Classification of pet dog skin diseases using deep learning with images captured from multispectral imaging device

The skin of 95 pet dogs (23 with bacterial dermatosis, 19 with fungal infections, 23 with hypersensitivity allergic dermatosis, and 30 healthy) who visited the hospital with their owner for three types of spontaneously occurring skin diseases were imaged. The skin images of pet dogs were taken after obtaining written consent from dog owner. These image data set was used to build dog skin disease classification model using four convolution neural networks.

本数据集收录了95只宠物犬的皮肤影像数据，其中23例罹患细菌性皮肤病、19例为真菌感染、23例患超敏反应性过敏性皮炎，另有30例健康个体。所有受试宠物犬均随主人前往医院就诊，患病个体所患疾病为三类自发性皮肤疾病。所有皮肤影像均在获得犬主书面知情同意后采集完成。该图像数据集被用于构建基于四种卷积神经网络的犬类皮肤病分类模型。