🤖 AI Summary
In laparoscopic surgery, instrument-generated smoke degrades image quality, severely impairing intraoperative visual perception and computer-assisted analysis. To address this, we propose ULW—a novel end-to-end smoke removal framework built upon a U-Net architecture. ULW introduces, for the first time, a learnable and differentiable Wiener filtering module to explicitly model the smoke-induced degradation process. Furthermore, we design a composite loss function integrating multi-scale structural similarity (SSIM), VGG-based perceptual loss, and mean squared error (MSE) to jointly optimize structural fidelity and visual realism. Evaluated on a public paired dataset, ULW achieves state-of-the-art performance—outperforming existing methods by +2.1 dB in PSNR and +0.032 in SSIM—while maintaining real-time inference capability. This work establishes a new paradigm for clinical laparoscopic image enhancement.
📝 Abstract
Laparoscopic surgeries often suffer from reduced visual clarity due to the presence of surgical smoke originated by surgical instruments, which poses significant challenges for both surgeons and vision based computer-assisted technologies. In order to remove the surgical smoke, a novel U-Net deep learning with new loss function and integrated differentiable Wiener filter (ULW) method is presented. Specifically, the new loss function integrates the pixel, structural, and perceptual properties. Thus, the new loss function, which combines the structural similarity index measure loss, the perceptual loss, as well as the mean squared error loss, is able to enhance the quality and realism of the reconstructed images. Furthermore, the learnable Wiener filter is capable of effectively modelling the degradation process caused by the surgical smoke. The effectiveness of the proposed ULW method is evaluated using the publicly available paired laparoscopic smoke and smoke-free image dataset, which provides reliable benchmarking and quantitative comparisons. Experimental results show that the proposed ULW method excels in both visual clarity and metric-based evaluation. As a result, the proposed ULW method offers a promising solution for real-time enhancement of laparoscopic imagery. The code is available at https://github.com/chengyuyang-njit/ImageDesmoke.