W-DUALMINE: Reliability-Weighted Dual-Expert Fusion With Residual Correlation Preservation for Medical Image Fusion

TL;DR

W-DUALMINE is a novel deep learning framework for medical image fusion that balances global correlation and local detail preservation through reliability-weighted dual-expert fusion and residual correlation strategies.

Contribution

It introduces a reliability-weighted dual-expert fusion architecture with residual correlation preservation, explicitly addressing the trade-off between correlation and mutual information in medical image fusion.

Findings

Outperforms existing methods in correlation and mutual information metrics

Effectively preserves global correlation and enhances local details

Demonstrates robustness across multiple medical imaging modalities

Abstract

Medical image fusion integrates complementary information from multiple imaging modalities to improve clinical interpretation. However, existing deep learningbased methods, including recent spatial-frequency frameworks such as AdaFuse and ASFE-Fusion, often suffer from a fundamental trade-off between global statistical similaritymeasured by correlation coefficient (CC) and mutual information (MI)and local structural fidelity. This paper proposes W-DUALMINE, a reliability-weighted dual-expert fusion framework designed to explicitly resolve this trade-off through architectural constraints and a theoretically grounded loss design. The proposed method introduces dense reliability maps for adaptive modality weighting, a dual-expert fusion strategy combining a global-context spatial expert and a wavelet-domain frequency expert, and a soft gradient-based arbitration mechanism. Furthermore, we employ a residual-to-average fusion paradigm that guarantees the preservation of global correlation while enhancing local details. Extensive experiments on CT-MRI, PET-MRI, and SPECT-MRI datasets demonstrate that W-DUALMINE consistently outperforms AdaFuse and ASFE-Fusion in CC and MI metrics while