Automated Skin Lesion Classification Using Efficientnet-B4 Deep Learning Architecture On The Ham10000 Dataset

Abstract

Timely diagnosis of skin cancer is a key to longer life and better results of the treatment process; nevertheless, exploring dermoscopic images manually by the dermatologists is both time-consuming and has a high risk of diagnostic variability owing to the visual similarity of various types of skin lesions. In recent times, the development of deep learning has produced automated systems of image analysis as potentially useful tools in helping diagnose a medical illness. The current research provides a framework of deep learning-based classification of multiclass skin lesions with the help of the EfficientNet-B4 and HAM10000 models. The data set has dermoscopic images of seven classes of diagnoses, such as melanoma, basal cell carcinoma, benign keratosis, dermatofibroma, vascular lesion, actinic keratoses, and melanocytic nevus. The image preprocessing and augmentation methods are used to enhance the generalization and training efficiency of models whereas transfer learning is used to fine-tune the EfficientNet-B4 network to the task of classification. The provided model is experimentally tested to present the overall accuracy of 86.9% which proves the effectiveness of deep learning methods in assisting in early skin cancer screening and computerized dermatological diagnosis.