Brinker T J, Schlager G, French L E, Jutzi T, Kittler H
Nachwuchsgruppe Digitale Biomarker für die Onkologie (DBO), Deutsches Krebsforschungszentrum (DKFZ), Heidelberg, Deutschland.
Abteilung für Dermatologie und Allergologie, Universitätsklinikum, LMU München, München, Deutschland.
Hautarzt. 2020 Sep;71(9):669-676. doi: 10.1007/s00105-020-04662-8.
Artificial intelligence (AI) is increasingly being used in medical practice. Especially in the image-based diagnosis of skin cancer, AI shows great potential. However, there is a significant discrepancy between expectations and true relevance of AI in current dermatological practice.
This article summarizes promising study results of skin cancer diagnosis by computer-based diagnostic systems and discusses their significance for daily practice. We hereby focus on the analysis of dermoscopic images of pigmented and unpigmented skin lesions.
A selective literature search for recent relevant trials was conducted. The included studies used machine learning, and in particular "convolutional neural networks", which have been shown to be particularly effective for the classification of image data.
In numerous studies, computer algorithms were able to detect pigmented and nonpigmented neoplasms of the skin with high precision, comparable to that of dermatologists. The combination of the physician's assessment and AI showed the best results. Computer-based diagnostic systems are widely accepted among patients and physicians. However, they are still not applicable in daily practice, since computer-based diagnostic systems have only been tested in an experimental environment. In addition, many digital diagnostic criteria that help AI to classify skin lesions remain unclear. This lack of transparency still needs to be addressed. Moreover, clinical studies on the use of AI-based assistance systems are needed in order to prove its applicability in daily dermatologic practice.
人工智能（AI）在医学实践中的应用越来越广泛。尤其是在皮肤癌的基于图像的诊断中，人工智能显示出巨大的潜力。然而，在当前皮肤科实践中，人工智能的预期与实际相关性之间存在显著差异。
本文总结了基于计算机的诊断系统在皮肤癌诊断方面有前景的研究结果，并讨论了它们在日常实践中的意义。我们在此重点分析色素沉着和非色素沉着皮肤病变的皮肤镜图像。
对近期相关试验进行了选择性文献检索。纳入的研究使用了机器学习，特别是“卷积神经网络”，已证明其对图像数据分类特别有效。
在众多研究中，计算机算法能够高精度地检测皮肤色素沉着和非色素沉着性肿瘤，与皮肤科医生的检测精度相当。医生评估与人工智能相结合显示出最佳效果。基于计算机的诊断系统在患者和医生中得到广泛认可。然而，它们仍不适用于日常实践，因为基于计算机的诊断系统仅在实验环境中进行了测试。此外，许多有助于人工智能对皮肤病变进行分类的数字诊断标准仍不明确。这种缺乏透明度的问题仍需解决。此外，需要开展关于使用基于人工智能的辅助系统的临床研究，以证明其在日常皮肤科实践中的适用性。
