提升医学影像融合的全局相关性与局部清晰度平衡
W-DUALMINE: Reliability-Weighted Dual-Expert Fusion With Residual Correlation Preservation for Medical Image Fusion
- 双专家架构结合空间与频域信息，自适应加权融合
- 保留全局相关性的同时增强局部细节，指标优于现有方法
- 适合需要高保真医学图像分析的临床研究场景
医学图像融合通过整合多模态影像的互补信息，提升临床判读效果。然而，现有基于深度学习的方法，包括最近的空间-频率框架AdaFuse和ASFE-Fusion，普遍面临全局统计相似性（相关系数CC与互信息MI）与局部结构保真度之间的根本性权衡。本文提出W-DUALMINE，一种可靠性加权的双专家融合框架，通过架构约束与理论支撑的损失设计，显式解决该权衡问题。方法引入密集可靠性图实现模态自适应加权，采用包含全局上下文空间专家与小波域频域专家的双专家融合策略，并设计软梯度仲裁机制。此外，采用残差均值融合范式，在保证全局相关性的同时强化局部细节。在CT-MRI、PET-MRI与SPECT-MRI数据集上的大量实验表明，W-DUALMINE在CC与MI指标上持续优于AdaFuse和ASFE-Fusion。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。