This paper presents a deep learning-based wound classification tool that can assist medical personnel in non-wound care specialization to classify five key wound conditions, namely deep wound, infected wound, arterial wound, venous wound, and pressure wound, given color images captured using readily available cameras. The accuracy of the classification is vital for appropriate wound management. The proposed wound classification method adopts a multi-task deep learning framework that leverages the relationships among the five key wound conditions for a unified wound classification architecture. With differences in Cohen's kappa coefficients as the metrics to compare our proposed model with humans, the performance of our model was better or non-inferior to those of all human medical personnel. Our convolutional neural network-based model is the first to classify five tasks of deep, infected, arterial, venous, and pressure wounds simultaneously with good accuracy. The proposed model is compact and matches or exceeds the performance of human doctors and nurses. Medical personnel who do not specialize in wound care can potentially benefit from an app equipped with the proposed deep learning model.

翻译：本文提出了一种基于深度学习的伤口分类工具，可协助非伤口护理专业的医疗人员，利用普通相机拍摄的彩色图像对五种关键伤口状况进行分类，包括深度伤口、感染伤口、动脉性伤口、静脉性伤口及压力性伤口。分类的准确性对适当的伤口管理至关重要。所提出的伤口分类方法采用多任务深度学习框架，利用五种关键伤口状况之间的关联性构建统一的伤口分类架构。以Cohen's kappa系数差异作为指标，将我们的模型与人类进行比较，结果显示模型性能优于或不逊于所有人类医疗人员。我们基于卷积神经网络的模型首次实现了同时对深度、感染、动脉性、静脉性和压力性五类伤口进行高精度分类。该模型架构紧凑，其性能达到或超过人类医生与护士的水平。非伤口护理专业的医疗人员可通过配备该深度学习模型的应用程序获得潜在助益。