Benchmarking Laparoscopic Surgical Image Restoration and Beyond

2025-05-25

AI Summary

In laparoscopic surgery, concurrent visual degradations—including smoke, lens fogging, and fluid splashes—severely impair surgical field clarity and compromise patient safety. To address this, we introduce SurgClean, the first open-source paired dataset (1,020 images) specifically designed for surgical image restoration. We formally define the multi-type surgical degradation task and establish the first standardized benchmark for evaluating surgical image restoration algorithms. Leveraging this benchmark, we comprehensively assess 22 state-of-the-art general-purpose and domain-specific methods, revealing critical deficiencies in clinical applicability—e.g., widespread failure to meet clinically required PSNR/SSIM thresholds. Further, we analyze fundamental distinctions between surgical and natural-image degradations from both structural and semantic perspectives. Our work provides reproducible baselines, rigorous degradation characterization, and actionable insights to advance the development of minimally invasive surgery–specific image restoration algorithms.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

In laparoscopic surgery, a clear and high-quality visual field is critical for surgeons to make accurate intraoperative decisions. However, persistent visual degradation, including smoke generated by energy devices, lens fogging from thermal gradients, and lens contamination due to blood or tissue fluid splashes during surgical procedures, severely impair visual clarity. These degenerations can seriously hinder surgical workflow and pose risks to patient safety. To systematically investigate and address various forms of surgical scene degradation, we introduce a real-world open-source surgical image restoration dataset covering laparoscopic environments, called SurgClean, which involves multi-type image restoration tasks, e.g., desmoking, defogging, and desplashing. SurgClean comprises 1,020 images with diverse degradation types and corresponding paired reference labels. Based on SurgClean, we establish a standardized evaluation benchmark and provide performance for 22 representative generic task-specific image restoration approaches, including 12 generic and 10 task-specific image restoration approaches. Experimental results reveal substantial performance gaps relative to clinical requirements, highlighting a critical opportunity for algorithm advancements in intelligent surgical restoration. Furthermore, we explore the degradation discrepancies between surgical and natural scenes from structural perception and semantic understanding perspectives, providing fundamental insights for domain-specific image restoration research. Our work aims to empower the capabilities of restoration algorithms to increase surgical environments and improve the efficiency of clinical procedures.

Problem

• Addressing visual degradation in laparoscopic surgery images
• Creating a dataset for surgical image restoration tasks
• Evaluating performance gaps in current restoration algorithms

Innovation

• Introduces SurgClean dataset for surgical image restoration
• Benchmarks 22 image restoration methods on SurgClean
• Analyzes surgical-natural scene degradation differences