EVM-Fusion: An Explainable Vision Mamba Architecture with Neural Algorithmic Fusion

TL;DR

EVM-Fusion is an explainable neural architecture for multi-organ medical image classification that combines diverse feature pathways with a novel fusion mechanism, achieving high accuracy and interpretability.

Contribution

The paper introduces EVM-Fusion, a novel architecture with Neural Algorithmic Fusion for improved accuracy and explainability in medical image classification.

Findings

Achieved 99.75% test accuracy on a 9-class dataset.

Provided multi-faceted interpretability through attention and feature maps.

Demonstrated strong performance and explainability in medical diagnostics.

Abstract

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 {\Delta}-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.