cs.CVApr 8, 2025

WoundAmbit: Bridging State-of-the-Art Semantic Segmentation and Real-World Wound Care

Authors: Vanessa Borst, Timo Dittus, Tassilo Dege, Astrid Schmieder, Samuel Kounev

Organizations: Julius-Maximilians-University Würzburg, 97070 Würzburg, Germany · University Hospital Würzburg, 97070 Würzburg, Germany

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Chronic wounds affect a large population, particularly the elderly and diabetic patients, who often exhibit limited mobility and co-existing health conditions. Automated wound monitoring via mobile image capture can reduce in-person physician visits by enabling remote tracking of wound size. Semantic segmentation is key to this process, yet wound segmentation remains underrepresented in medical imaging research. To address this, we benchmark state-of-the-art deep learning models from general-purpose vision, medical imaging, and top methods from public wound challenges. For a fair comparison, we standardize training, data augmentation, and evaluation, conducting cross-validation to minimize partitioning bias. We also assess real-world deployment aspects, including generalization to an out-of-distribution wound dataset, computational efficiency, and interpretability. Additionally, we propose a reference object-based approach to convert AI-generated masks into clinically relevant wound size estimates and evaluate this, along with mask quality, for the five best architectures based on physician assessments. Overall, the transformer-based TransNeXt showed the highest levels of generalizability. Despite variations in inference times, all models processed at least one image per second on the CPU, which is deemed adequate for the intended application. Interpretability analysis typically revealed prominent activations in wound regions, emphasizing focus on clinically relevant features. Expert evaluation showed high mask approval for all analyzed models, with VWFormer and ConvNeXtS backbone performing the best. Size retrieval accuracy was similar across models, and predictions closely matched expert annotations. Finally, we demonstrate how our AI-driven wound size estimation framework, WoundAmbit, is integrated into a custom telehealth system.

Figures & tables

Figure 1: Schematic visualization of our WoundAmbit approach.
Table 1: Overview of the selected methods besides our baseline U-Net [ 1 ] .
Figure 2: Gradient-weighted Class Activation Mapping for exemplary OOD images, alongside their GT annotation.
Figure 3: Visualization of the size retrieval process for exemplar real-world patients.
Figure 4: Overview of the seven wounds with consistent expert size estimates.
Figure 5: Simplified visualization of the overall telehealth system.
Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 0.A.1 : Grad-CAM for exemplary OOD images, alongside their GT annotation.
Figure 0.A.2 : Grad-CAM for further OOD images, alongside their GT annotation.
Table 0.B.1 : Comparison of the mask, size (in mm), and area (in cm2\text{cm}^{2} ) predictions for different wounds. If more than one wound is detected, we report the dimension and area of the largest wound in the image.
Figure 0.B.1 : Mask Quality Assessment and Image Annotation Tool
More in this topic

Medical Image Analysis

Medical image analysis uses computational methods to interpret clinical images, measure anatomy and disease, and support diagnosis and treatment.

See all 292 papers

Explore similar work

CardsList
Mar 28, 2026

Automated multi-class wound assessment using dedicated instance segmentation models for boundary detection and classification

Accurate wound classification (WC) and boundary segmentation are essential for guiding clinical decisions in chronic and acute wound management. However, most existing artificial intelligence (AI) models are limited, focusing on a narrow set of wound types, limited variations in wound severity, or a single task (segmentation or classification), which reduces their clinical applicability. This study presents two dedicated instance segmentation models based on You Only Look Once (YOLO)v11 that perform wound boundary segmentation (WBS) and WC across five clinically relevant wound types: burn injury (BI), pressure injury, diabetic foot ulcer, vascular ulcer, and surgical wound. A wound-type balanced dataset of 2,963 annotated images was created to train the models for both tasks, using five-fold cross-validation. Models trained on the original, non-augmented dataset performed consistently across folds, though BI detection accuracy was relatively low; augmenting the dataset with rotation, flipping, and variations in brightness, saturation, and exposure significantly improved performance, particularly for visually subtle BI cases. Among the tested variants, YOLOv11x achieved the best WBS performance (F1-score: 0.9341; mAP50: 0.9629). For WC, YOLOv11m achieved the highest mAP50 (0.9194) and mAP50-95 (0.6950), whereas YOLOv11l achieved the highest F1-score (0.8797). The lightweight YOLOv11n provided comparable accuracy at lower computational cost, making it suitable for resource-constrained deployments. Supported by confusion matrices and visual detection outputs, the results confirm robustness against complex backgrounds and high intra-class variability, demonstrating the potential of YOLOv11-based architectures for accurate, real-time wound analysis in clinical and remote care settings.

Mehedi Hasan Tusar, Fateme Fayyazbakhsh, Igor Melnychuk +1

Department of Mechanical and Aerospace Engineering, College of Engineering and Computing, Missouri University of Science and Technology, Rolla, Missouri, United States of America · Missouri Protoplex, Missouri University of Science and Technology, Rolla, Missouri, United States of America · Center for Biomedical Research, Missouri University of Science and Technology, Rolla, Missouri, United States of America +2

Instance SegmentationMedical Image ClassificationMedical Image SegmentationObject Detection
AskPDF
May 19, 2026

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

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.

Muhammad Ashad Kabir, Rabin Dulal

School of Computing, Mathematics and Engineering, Charles Sturt University, NSW, Australia

Multi-Scale Feature FusionMedical Image Segmentation
AskPDF
Oct 4, 2026

WILLIE: A Unified Framework and Benchmark for Wound Classification, Segmentation, and Localization

Chronic wound management affects over 8.2 million patients in the United States and imposes substantial clinical and economic burden. Clinical wound assessment commonly involves three coupled tasks: identifying wound type, delineating wound boundaries, and localizing the wound region for measurement and monitoring. Despite this clinical coupling, existing machine learning approaches typically address wound classification, segmentation, and localization using separate models. We present WILLIE, a unified framework and benchmark for wound classification, segmentation and localization that enables systematic evaluation of multi-task wound analysis under a common protocol. WILLIE harmonizes three public wound datasets into a shared benchmark and compares unified models across three scaling configurations against 10 single-task baselines. The best model achieves 91.88% classification accuracy, 91.41% Dice, and 96.23% [email protected] while producing all three outputs in a single forward pass. Beyond aggregate performance, our results show that segmentation-derived localization outperforms dedicated detection baselines in this benchmark, suggesting that box-based localization may be unnecessary for spatially coherent wound targets. Our findings highlight that effective multi-task learning in healthcare imaging depends not only on shared representations, but also on task formulation, compatibility, and benchmark design.

Gopi Trinadh Maddikunta, Shannan Hamlin, Hsin-Mei Chen +2

Department of Computer Science University of Houston Houston, Texas, USA · Houston Methodist Academic Institute Houston Methodist Hospital System Houston, Texas, USA

Multi-Task LearningMedical Image SegmentationMedical Image LocalizationMedical Image Benchmarks
AskPDF