提出可解释的视觉马尔可夫架构，提升多器官医学图像分类准确率与可信度。
EVM-Fusion: An Explainable Vision Mamba Architecture with Neural Algorithmic Fusion
- 采用多路径设计，融合密集网、U-Net与视觉马尔可夫模块，动态集成特征。
- 在9类多器官数据集上达到99.75%测试准确率，显著优于现有方法。
- 支持多种可解释性机制，适合临床可信AI诊断场景使用。
医学图像分类对临床决策至关重要，但准确性、可解释性和泛化能力仍具挑战。本文提出EVM-Fusion，一种基于新型神经算法融合（NAF）机制的可解释视觉马尔可夫架构，用于多器官医学图像分类。该模型采用多路径设计：由密集网（DenseNet）和U-Net构建的路径，结合视觉马尔可夫（Vim）模块，与传统特征路径并行运行。通过两阶段融合过程——跨模态注意力与迭代NAF块——实现特征的动态整合，其中NAF块可学习自适应融合策略。内在可解释性通过路径特异性空间注意力、Vim Δ值图、传统特征SE注意力及跨模态注意力权重实现。在包含9类器官的多样化医学图像数据集上的实验表明，EVM-Fusion在测试中达到99.75%的准确率，并提供多维度决策洞察，展现出在医疗诊断中构建可信AI的巨大潜力。
原文摘要 · Abstract (English)
Medical image classification is critical for clinical decision-making, yet demands for accuracy, interpretability, and generalizability remain challenging. This paper introduces EVM-Fusion, an Explainable Vision Mamba architecture featuring a novel Neural Algorithmic Fusion (NAF) mechanism for multi-organ medical image classification. EVM-Fusion leverages a multipath design, where DenseNet and U-Net based pathways, enhanced by Vision Mamba (Vim) modules, operate in parallel with a traditional feature pathway. These diverse features are dynamically integrated via a two-stage fusion process: cross-modal attention followed by the iterative NAF block, which learns an adaptive fusion algorithm. Intrinsic explainability is embedded through path-specific spatial attention, Vim Δ-value maps, traditional feature SE-attention, and cross-modal attention weights. Experiments on a diverse 9-class multi-organ medical image dataset demonstrate EVM-Fusion's strong classification performance, achieving 99.75% test accuracy and provide multi-faceted insights into its decision-making process, highlighting its potential for trustworthy AI in medical diagnostics.
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。