Attention Based Feature Fusion Network for Monkeypox Skin Lesion Detection

TL;DR

This paper tackles automated monkeypox detection from skin lesion imagery, addressing diagnostic challenges due to similarity with other diseases. It proposes a lightweight ensemble that fuses features from EfficientNetV2B3 and ResNet152V2, augmented with an SE-Net attention module and dense post-processing for binary classification. The approach achieves a mean validation accuracy of 96.52% and a test accuracy of 97.19% on the Monkeypox Skin Lesion Dataset with strong precision and recall, outperforming prior methods. The work demonstrates the practical potential of attention-guided feature fusion in medical image classification and offers a scalable framework for rapid screening.

Abstract

The recent monkeypox outbreak has raised significant public health concerns due to its rapid spread across multiple countries. Monkeypox can be difficult to distinguish from chickenpox and measles in the early stages because the symptoms of all three diseases are similar. Modern deep learning algorithms can be used to identify diseases, including COVID-19, by analyzing images of the affected areas. In this study, we introduce a lightweight model that merges two pre-trained architectures, EfficientNetV2B3 and ResNet151V2, to classify human monkeypox disease. We have also incorporated the squeeze-and-excitation attention network module to focus on the important parts of the feature maps for classifying the monkeypox images. This attention module provides channels and spatial attention to highlight significant areas within feature maps. We evaluated the effectiveness of our model by extensively testing it on a publicly available Monkeypox Skin Lesions Dataset using a four-fold cross-validation approach. The evaluation metrics of our model were compared with the existing others. Our model achieves a mean validation accuracy of 96.52%, with precision, recall, and F1-score values of 96.58%, 96.52%, and 96.51%, respectively.

Figures (6)

• Figure 1: The overall pipeline of our proposed work.
• Figure 2: Architectural diagram of our proposed method.
• Figure 3: Squeeze-and-Excitation Network (SE-Net) Module hu2018squeeze
• Figure 4: Sample images from the Monkeypox Skin Lesion Dataset.
• Figure 5: Confusion matrix from the 4-fold cross-validation.