NeDSeM: Neutrosophy Domain-Based Segmentation Method for Malignant Melanoma Images

Area of Science:

• Medical Imaging
• Computer Vision
• Dermatology

Background:

• Accurate skin lesion segmentation is crucial for diagnosing malignant melanoma.
• Existing methods struggle with the nonlinear, gradual color changes at lesion edges.
• Fuzzy theory limitations in handling uncertain and fuzzy boundaries necessitate advanced approaches.

Purpose of the Study:

• To develop a robust segmentation method for accurately identifying malignant melanoma lesion edges.
• To address the limitations of current techniques in segmenting uncertain and fuzzy banded edges.
• To leverage neutrosophic set theory for enhanced skin lesion edge detection.

Main Methods:

• Proposed a six-step neutrosophy domain-based segmentation (NeDSeM) method.
• Converted images to Neutrosophic Set domain to represent edge uncertainty and fuzziness.
• Introduced a Neutrosophic Entropy model to highlight lesion edges.
• Utilized feature augmentation and dilation for noise reduction.
• Employed Hierarchical Gaussian Mixture Model clustering for final segmentation.

Main Results:

• The NeDSeM method demonstrated effective segmentation of malignant melanoma lesion edges.
• Qualitative and quantitative experiments confirmed the method's performance.
• Achieved superior results compared to state-of-the-art methods in terms of accuracy and performance.

Conclusions:

• The proposed NeDSeM method offers a significant advancement in segmenting uncertain and fuzzy skin lesion edges.
• Neutrosophic set theory provides a powerful framework for addressing challenges in medical image segmentation.
• The method shows promise for improving the accuracy of malignant melanoma diagnosis.