,共评估1690处黑素细胞性病变。
  • 由皮肤科医生、二维FotoFinder-ATBM和三维Vectra WB360全身摄影(TBP)进行评估。
  • 切除基于皮肤科医生的二分决策、CNN风险评分升高(研究特定恶性临界值:FotoFinder >0.5,Vectra >5.0)和/或第二位皮肤科医生在CNN支持下的评估。
  • 将二维和三维CNN分类的诊断准确性与皮肤科医生及基于组织病理和皮肤科医生评估的增强智能进行比较。
  • 次要终点包括风险评分的可重复性及医护人员(金标准)与自动三维和二维TBP CNN计数相比的每患者痣计数。

主要发现

  • 三维CNN风险评分评估与组织病理相比的灵敏度、特异度和ROC-AUC分别为90.0%、64.6%和0.92(95%CI 0.85-1.00)。
  • 皮肤科医生和增强智能与三维CNN达到相同灵敏度(90%)和可比分类ROC-AUC(分别为0.91 [95%CI 0.80-1.00]和0.88 [95%CI 0.77-1.00]),但特异度更高(分别为92.3%和86.2%)。
  • 二维CNN灵敏度70%、特异度40%、ROC-AUC 0.68(95%CI 0.46-0.90),被三维CNN和皮肤科医生超越。
  • 三维CNN对246处病变重复测量的相关系数(R=0.89)高于二维CNN(R=0.79)。
  • 每患者平均痣计数差异显著(金标准:210处病变;三维CNN:469;二维CNN:1324;p<0.0001)。

局限性

  • CNN特异度低及缺乏全身摄影痣的自动计数目前限制增强智能在临床实践中的应用。

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: Convolutional neural networks (CNNs) have outperformed dermatologists in classifying pigmented skin lesions under artificial conditions. We investigated, for the first time, the performance of three-dimensional (3D) and two-dimensional (2D) CNNs and dermatologists in the early detection of melanoma in a real-world setting. METHODS: In this prospective study, 1690 melanocytic lesions in 143 patients with high-risk criteria for melanoma were evaluated by dermatologists, 2D-FotoFinder-ATBM and 3D-Vectra WB360 total body photography (TBP). Excision was based on the dermatologists' dichotomous decision, an elevated CNN risk score (study-specific malignancy cut-off: FotoFinder >0.5, Vectra >5.0) and/or the second dermatologist's assessment with CNN support. The diagnostic accuracy of the 2D and 3D CNN classification was compared with that of the dermatologists and the augmented intelligence based on histopathology and dermatologists' assessment. Secondary end-points included reproducibility of risk scores and naevus counts per patient by medical staff (gold standard) compared to automated 3D and 2D TBP CNN counts. RESULTS: The sensitivity, specificity, and receiver operating characteristics area under the curve (ROC-AUC) for risk-score-assessments compared to histopathology of 3D-CNN with 95% confidence intervals (CI) were 90.0%, 64.6% and 0.92 (CI 0.85-1.00), respectively. While dermatologists and augmented intelligence achieved the same sensitivity (90%) and comparable classification ROC-AUC (0.91 [CI 0.80-1.00], 0.88 [CI 0.77-1.00]) with 3D-CNN, their specificity was superior (92.3% and 86.2%, respectively). The 2D-CNN (sensitivity: 70%, specificity: 40%, ROC-AUC: 0.68 [CI 0.46-0.90]) was outperformed by 3D CNN and dermatologists. The 3D-CNN showed a higher correlation coefficient for repeated measurements of 246 lesions (R = 0.89) than the 2D-CNN (R = 0.79). The mean naevus count per patient varied significantly (gold standard: 210 lesions; 3D-CNN: 469; 2D-CNN: 1324; p < 0.0001). CONCLUSIONS: Our study emphasises the importance of validating the classification of CNNs in real life. The novel 3D-CNN device outperformed the 2D-CNN and achieved comparable sensitivity with dermatologists. The low specificity of CNNs and the lack of automated counting of TBP nevi currently limit the use of augmented intelligence in clinical practice.

来源:Eur J Cancer,查看原文。版权归原作者所有。

引用

  1. Cerminara SE, Cheng P, Kostner L, et al. Diagnostic performance of augmented intelligence with 2D and 3D total body photography and convolutional neural networks in a high-risk population for melanoma under real-world conditions: A new era of skin cancer screening? Eur J Cancer. 2023. PMID: 37453242. doi:10.1016/j.ejca.2023.112954

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。