Computational intelligence approaches for malignant melanoma detection and diagnosis

Abstract

Malignant melanoma is reported to be the deadliest of skin cancers. Therefore, early diagnosis is crucial for reducing of melanoma-related deaths. Medical Informatics uses the computer technology such as Computer Aided Diagnosis (CAD) for melanoma diagnostic. This paper presents computational intelligence approaches namely, Artificial Neural Network (ANN) and Adaptive-Network-based Fuzzy Inference System (ANFIS). The dermoscopy images are taken from Dermatology Information System (DermIS) and DermQuest, image enhancement is achieved by various pre-processing approaches. The extracted features are based on Discrete Wavelet Transform (DWT), and Principle Component Analysis (PCA) is used to take the eigenvalue as features. These features become the input to the various classification approaches such as: ANN and ANFIS to classify the lesions as malignant or benign. The results show the rate of accuracy for ANFIS is 95.18%, while ANN gives higher rate of accuracy about 98.8%. Moreover; the results obtained are compared with other approaches. The comparative results indicated that the proposed feature extraction and classification approaches are more accurate than other approaches in this field of melanoma diagnosis.