Guo Lifang, Yang Yin, Ding Hui, Zheng Huiying, Yang Hedan, Xie Junxiang, Li Yong, Lin Tong, Ge Yiping
Department of Cosmetic Laser Surgery, Hospital for Skin Disease and Institute of Dermatology, Chinese Academy of Medical Sciences (CAMS) & Peking Union Medical College, Nanjing, China.
Institute of Medical Information, Hospital for Skin Disease and Institute of Dermatology, Chinese Academy of Medical Sciences (CAMS) & Peking Union Medical College, Beijing, China.
Ann Transl Med. 2022 May;10(10):590. doi: 10.21037/atm-22-1738.
We aimed to establish and validate a deep learning-based hybrid artificial intelligence (AI) model for the objective morphometric and colorimetric assessment of vitiligo lesions.
Two main datasets containing curated images of vitiligo lesions from Chinese patients (Fitzpatrick skin types III or IV) were established, including one with 2,720 images for lesion localization study and the other with 1,262 images for lesion segmentation study. Besides, an additional test set containing 145 images of vitiligo lesions from other Fitzpatrick skin types (I, II, or V) was also generated. A 3-stage hybrid model was constructed. YOLO v3 (You Only Look Once, v3) architecture was trained and validated to classify and localize vitiligo lesions, with sensitivity and error rate as primary performance outcomes. Then a segmentation study comparing 3 deep convolutional neural networks (DCNNs), Pyramid Scene Parsing Network (PSPNet), UNet, and UNet++, was carried out based on the Jaccard index (JI). The architecture with the best performance was integrated into the model. Three add-on metrics, namely VAreaA, VAreaR, and VColor were finally developed to measure absolute, relative size changes and pigmentation, respectively. Agreement between the AI model and dermatologist evaluators were assessed.
The sensitivity of the YOLO v3 architecture to detect vitiligo lesions was 92.91% with an error rate of 14.98%. The UNet++ architecture outperformed the others in the segmentation study (JI, 0.79) and was integrated into the model. On the additional test set, however, the model achieved a lower detection sensitivity (72.41%) and a lower segmentation score (JI, 0.69). With respect to size changes, no difference was observed between the AI model, trained dermatologists (W=0.812, P<0.05), and Photoshop analysis (P=0.075, P=0.212 respectively), which all displayed good concordance.
We developed a novel, convenient, objective, and quantitative deep learning-based hybrid model which simultaneously evaluated both morphometric and colorimetric vitiligo lesions from patients with Fitzpatrick skin types III or IV, rendering it suitable for the assessment of severity of vitiligo lesions in Asians in both clinic and research scenarios. More work is also warranted for its use in other ethnic skin groups.
我们旨在建立并验证一种基于深度学习的混合人工智能（AI）模型，用于对白癜风皮损进行客观的形态学和比色评估。
建立了两个主要数据集，包含来自中国患者（Fitzpatrick皮肤类型III或IV）的白癜风皮损精选图像，其中一个数据集有2720张图像用于皮损定位研究，另一个有1262张图像用于皮损分割研究。此外，还生成了一个包含145张来自其他Fitzpatrick皮肤类型（I、II或V）的白癜风皮损图像的额外测试集。构建了一个三阶段混合模型。对YOLO v3（You Only Look Once, v3）架构进行训练和验证，以对白癜风皮损进行分类和定位，将敏感度和错误率作为主要性能指标。然后基于杰卡德指数（JI）开展一项分割研究，比较3种深度卷积神经网络（DCNN），即金字塔场景解析网络（PSPNet）、UNet和UNet++。将性能最佳的架构整合到模型中。最终开发了3个附加指标，即VAreaA、VAreaR和VColor，分别用于测量绝对大小变化、相对大小变化和色素沉着。评估了AI模型与皮肤科医生评估结果之间的一致性。
YOLO v3架构检测白癜风皮损的敏感度为92.91%，错误率为14.98%。在分割研究中，UNet++架构表现优于其他架构（JI为0.79）并被整合到模型中。然而，在额外测试集上，该模型的检测敏感度较低（72.41%），分割分数也较低（JI为0.69）。在大小变化方面，AI模型、训练有素的皮肤科医生（W = 0.812，P < 0.05）和Photoshop分析（P分别为0.075、0.212）之间未观察到差异，三者均显示出良好的一致性。
我们开发了一种新颖、便捷、客观且定量的基于深度学习的混合模型，该模型可同时评估Fitzpatrick皮肤类型III或IV患者的白癜风皮损的形态学和比色特征，使其适用于临床和研究场景中亚洲人白癜风皮损严重程度的评估。在将其应用于其他种族皮肤群体方面，也需要开展更多工作。
