Efficient Monkeypox Skin Lesion Detection Using Deep Learning in Mobile Applications
Annotatsiya
Monkeypox is skin lesion which is spreading continuously and infected by monkeypox virus. It spreads from infected person to other very fast. In this study, a comprehensive strategy has been presented employing sophisticated deep learning methodologies for the identification of monkeypox. Top of form using the power of Convolutional Neural Networks (CNN) and several state-of-the-art pretrained models including VGG16, VGG19, MobileNetV2, InceptionV3, ResNet50, DenseNet201 and Xception, tried to achieve high accuracy in identifying monkeypox prediction. Furthermore, and explored hybrid models combining CNN with InceptionV3, ResNet50, MobileNetV2, Xception and Support Vector Machine (SVM), as well as Random Forest (RF) classifiers. This investigation revealed that hybrid models, particularly CNN-InceptionV3, and InceptionV3-RF, alongside ensemble model using VGG16, Vgg19, InceptionV3, MobileNetV2 and Xception achieved superior performance with accuracy of 99%. Finally, to facilitate practical application, a mobile application has been developed by me, integrating the trained ensemble model, enabling accessible and efficient detection of monkeypox. Emphasis is placed on the potential of hybrid and ensemble of the various pre-trained deep learning models in medical diagnostics, and a robust tool is offered for managing monkeypox outbreaks in the future.