Spitzoid Lesions Diagnosis based on GA feature selection and Random Forest
This work addresses a critical problem for dermatopathologists in distinguishing highly similar spitzoid lesions, though it is incremental as it combines existing methods on a private dataset.
The study tackled the challenge of accurately diagnosing spitzoid lesions (Spitz Nevus, Atypical Spitz Tumors, and Spitz Melanomas) by developing an AI model using SMOTE, genetic algorithm feature selection, and Random Forest, achieving high performance with accuracy of 0.97, F-measure of 0.98, AUC of 0.98, and G-mean of 0.97.
Spitzoid lesions broadly categorized into Spitz Nevus (SN), Atypical Spitz Tumors (AST), and Spitz Melanomas (SM). The accurate diagnosis of these lesions is one of the most challenges for dermapathologists; this is due to the high similarities between them. Data mining techniques are successfully applied to situations like these where complexity exists. This study aims to develop an artificial intelligence model to support the diagnosis of Spitzoid lesions. A private spitzoid lesions dataset have been used to evaluate the system proposed in this study. The proposed system has three stages. In the first stage, SMOTE method applied to solve the imbalance data problem, in the second stage, in order to eliminate irrelevant features; genetic algorithm is used to select significant features. This later reduces the computational complexity and speed up the data mining process. In the third stage, Random forest classifier is employed to make a decision for two different categories of lesions (Spitz nevus or Atypical Spitz Tumors). The performance of our proposed scheme is evaluated using accuracy, sensitivity, specificity, G-mean, F- measure, ROC and AUC. Results obtained with our SMOTE-GA-RF model with GA-based 16 features show a great performance with accuracy 0.97, F-measure 0.98, AUC 0.98, and G-mean 0.97.Results obtained in this study have potential to open new opportunities in diagnosis of spitzoid lesions.