A powerful deep learning method for skin cancer detection

Abstract

<p>The authors discussed the issues posed by our study’s inability to accurately diagnose skin cancer and distinguish between various skin growths, especially without the aid of cutting-edge medical technology and highly skilled diagnosticians. To that purpose, the authors have developed a deep learning (DL) method that can recognise skin cancer from images. This study investigates the use of a convolutional neural network (CNN) and the Keras Sequential-application programming interface (API) to detect cancer in seven different types of chronic lesions. The researchers used the HAM10000 dataset, which is openly available. 10,015 skin growth images with annotations are included in this dataset. The authors used several data pre-processing techniques after reading the data but before training our model. The authors provide pre-trained data for comparison and reliability assessments. Examples of transfer learning models that are used for comparison include ResNet50, DenseNet121, and VGG11. In the area of skin growth classification for skin cancer diagnosis, this helps in the identification of improved DL application procedures. Over 97.12% of the time, our suggested model accurately predicts the sort of skin that will develop.</p>