Monkeypox Skin Lesion Classification Using Fine-Tune CNN Model
Dhwani Jagani, Sheshang Degadwala
Abstract
A novel method for categorizing Monkeypox skin lesions is presented in this research work utilizing a finely adjusted Convolutional Neural Network (CNN) model. Monkeypox, a rare viral ailment that can lead to serious skin lesions, necessitates precise and prompt diagnosis for successful therapy. This research work refines a pre-existing CNN model using a collection of Monkeypox skin lesion pictures to construct a classification system that can differentiate between various lesion types. The experimental findings showcase the efficacy of this proposed method, achieving remarkable accuracy and sensitivity in Monkeypox skin lesion classification. This study contributes significantly to the advancement of automated diagnostic solutions for infectious illnesses, supporting healthcare professionals in making quicker and more precise diagnoses.