文献速递皮肤肿瘤

深度学习用于反射共聚焦显微镜下基底细胞癌检测

Deep Learning for Basal Cell Carcinoma Detection for Reflectance Confocal Microscopy.
PubMed 文献 · J Invest Dermatol · 2021-07-13

该研究开发并评估了一种深度学习人工智能模型,用于在反射共聚焦显微镜图像中自动检测基底细胞癌。模型在受试者工作特征曲线下的面积达到89.7%(堆叠层面)和88.3%(病变层面),与国际反射共聚焦显微镜专家的性能相当,并在国际合作的保留测试集上达到86.1%,表明该自动化诊断方法具有可重复性和泛化性。

要点

  • 深度学习模型在反射共聚焦显微镜图像中检测基底细胞癌的AUC达89.7%(堆叠层面)和88.3%(病变层面)。
  • 模型性能与反射共聚焦显微镜专家相当,国际保留测试集AUC为86.1%。
  • 该决策支持系统有望优化皮肤癌患者的评估与诊断。

核心结论

  • 深度学习模型可在反射共聚焦显微镜图像中自动检测基底细胞癌,性能与专家相当,并具备泛化性。

研究设计与样本

  • 研究开发并评估了一种基于深度学习的人工智能模型,用于在反射共聚焦显微镜图像中自动检测基底细胞癌。

主要发现

  • 模型在受试者工作特征曲线下的面积达到89.7%(堆叠层面)和88.3%(病变层面)。
  • 模型性能与反射共聚焦显微镜专家相当。
  • 在国际合作者的保留测试集上,模型达到86.1%的受试者工作特征曲线下面积。

关键数值与推荐

  • 反射共聚焦显微镜可提高基底细胞癌诊断特异性,并将需活检数量减少2-3倍。

临床怎么用

  • 临床部署决策支持系统有望优化反射共聚焦显微镜图像中基底细胞癌的检测,改善皮肤癌患者的评估与诊断。

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

Basal cell carcinoma (BCC) is the most common skin cancer, with over 2 million cases diagnosed annually in the United States. Conventionally, BCC is diagnosed by naked eye examination and dermoscopy. Suspicious lesions are either removed or biopsied for histopathological confirmation, thus lowering the specificity of noninvasive BCC diagnosis. Recently, reflectance confocal microscopy, a noninvasive diagnostic technique that can image skin lesions at cellular level resolution, has shown to improve specificity in BCC diagnosis and reduced the number needed to biopsy by 2-3 times. In this study, we developed and evaluated a deep learning-based artificial intelligence model to automatically detect BCC in reflectance confocal microscopy images. The proposed model achieved an area under the curve for the receiver operator characteristic curve of 89.7% (stack level) and 88.3% (lesion level), a performance on par with that of reflectance confocal microscopy experts. Furthermore, the model achieved an area under the curve of 86.1% on a held-out test set from international collaborators, demonstrating the reproducibility and generalizability of the proposed automated diagnostic approach. These results provide a clear indication that the clinical deployment of decision support systems for the detection of BCC in reflectance confocal microscopy images has the potential for optimizing the evaluation and diagnosis of patients with skin cancer.

来源:J Invest Dermatol,查看原文。版权归原作者所有。

引用

  1. Campanella G, Navarrete-Dechent C, Liopyris K, et al. Deep Learning for Basal Cell Carcinoma Detection for Reflectance Confocal Microscopy. J Invest Dermatol. 2021. PMID: 34265329. doi:10.1016/j.jid.2021.06.015

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。