文献速递骨软组织肉瘤与黑色素瘤

联合CNN组织学全切片图像分析与患者数据改进皮肤癌分类

Combining CNN-based histologic whole slide image analysis and patient data to improve skin cancer classification.
PubMed 文献 · Eur J Cancer · 2021-04-07

该研究基于431张来自两个实验室的组织学全切片图像,在黑色素瘤/痣二分类任务中比较卷积神经网络(CNN)单独使用与结合患者数据(年龄、性别、病变解剖部位)的分类性能。CNN单独使用AUROC达92.30%±0.23%、平衡准确率83.17%±0.38%;常规融合未显著提升性能,但对CNN输出评分<0.7的“不确定”病例改用患者数据分类器决策后,平衡准确率提升至86.72%±0.36%。

要点

  • CNN单独分类黑色素瘤/痣的AUROC为92.30%,平衡准确率83.17%。
  • 常规融合患者数据未显著提升CNN分类性能。
  • 对CNN低置信度(评分<0.7)病例改用患者数据分类可提升平衡准确率至86.72%。

核心结论

  • 多数情况下CNN单独分类已足够准确,整合患者数据未带来获益。
  • 对CNN分类置信度低的病变,纳入患者数据可提升平衡准确率。

研究设计与样本

  • 研究使用431张来自两个不同实验室的组织学全切片图像(WSI)。
  • 比较仅用图像、仅用患者数据及三种常见融合技术的分类器性能。
  • 测试一种朴素策略:对CNN输出评分<0.7的病例,用患者数据分类器决策替代CNN决策。

主要发现

  • CNN单独使用表现最佳,五次独立运行的AUROC为92.30%±0.23%,平衡准确率为83.17%±0.38%。
  • 所测试的任何融合方式总体上均未显著改善分类性能。
  • 对低输出评分切片用患者数据分类器替代CNN的朴素策略,将平衡准确率提升至86.72%±0.36%。

临床怎么用

  • 在CNN分类置信度低(输出评分<0.7)的病例中,可结合患者数据辅助决策以提升平衡准确率。
  • 对于CNN高置信度病例,单独使用CNN即可,无需常规整合患者数据。

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: Clinicians and pathologists traditionally use patient data in addition to clinical examination to support their diagnoses. OBJECTIVES: We investigated whether a combination of histologic whole slides image (WSI) analysis based on convolutional neural networks (CNNs) and commonly available patient data (age, sex and anatomical site of the lesion) in a binary melanoma/nevus classification task could increase the performance compared with CNNs alone. METHODS: We used 431 WSIs from two different laboratories and analysed the performance of classifiers that used the image or patient data individually or three common fusion techniques. Furthermore, we tested a naive combination of patient data and an image classifier: for cases interpreted as 'uncertain' (CNN output score <0.7), the decision of the CNN was replaced by the decision of the patient data classifier. RESULTS: The CNN on its own achieved the best performance (mean ± standard deviation of five individual runs) with AUROC of 92.30% ± 0.23% and balanced accuracy of 83.17% ± 0.38%. While the classification performance was not significantly improved in general by any of the tested fusions, naive strategy of replacing the image classifier with the patient data classifier on slides with low output scores improved balanced accuracy to 86.72% ± 0.36%. CONCLUSION: In most cases, the CNN on its own was so accurate that patient data integration did not provide any benefit. However, incorporating patient data for lesions that were classified by the CNN with low 'confidence' improved balanced accuracy.

来源:Eur J Cancer,查看原文。版权归原作者所有。

引用

  1. Höhn J, Krieghoff-Henning E, Jutzi TB, et al. Combining CNN-based histologic whole slide image analysis and patient data to improve skin cancer classification. Eur J Cancer. 2021. PMID: 33838393. doi:10.1016/j.ejca.2021.02.032

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。