SurgWound-Bench: A Benchmark for Surgical Wound Diagnosis

2025-08-20

AI Summary

The lack of publicly available datasets and standardized benchmarks for surgical wound analysis hinders the development of open-source screening tools. Method: We introduce SurgWound, the first open surgical wound dataset—comprising 697 images with fine-grained annotations from three surgeons—and propose the first clinical-diagnostic multi-task benchmark, encompassing visual question answering and structured report generation. We design a novel three-stage multimodal learning framework: (1) fine-grained wound feature identification; (2) infection risk classification; and (3) natural language report generation. The framework integrates feature extraction from five vision-language models (VLMs), decision fusion from two classifiers, and report synthesis via one generative model, augmented with expert knowledge injection. Contribution/Results: Experiments demonstrate significant improvements in diagnostic accuracy, interpretability, and clinical utility, establishing a foundational platform for personalized intelligent wound care.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Surgical site infection (SSI) is one of the most common and costly healthcare-associated infections and and surgical wound care remains a significant clinical challenge in preventing SSIs and improving patient outcomes. While recent studies have explored the use of deep learning for preliminary surgical wound screening, progress has been hindered by concerns over data privacy and the high costs associated with expert annotation. Currently, no publicly available dataset or benchmark encompasses various types of surgical wounds, resulting in the absence of an open-source Surgical-Wound screening tool. To address this gap: (1) we present SurgWound, the first open-source dataset featuring a diverse array of surgical wound types. It contains 697 surgical wound images annotated by 3 professional surgeons with eight fine-grained clinical attributes. (2) Based on SurgWound, we introduce the first benchmark for surgical wound diagnosis, which includes visual question answering (VQA) and report generation tasks to comprehensively evaluate model performance. (3) Furthermore, we propose a three-stage learning framework, WoundQwen, for surgical wound diagnosis. In the first stage, we employ five independent MLLMs to accurately predict specific surgical wound characteristics. In the second stage, these predictions serve as additional knowledge inputs to two MLLMs responsible for diagnosing outcomes, which assess infection risk and guide subsequent interventions. In the third stage, we train a MLLM that integrates the diagnostic results from the previous two stages to produce a comprehensive report. This three-stage framework can analyze detailed surgical wound characteristics and provide subsequent instructions to patients based on surgical images, paving the way for personalized wound care, timely intervention, and improved patient outcomes.

Problem

• Addressing lack of open-source surgical wound datasets and benchmarks
• Developing AI framework for surgical wound infection diagnosis
• Overcoming data privacy and expert annotation cost barriers

Innovation

• Open-source dataset with diverse surgical wound images
• Three-stage MLLM framework for wound diagnosis
• Visual question answering and report generation tasks