Energy- and Contrast-Aware NSST-Based Medical Image Fusion with Anisotropic Diffusion Enhancement

Abstract

Medical image fusion (MIF) integrates complementary information from multiple modalities to enhance diagnostic accuracy. However, existing approaches often struggle to suppress noise while preserving critical anatomical details. We propose ENCAF-NSST-AD, a fusion technique that combines the Non-Subsampled Shearlet Transform (NSST) with anisotropic diffusion (AD) refinement. Lowfrequency base layers (LFBL) are fused using an energy-based weighting strategy, while high-frequency detail layers (HFDL) are integrated through a contrast-aware rule. The reconstructed image is further enhanced using AD filtering with optimized parameters to improve clarity and preserve structural information. Experiments on standard medical image datasets demonstrate that ENCAF-NSST-AD consistently outperforms existing methods in both visual quality and quantitative metrics, including FMI, FF, entropy, and standard deviation. Experiments on benchmark datasets demonstrate that ENCAF-NSST-AD achieves superior fusion quality compared with existing state-of-the-art methods, exhibiting enhanced visual clarity and higher values across standard quantitative metrics. The proposed method effectively balances noise suppression with edge preservation, addressing limitations of traditional MIF schemes. By combining adaptive fusion rules with edgepreserving diffusion, ENCAF-NSST-AD preserves global contrast and fine anatomical boundaries, resulting in fused images more suitable for clinical interpretation. Its energy- and contrast- aware fusion with AD refinement represents a clinically relevant and patent-oriented advancement. The integration of NSST with adaptive fusion rules and AD refinement produces robust and diagnostically meaningful fusion outcomes. ENCAF-NSST-AD is an effective MIF approach that can enhance clinical decision support in medical imaging.