# MDF2Former: Multi-Scale Dual-Domain Feature Fusion Transformer for Hyperspectral Image Classification of Bacteria in Murine Wounds

## TL;DR

This paper introduces a new AI model for quickly and accurately identifying bacteria in wounds using hyperspectral imaging, which could improve treatment outcomes.

## Contribution

A novel transformer model, MDF2Former, is proposed for hyperspectral image classification of wound bacteria with multi-scale dual-domain feature fusion.

## Key findings

- MDF2Former achieved 91.94% accuracy in classifying wound bacteria using hyperspectral imaging.
- The model outperformed existing methods across multiple evaluation metrics like precision and F1-score.
- The study demonstrates the potential of combining HSI and deep learning for rapid bacterial identification.

## Abstract

Bacterial wound infection poses a major challenge in trauma care and can lead to severe complications such as sepsis and organ failure. Therefore, rapid and accurate identification of the pathogen, along with targeted intervention, is of vital importance for improving treatment outcomes and reducing risks. However, current detection methods are still constrained by procedural complexity and long processing times. In this study, a hyperspectral imaging (HSI) acquisition system for bacterial analysis and a multi-scale dual-domain feature fusion transformer (MDF2Former) were developed for classifying wound bacteria. MDF2Former integrates three modules: a multi-scale feature enhancement and fusion module that generates tokens with multi-scale discriminative representations, a spatial–spectral dual-branch attention module that strengthens joint feature modeling, and a frequency and spatial–spectral domain encoding module that captures global and local interactions among tokens through a hierarchical stacking structure, thereby enabling more efficient feature learning. Extensive experiments on our self-constructed HSI dataset of typical wound bacteria demonstrate that MDF2Former achieved outstanding performance across five metrics: Accuracy (91.94%), Precision (92.26%), Recall (91.94%), F1-score (92.01%), and Kappa coefficient (90.73%), surpassing all comparative models. These results have verified the effectiveness of combining HSI with deep learning for bacterial identification, and have highlighted its potential in assisting in the identification of bacterial species and making personalized treatment decisions for wound infections.