{"title":"Mobile-based Intelligent Skin Diseases Diagnosis System","authors":"A. Sallam, Abdulfattah E. Ba Alawi","doi":"10.1109/ICOICE48418.2019.9035129","DOIUrl":null,"url":null,"abstract":"Skin diseases are the most common diseases in humans. The inherent variability in the appearance of skin diseases makes it hard even for medical experts to detect disease type from dermoscopic images. Recent advances in image processing using the Convolution Neural Networks have led to better results in diagnosing systems. We aim to develop an advanced diagnostic system in a manner that meets the requirements of real-time and extensibility of medical services for skin disease detection. The proposed system provides offline diagnosis for the users who have not Internet connection or online diagnosing uses on-cloud service. The user captures the affected area and get the offline immediate report. The schema offers the users a communication window with dermatologists to get medical recommendations in addition to an online accurate diagnosis service. The new images that are labeled by dermatologists are used to retrain the model to enhance model accuracy. To maximize the number of users, the system is implemented in a mobile-based environment. With the growing numbers of portable apps, it becomes easy for people to obtain up-to-date data. Users are familiar with looking for answers from the virtual globe including health issues. The following experimental results demonstrate the feasibility of the proposed method. The average obtained accuracy is 83% in testing cases.","PeriodicalId":109414,"journal":{"name":"2019 First International Conference of Intelligent Computing and Engineering (ICOICE)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 First International Conference of Intelligent Computing and Engineering (ICOICE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICOICE48418.2019.9035129","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
Skin diseases are the most common diseases in humans. The inherent variability in the appearance of skin diseases makes it hard even for medical experts to detect disease type from dermoscopic images. Recent advances in image processing using the Convolution Neural Networks have led to better results in diagnosing systems. We aim to develop an advanced diagnostic system in a manner that meets the requirements of real-time and extensibility of medical services for skin disease detection. The proposed system provides offline diagnosis for the users who have not Internet connection or online diagnosing uses on-cloud service. The user captures the affected area and get the offline immediate report. The schema offers the users a communication window with dermatologists to get medical recommendations in addition to an online accurate diagnosis service. The new images that are labeled by dermatologists are used to retrain the model to enhance model accuracy. To maximize the number of users, the system is implemented in a mobile-based environment. With the growing numbers of portable apps, it becomes easy for people to obtain up-to-date data. Users are familiar with looking for answers from the virtual globe including health issues. The following experimental results demonstrate the feasibility of the proposed method. The average obtained accuracy is 83% in testing cases.