Extended Feature Space-Based Automatic Melanoma Detection System

TL;DR

This paper introduces a novel extended feature vector space algorithm for melanoma detection from skin images, demonstrating high accuracy and sensitivity using ensemble classifiers on a standard dataset.

Contribution

The study proposes the ExtFvAMDS algorithm for extended feature extraction, improving melanoma detection accuracy over traditional methods.

Findings

Achieved 99% AUC with HSV features and ensemble classifiers.

Attained 95.30% accuracy, 94.23% sensitivity, and 96.96% specificity.

Validated effectiveness on Med-Node dataset.

Abstract

Melanoma is the deadliest form of skin cancer. Uncontrollable growth of melanocytes leads to melanoma. Melanoma has been growing wildly in the last few decades. In recent years, the detection of melanoma using image processing techniques has become a dominant research field. The Automatic Melanoma Detection System (AMDS) helps to detect melanoma based on image processing techniques by accepting infected skin area images as input. A single lesion image is a source of multiple features. Therefore, It is crucial to select the appropriate features from the image of the lesion in order to increase the accuracy of AMDS. For melanoma detection, all extracted features are not important. Some of the extracted features are complex and require more computation tasks, which impacts the classification accuracy of AMDS. The feature extraction phase of AMDS exhibits more variability, therefore it is important to study the behaviour of AMDS using individual and extended feature extraction approaches. A novel algorithm ExtFvAMDS is proposed for the calculation of Extended Feature Vector Space. The six models proposed in the comparative study revealed that the HSV feature vector space for automatic detection of melanoma using Ensemble Bagged Tree classifier on Med-Node Dataset provided 99% AUC, 95.30% accuracy, 94.23% sensitivity, and 96.96% specificity.