WoundFormer: Multi-Scale Spatial Feature Fusion for Multi-Class Wound Tissue Segmentation

2026-05-19

AI Summary

This work addresses the challenges of multi-class chronic wound tissue segmentation, which include high intra-class variability, scarce annotations, and visually similar tissue appearances that lead to ambiguous boundaries and poor discriminability. To tackle these issues, the authors propose WoundFormer—a Transformer-based framework featuring a novel spatial-preserving multi-scale aggregation decoder that replaces the standard SegFormer decoder. This design is further enhanced with a convolutional context enrichment mechanism and hierarchical spatial interaction modeling, significantly improving boundary localization accuracy and the ability to distinguish between morphologically similar tissues while maintaining computational efficiency. Evaluated on the WoundTissueSeg and DFUTissue datasets, the method achieves a Dice score of 81.9%, outperforming current CNN- and Transformer-based baselines by up to 4.3 Dice points, with notable gains in segmentation performance for minority tissue classes.

Abstract

Chronic wounds such as diabetic foot ulcers and pressure injuries require accurate tissue-level assessment to guide treatment planning and monitor healing progression. While deep learning methods have advanced automated wound analysis, most existing approaches focus on binary segmentation and inadequately model heterogeneous tissue composition due to high intra-class variability and limited annotated data. Multi-class wound tissue segmentation, therefore, remains a challenging and clinically relevant problem. We propose WoundFormer, a transformer-based framework that enhances hierarchical spatial feature fusion for multi-class wound tissue segmentation. Specifically, we replace the standard SegFormer decoder with a spatially-preserving multi-scale aggregation head that maintains feature topology during cross-scale integration and strengthens contextual interactions through convolutional fusion. This design improves boundary localization and discrimination between visually similar tissue categories while preserving transformer efficiency. We evaluate WoundFormer on the WoundTissueSeg dataset (147 images, six tissue classes) and a second benchmark (DFUTissue dataset). The proposed method achieves an overall Dice score of 81.9%, outperforming strong CNN- and transformer-based baselines by up to 4.3 Dice points on the WoundTissueSeg benchmark, with consistent improvements across minority tissue classes. These results indicate that explicit modeling of hierarchical spatial interactions enhances transformer representations for heterogeneous wound tissue segmentation and supports more reliable quantitative wound assessment.

Problem

• multi-class wound segmentation
• chronic wounds
• tissue heterogeneity
• limited annotated data
• boundary localization

Innovation

• multi-scale feature fusion
• spatially-preserving aggregation
• transformer-based segmentation
• wound tissue classification
• convolutional-contextual fusion