Winkler Julia K, Haenssle Holger A
Universitätshautklinik Heidelberg, Im Neuenheimer Feld 440, 69120, Heidelberg, Deutschland.
Dermatologie (Heidelb). 2022 Nov;73(11):838-844. doi: 10.1007/s00105-022-05058-6. Epub 2022 Sep 12.
Convolutional neural networks (CNN) achieve a level of performance comparable or even superior to dermatologists in the assessment of pigmented and nonpigmented skin lesions. In the analysis of images by artificial neural networks, images on a pixel level pass through various layers of the network with different graphic filters. Based on excellent study results, a first deep learning network (Moleanalyzer pro, Fotofinder Systems GmBH, Bad Birnbach, Germany) received market approval in Europe. However, such neural networks also reveal relevant limitations, whereby rare entities with insufficient training images are classified less adequately and image artifacts can lead to false diagnoses. Best results can ultimately be achieved in a cooperation of "man with machine". For future skin cancer screening, automated total body mapping is evaluated, which combines total body photography, automated data extraction and assessment of all relevant skin lesions.
在色素沉着和非色素沉着性皮肤病变的评估中，卷积神经网络（CNN）达到了与皮肤科医生相当甚至更优的性能水平。在人工神经网络对图像的分析中，像素级别的图像会通过具有不同图形滤波器的网络各层。基于出色的研究成果，首个深度学习网络（Moleanalyzer pro，德国巴特比尔恩巴赫市的Fotofinder Systems GmBH公司）在欧洲获得了市场批准。然而，此类神经网络也存在相关局限性，即训练图像不足的罕见病变分类不够准确，且图像伪影可能导致误诊。最终，“人机协作”才能取得最佳效果。对于未来的皮肤癌筛查，正在评估结合全身摄影、自动数据提取以及对所有相关皮肤病变进行评估的自动全身映射技术。
