Enhancement of Digital Mammography Images Using Neutrosophic Divergence Score Based on Intuitionistic Fuzzy Entropy

Area of Science:

• Medical Imaging
• Computer Vision
• Artificial Intelligence

Background:

• Low contrast and brightness in mammograms hinder the detection of masses and microcalcifications.
• This uncertainty impacts radiologists' diagnostic accuracy, necessitating advanced image enhancement techniques.

Purpose of the Study:

• To develop an improved digital mammography image enhancement method.
• The goal is to reduce diagnostic uncertainty, enhance image contrast, and preserve fine details for better clinical assessment.

Main Methods:

• A five-stage framework integrating intuitionistic fuzzy entropy and neutrosophic sets (NSs).
• Key steps include fuzzy set transformation, entropy application for ambiguity reduction, NS conversion, detail enhancement via neutrosophic divergence score (NDS), and contrast improvement using fuzzy histogram hyperbolization.
• Performance evaluated on benchmark datasets using quantitative metrics and qualitative visual assessment.

Main Results:

• The proposed method outperformed existing techniques, including intuitionistic fuzzy sets, type-2 fuzzy sets, and other neutrosophic methods.
• Achieved superior contrast enhancement, maintained image naturalness, and effectively highlighted subtle mammographic features.

Conclusions:

• The method significantly reduces uncertainty in mammograms, improving visibility and diagnostic accuracy for radiologists.
• Demonstrated robust performance across various breast tissue types, positioning it as a valuable tool for computer-aided diagnosis systems.