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

TL;DR

SurgiATM is a physics-guided, plug-and-play deep learning module that effectively removes surgical smoke from laparoscopic images, improving image quality and surgical safety without altering existing model architectures.

Contribution

It introduces a lightweight, physics-informed atmospheric model that enhances deep learning-based surgical smoke removal with minimal modifications and no additional trainable parameters.

Findings

Reduces restoration errors across multiple datasets and architectures

Enhances generalizability of existing models in surgical smoke removal

Operates with minimal hyperparameters and no extra training overhead

Abstract

During laparoscopic surgery, smoke generated by tissue cauterization degrade endoscopic frames quality, increasing surgical risk and hindering both clinical decision-making and computer-assisted visual analysis. Therefore, removing surgical smoke is essential for patient safety and 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. 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. The proposed method is derived via statistically optimizing MoE model at the output end of arbitrary deep learning methods, with a Laplacian-like error distribution specifically leveraged to model surgical smoke. The output-stage MoE ensures minimal modification to the architecture of the original methods, while the Laplacian-like distribution characteristic of surgical smoke enables a lightweight reconstruction formulation with minimal parameters. Therefore, SurgiATM introduces only two hyperparameters and no extra trainable weights, preserving the original network architecture with minimal overhead. We conduct extensive experiments on three public surgical datasets, 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.