A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task
A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task
复制标题
DOI：
10.1016/j.ejca.2019.02.005
复制
发表时间：
2019-04-01
影响因子：
8.4
通讯作者：
Schruefer, Philipp
中科院分区：
文献类型：
--
作者：
Brinker, Titus J.;Hekler, Achim;Schruefer, Philipp
背景：最近的研究表明，使用卷积神经网络(CNN)对黑色素瘤图像进行分类，其精度可与委员会认证的皮肤科医生相媲美。然而，在与大量皮肤科医生直接竞争的临床图像分类任务中，专门使用皮肤镜图像训练的CNN的性能迄今尚未被测量。这项研究比较了卷积神经网络和皮肤科医生对相同图像的手动分级的性能，所述卷积神经网络使用专门用于识别临床照片中的黑色素瘤的皮肤镜图像进行训练。我们使用增强深度学习的方法来训练CNN，其中包含12,378张开源皮肤镜图像。我们使用100幅临床图像来比较CNN和皮肤科医生的表现。皮肤科医生和深度神经网络在敏感度、特异度和接收器操作特性方面进行了比较。结果：皮肤科医生根据临床图像获得的平均敏感度和特异度分别为89.4%(55.0%~100%)和64.4%(22.5%~92.5%)。在灵敏度相同的情况下，CNN的平均特异度为68.2%(47.5%~86.25%)。在皮肤科医生中，主治医师的平均敏感度最高，为92.8%，平均特异度为57.7%。在同样高的灵敏度92.8%的情况下，CNN的平均特异度为61.1%。解释：首次在临床图像分类任务中实现了皮肤科医生级别的图像分类，而不需要对临床图像进行训练。CNN的结果方差较小，表明与人类评估相比，计算机视觉在皮肤病图像分类任务中具有更高的稳健性。(C)2019年提交人。由爱思唯尔有限公司出版。这是CC BY-NC-ND许可证(http://creativecommons.org/licenses/by-nc-nd/4.0/).下的一篇开放获取文章
Background: Recent studies have demonstrated the use of convolutional neural networks (CNNs) to classify images of melanoma with accuracies comparable to those achieved by board-certified dermatologists. However, the performance of a CNN exclusively trained with dermoscopic images in a clinical image classification task in direct competition with a large number of dermatologists has not been measured to date. This study compares the performance of a convolutional neuronal network trained with dermoscopic images exclusively for identifying melanoma in clinical photographs with the manual grading of the same images by dermatologists.Methods: We compared automatic digital melanoma classification with the performance of 145 dermatologists of 12 German university hospitals. We used methods from enhanced deep learning to train a CNN with 12,378 open-source dermoscopic images. We used 100 clinical images to compare the performance of the CNN to that of the dermatologists.Dermatologists were compared with the deep neural network in terms of sensitivity, specificity and receiver operating characteristics.Findings: The mean sensitivity and specificity achieved by the dermatologists with clinical images was 89.4% (range: 55.0%-100%) and 64.4% (range: 22.5%-92.5%). At the same sensitivity, the CNN exhibited a mean specificity of 68.2% (range 47.5%-86.25%). Among the dermatologists, the attendings showed the highest mean sensitivity of 92.8% at a mean specificity of 57.7%. With the same high sensitivity of 92.8%, the CNN had a mean specificity of 61.1%.Interpretation: For the first time, dermatologist-level image classification was achieved on a clinical image classification task without training on clinical images. The CNN had a smaller variance of results indicating a higher robustness of computer vision compared with human assessment for dermatologic image classification tasks. (C) 2019 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).