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

• URL: http://arxiv.org/abs/2511.05059v1
• Date: Fri, 07 Nov 2025 08:04:24 GMT
• Title: SurgiATM: A Physics-Guided Plug-and-Play Model for Deep Learning-Based Smoke Removal in Laparoscopic Surgery
• Authors: Mingyu Sheng, Jianan Fan, Dongnan Liu, Guoyan Zheng, Ron Kikinis, Weidong Cai,
• Abstract summary: Smoke generated by tissue cauterization can significantly degrade the visual quality of endoscopic frames.<n>We propose the Surgical Atmospheric Model (SurgiATM) for surgical smoke removal.<n>SurgiATM statistically bridges a physics-based atmospheric model and data-driven deep learning models.
• Score: 16.71481757853012
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• RGA-Net: A Vision Enhancement Framework for Robotic Surgical Systems Using Reciprocal Attention Mechanisms [25.435178288442597]
  RGA-Net is a novel deep learning framework specifically designed for smoke removal in robotic surgery.<n>Our approach addresses the challenges of surgical smoke-including dense, non-homogeneous distribution and complex light scattering-through a hierarchical encoder-decoder architecture.
  arXiv  Detail & Related papers  (2026-02-14T11:31:54Z)
• How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment [69.13598421861654]
  We present SurgVeo, the first expert-curated benchmark for video generation model evaluation in surgery.<n>We task the advanced Veo-3 model with a zero-shot prediction task on surgical clips from laparoscopic and neurosurgical procedures.<n>Our results reveal a distinct "plausibility gap": while Veo-3 achieves exceptional Visual Perceptual Plausibility, it fails critically at higher levels of the Surgical Plausibility Pyramid.
  arXiv  Detail & Related papers  (2025-11-03T17:28:54Z)
• Adaptive transfer learning for surgical tool presence detection in laparoscopic videos through gradual freezing fine-tuning [1.1371756033920992]
  Minimally invasive surgery can benefit from automated surgical tool detection, enabling advanced analysis and assistance.<n>The limited availability of annotated data in surgical settings poses a challenge for training robust deep learning models.<n>This paper introduces a novel staged adaptive fine-tuning approach consisting of two steps: a linear probing stage and a gradual freezing stage.
  arXiv  Detail & Related papers  (2025-10-17T07:17:52Z)
• SurgVisAgent: Multimodal Agentic Model for Versatile Surgical Visual Enhancement [8.337819078911405]
  SurgVisAgent is an end-to-end intelligent surgical vision agent built on multimodal large language models (MLLMs)<n>It dynamically identifies distortion categories and severity levels in endoscopic images, enabling it to perform a variety of enhancement tasks.<n>We construct a benchmark simulating real-world surgical distortions, on which extensive experiments demonstrate that SurgVisAgent surpasses traditional single-task models.
  arXiv  Detail & Related papers  (2025-07-03T03:00:26Z)
• Toward Reliable AR-Guided Surgical Navigation: Interactive Deformation Modeling with Data-Driven Biomechanics and Prompts [21.952265898720825]
  We propose a data-driven algorithm that preserves FEM-level accuracy while improving computational efficiency.<n>We introduce a novel human-in-the-loop mechanism into the deformation modeling process.<n>Our algorithm achieves a mean target registration error of 3.42 mm, surpassing state-of-the-art methods in volumetric accuracy.
  arXiv  Detail & Related papers  (2025-06-08T14:19:54Z)
• Benchmarking Laparoscopic Surgical Image Restoration and Beyond [54.28852320829451]
  In laparoscopic surgery, a clear and high-quality visual field is critical for surgeons to make accurate decisions.<n> persistent visual degradation, including smoke generated by energy devices, lens fogging from thermal gradients, and lens contamination pose risks to patient safety.<n>We introduce a real-world open-source surgical image restoration dataset covering laparoscopic environments, called SurgClean.
  arXiv  Detail & Related papers  (2025-05-25T14:17:56Z)
• Surgical Foundation Model Leveraging Compression and Entropy Maximization for Image-Guided Surgical Assistance [50.486523249499115]
  Real-time video understanding is critical to guide procedures in minimally invasive surgery (MIS)<n>We propose Compress-to-Explore (C2E), a novel self-supervised framework to learn compact, informative representations from surgical videos.<n>C2E uses entropy-maximizing decoders to compress images while preserving clinically relevant details, improving encoder performance without labeled data.
  arXiv  Detail & Related papers  (2025-05-16T14:02:24Z)
• Improved Brain Tumor Detection in MRI: Fuzzy Sigmoid Convolution in Deep Learning [5.350541719319564]
  Fuzzy sigmoid convolution (FSC) is introduced along with two additional modules: top-of-the-funnel and middle-of-the-funnel.<n>A novel convolutional operator is central to this approach, effectively dilating the receptive field while preserving input data integrity.<n>This research offers lightweight, high-performance deep-learning models for medical imaging applications.
  arXiv  Detail & Related papers  (2025-05-08T13:02:44Z)
• Efficient Deformable Tissue Reconstruction via Orthogonal Neural Plane [58.871015937204255]
  We introduce Fast Orthogonal Plane (plane) for the reconstruction of deformable tissues. We conceptualize surgical procedures as 4D volumes, and break them down into static and dynamic fields comprised of neural planes. This factorization iscretizes four-dimensional space, leading to a decreased memory usage and faster optimization.
  arXiv  Detail & Related papers  (2023-12-23T13:27:50Z)
• Neural LerPlane Representations for Fast 4D Reconstruction of Deformable Tissues [52.886545681833596]
  LerPlane is a novel method for fast and accurate reconstruction of surgical scenes under a single-viewpoint setting. LerPlane treats surgical procedures as 4D volumes and factorizes them into explicit 2D planes of static and dynamic fields. LerPlane shares static fields, significantly reducing the workload of dynamic tissue modeling.
  arXiv  Detail & Related papers  (2023-05-31T14:38:35Z)
• Safe Deep RL for Intraoperative Planning of Pedicle Screw Placement [61.28459114068828]
  We propose an intraoperative planning approach for robotic spine surgery that leverages real-time observation for drill path planning based on Safe Deep Reinforcement Learning (DRL) Our approach was capable of achieving 90% bone penetration with respect to the gold standard (GS) drill planning.
  arXiv  Detail & Related papers  (2023-05-09T11:42:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.