This paper introduces a deep-learning based efficient classifier for common dermatological conditions, aimed at people without easy access to skin specialists. We report approximately 80% accuracy, in a situation where primary care doctors have attained 57% success rate, according to recent literature. The rationale of its design is centered on deploying and updating it on handheld devices in near future. Dermatological diseases are common in every population and have a wide spectrum in severity. With a shortage of dermatological expertise being observed in several countries, machine learning solutions can augment medical services and advise regarding existence of common diseases. The paper implements supervised classification of nine distinct conditions which have high occurrence in East Asian countries. Our current attempt establishes that deep learning based techniques are viable avenues for preliminary information to aid patients.
翻译:本文介绍了一种基于深学习的常见皮肤病症有效分类方法,针对的是无法方便地接触皮肤专家的人。我们报告大约80%的准确性,根据最近的文献,在初级护理医生成功率达到57%的情况下,我们报告这种准确性。其设计的基本原理是在最近的将来在手持装置上部署和更新它。皮肤病在每一个人口中都是常见的,其严重程度很广。随着几个国家的皮肤病学专业知识的缺乏,机器学习解决方案可以增加医疗服务,就常见疾病的存在提供咨询。该文件对东亚国家高发病率的9种不同情况进行了监督分类。我们目前的尝试证明深层次的学习技术是帮助病人的初步信息的可行途径。