SurgiATM: A Physics-Guided Plug-and-Play Model for Deep Learning-Based Smoke Removal in Laparoscopic Surgery

2025-11-07

AI Summary

Laparoscopic electrosurgical smoke severely degrades endoscopic image quality, compromising surgical safety and hindering computer-assisted analysis. To address this, we propose SurgiATM: a physics-guided, plug-and-play lightweight smoke removal module. Its core innovation lies in the first integration of the atmospheric scattering physical model with deep learning to design a parameter-free, universal plugin—requiring only two hyperparameters for seamless integration into any smoke removal network. SurgiATM introduces zero inference overhead and operates without retraining. Extensive evaluation across three public surgical datasets demonstrates that integrating SurgiATM significantly reduces reconstruction error across ten state-of-the-art methods, while markedly improving model stability and cross-scenario generalization. This work provides an efficient, broadly applicable solution for real-time clinical smoke removal and robust visual analysis.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

During laparoscopic surgery, smoke generated by tissue cauterization can significantly degrade the visual quality of endoscopic frames, increasing the risk of surgical errors and hindering both clinical decision-making and computer-assisted visual analysis. Consequently, removing surgical smoke is critical to ensuring patient safety and maintaining operative efficiency. In this study, we propose the Surgical Atmospheric Model (SurgiATM) for surgical smoke removal. SurgiATM statistically bridges a physics-based atmospheric model and data-driven deep learning models, combining the superior generalizability of the former with the high accuracy of the latter. Furthermore, SurgiATM is designed as a lightweight, plug-and-play module that can be seamlessly integrated into diverse surgical desmoking architectures to enhance their accuracy and stability, better meeting clinical requirements. It introduces only two hyperparameters and no additional trainable weights, preserving the original network architecture with minimal computational and modification overhead. We conduct extensive experiments on three public surgical datasets with ten desmoking methods, involving multiple network architectures and covering diverse procedures, including cholecystectomy, partial nephrectomy, and diaphragm dissection. The results demonstrate that incorporating SurgiATM commonly reduces the restoration errors of existing models and relatively enhances their generalizability, without adding any trainable layers or weights. This highlights the convenience, low cost, effectiveness, and generalizability of the proposed method. The code for SurgiATM is released at https://github.com/MingyuShengSMY/SurgiATM.

Problem

• Removing surgical smoke to improve laparoscopic surgery visual quality
• Enhancing smoke removal accuracy while maintaining computational efficiency
• Developing plug-and-play module compatible with existing surgical desmoking systems

Innovation

• Physics-guided plug-and-play deep learning model
• Lightweight module with two hyperparameters and no trainable weights
• Seamlessly integrates into diverse surgical desmoking architectures