A Deep Learning Based Framework for Diagnosing Multiple Skin Diseases in a Clinical Environment

作者：Chenyu Zhu, Yukun Wang, Haipeng Chen, Kunlun Gao, Chang Shu, Juncheng Wang, Lifeng Yan, Yiguang Yang, Fengying Xie, Jie Liu · 发表于：Frontiers in Medicine · 年份：2021 · DOI：10.3389/fmed.2021.626369 · 被引用次数：98 · 研究领域：Cutaneous Melanoma Detection and Management、Nonmelanoma Skin Cancer Studies、Dermatologic Treatments and Research

Background: Numerous studies have attempted to apply artificial intelligence (AI) in the dermatological field, mainly on the classification and segmentation of various dermatoses. However, researches under real clinical settings are scarce. Objectives: This study was aimed to construct a novel framework based on deep learning trained by a dataset that represented the real clinical environment in a tertiary class hospital in China, for better adaptation of the AI application in clinical practice among Asian patients. Methods: Our dataset was composed of 13,603 dermatologist-labeled dermoscopic images, containing 14 categories of diseases, namely lichen planus (LP), rosacea (Rosa), viral warts (VW), acne vulgaris (AV), keloid and hypertrophic scar (KAHS), eczema and dermatitis (EAD), dermatofibroma (DF), seborrheic dermatitis (SD), seborrheic keratosis (SK), melanocytic nevus (MN), hemangioma (Hem), psoriasis (Pso), port wine stain (PWS), and basal cell carcinoma (BCC). In this study, we applied Google's EfficientNet-b4 with pre-trained weights on ImageNet as the backbone of our CNN architecture. The final fully-connected classification layer was replaced with 14 output neurons. We added seven auxiliary classifiers to each of the intermediate layer groups. The modified model was retrained with our dataset and implemented using Pytorch. We constructed saliency maps to visualize our network's attention area of input images for its prediction. To explore the visual characteristics...