Usman Saif2025-09-262025-09-262019https://escholar.umt.edu.pk/handle/123456789/7126Skin cancer, being one of common and rapid increasing human malignancy, is diagnosed visually. The diagnosis begins with preliminary medical screening and by dermoscopic analysis, histopathological examination and a biopsy. In this research, skin images are classified into seven skin cancer classes using Convolutional Neural Network (CNN) model along with Long Short-Term Memory (LSTM) and then analyses of the results is made to see if the model can be useful in a practical scenario. It seems our model has a maximum number of correct predicted values for code 4 label akiec and incorrect predictions for Basal cell carcinoma which has code 3, then the second most misclassified type is Vascular lesions code 5 then Melanocytic nevi code 0 whereas Actinic keratoses code 4 has least misclassified type. We can also further tune our model to easily achieve the accuracy above 80%, and still this model is efficient in comparison to detection with human eyes, as human error can never be overlooked.enThesis