Accurate Detection and Classification of Melanoma Skin Cancer Using Decision Tree Algorithm over CNN

Abstract

The study’s primary purpose is to propose an automatic melanoma cancer detection system using the Decision Tree algorithm and convolutional neural network algorithm to detect melanoma cancer and compare their accuracy. Group 1 was the Decision Tree algorithm with a sample size of 10, and Group 2 was a convolutional neural network algorithm with a sample size of 10. They were iterated 20 times to predict the accuracy percentage of identifying melanoma cancer. Compared to convolutional neural network accuracy(75.58 %), the Decision Tree method has substantially higher accuracy (85.61%). The Decision Tree p=0.018 (p<0.05) Independent Sample T-test has a high statistical significance. Within the scope of this study, the Decision Tree method outperforms convolutional neural networks in melanoma skin cancer detection.

Skin cancer diagnosis using artificial intelligence methods: a review of the most recent research

“…Additionally, it might be advantageous as an adjuvant in clinical decision-making 24 . Among the machine learning algorithms used in this context, are the KNN 25 , ANN 26 , decision trees 27 , and random forests 28 .…”