Lightweight dual-backbone network with attentional fusion for wound image classification

The global burden of acute and chronic wounds continues to demand improved classification methods, a critical step in guiding appropriate treatment plans. In this work, we present a lightweight dual-backbone deep learning architecture that combines EfficientNet-B3 and MobileNetV3-Small in a parallel feature extraction framework for wound image classification. The proposed network employs depthwise separable reduction layers, dynamic multi-scale mixers, parallel squeeze-and-excitation attention modules, efficient channel attention blocks, and a learned gated fusion mechanism to merge complementary features from both backbones. Our model was trained and evaluated on two publicly available datasets (AZH and Medetec) across Region of Interest (ROI) and whole image classification protocols using a 70/15/15 train-validation-test split. The proposed network achieves 90.63% accuracy on the six-class ROI classification task, improving upon the previous state-of-the-art of 85.41% by 5.22 percentage points, without requiring wound location data. Additionally, the model attains 85.03% on four-class whole image classification and 90.63% on three-class Medetec classification. Grad-CAM visualizations confirm that the network focuses on clinically relevant wound regions, supporting its potential as a decision-support tool for wound care practitioners.