Department of Dermatology, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, 222, Banpo-daero, Seocho-gu, Seoul, 06591, Korea.
Department of Business Management, Kwangwoon University, 536 Nuri Hall, 20, Kwangwoon-ro, Nowon-gu, Seoul, 01897, Korea.
Sci Rep. 2021 Mar 15;11(1):6049. doi: 10.1038/s41598-021-85489-8.
Scoring atopic dermatitis (AD) severity with the Eczema Area and Severity Index (EASI) in an objective and reproducible manner is challenging. Automated measurement of erythema, papulation, excoriation, and lichenification severity using images has not yet been investigated. Our aim was to determine whether convolutional neural networks (CNNs) could assess erythema, papulation, excoriation, and lichenification severity at a level of competence comparable to dermatologists. We created a standard dataset of 8,000 clinical images showing AD. Each component of the EASI was scored from 0 to 3 by three dermatologists. We trained four CNNs (ResNet V1, ResNet V2, GoogLeNet, and VGG-Net) with the image dataset and determined which CNN was the most suitable for erythema, papulation, excoriation, and lichenification scoring. The brightness of the images in each dataset was adjusted to - 80% to + 80% of the original brightness (i.e., 9 levels by 20%) to investigate if the CNNs accurately measured scores if image brightness levels were changed. Compared to the dermatologists' scoring, accuracy rates of the CNNs were 99.17% for erythema, 93.17% for papulation, 96.00% for excoriation, and 97.17% for lichenification. CNNs trained with brightness-adjusted images achieved a high accuracy without the need to standardize camera settings. These results suggested that CNNs perform at level of competence comparable to dermatologists for scoring erythema, papulation, excoriation, and lichenification severity.
用湿疹面积及严重度指数（EASI）客观且可重复地对特应性皮炎（AD）严重程度进行评分具有挑战性。使用图像自动测量红斑、丘疹、抓挠和苔藓样变的严重程度尚未得到研究。我们的目的是确定卷积神经网络（CNN）是否可以评估红斑、丘疹、抓挠和苔藓样变的严重程度，其能力是否可与皮肤科医生相媲美。我们创建了一个包含 8000 张显示 AD 的临床图像的标准数据集。三位皮肤科医生对 EASI 的每个组成部分进行 0 到 3 的评分。我们使用图像数据集训练了四个 CNN（ResNet V1、ResNet V2、GoogLeNet 和 VGG-Net），并确定了哪个 CNN 最适合红斑、丘疹、抓挠和苔藓样变的评分。每个数据集的图像亮度调整为原始亮度的-80%至+80%（即 9 个级别乘以 20%），以研究如果图像亮度水平发生变化，CNN 是否能准确测量评分。与皮肤科医生的评分相比，CNN 对红斑的准确率为 99.17%，对丘疹的准确率为 93.17%，对抓挠的准确率为 96.00%，对苔藓样变的准确率为 97.17%。经过亮度调整的图像训练的 CNN 无需标准化相机设置即可实现高精度。这些结果表明，CNN 在评分红斑、丘疹、抓挠和苔藓样变严重程度方面的能力与皮肤科医生相当。
