Mobile Application for Skin Cancer Risk Prediction Based on Embedded Convolution Neural Network Model
Bruno Trstenjak, Marko Hrnčić · Annals of DAAAM for ... & proceedings of the ... International DAAAM Symposium · 2020
The skin cancer has been a serious problem globally for a long time.For the prevention and early detection of this type of cancer, various scientific research and applications have been published.This paper is addressed to the introduction of a modern mobile application for the skin cancer risk prediction based on the embedded Convolution Neural Network model.The paper explains the working principle of the application, the structure of the model and how it is embedded in the mobile application.The results of testing and measuring the prediction accuracy are presented compared with similar classification models published in several scientific studies.The mobile app is downloaded and used by users from all over the world.In this study, the analysis of actual prediction results was performed, the results of risk assessment and geographical distribution of the users were actually measured.The end of the article presented the guidelines for further research and development of the prediction model.