Advanced Machine Learning Techniques for Detecting Irregularities in Skin Lesion Borders: Enhancing Early Skin Cancer Detection
Abstract
Dermatograms are pivotal in the early detection of skin cancer, a disease with significant mortality rates. This paper introduces a novel feature extraction method that captures irregularities in the boundaries of abnormal skin regions. Each raw dermatogram is converted into a binary mask image using an effective segmentation algorithm. The boundary of the lesion region is extracted from the mask. The boundary, together with the centroid of the lesion mask, is used to define a set of directional vectors. An Arc is defined using these directional vectors, and a new Arc feature is calculated based on the number of times the lesion boundary crosses the arc. The proposed Arc feature is evaluated using three standard skin lesion datasets: ISBI 2016, HAM10000, and PH2. Additionally, color features and Local Binary Pattern (LBP) features are implemented for comparison. Classical machine learning algorithms are employed to evaluate these features. Results indicate that for the ISBI 2016 and HAM10000 datasets, the Arc feature set demonstrates superior classification accuracy. In contrast, the PH2 dataset benefits more from the LBP feature. Comparative analysis with recent studies highlights the dependency of accuracy on datasets and classifiers, underscoring the necessity for models incorporating feature fusion and ensemble classifiers. The proposed method outperforms traditional color and texture features and shows competitive results against deep learning models, particularly in scenarios with limited computational resources. These findings suggest that the Arc feature is a promising approach for improving skin cancer detection, although further investigation is needed to fine-tune performance, optimize classifier selection, and explore feature fusion strategies.
| Remember to check out the Most Cited Articles! |
|---|
|
Check out Notable Titles in Artificial Intelligence. |
