LSD3K: A Benchmark for Smoke Removal from Laparoscopic Surgery Images

TL;DR

This paper introduces LSD3K, a high-quality benchmark dataset of 3,000 synthetic laparoscopic images with smoke, to facilitate the development and evaluation of smoke removal algorithms in surgical imaging.

Contribution

The paper presents a new publicly available dataset, LSD3K, with a detailed generation pipeline and comprehensive evaluation of existing desmoking algorithms.

Findings

LSD3K dataset enables standardized evaluation of desmoking methods.

Existing algorithms show varying performance on the new benchmark.

The dataset supports future research in surgical image enhancement.

Abstract

Smoke generated by surgical instruments during laparoscopic surgery can obscure the visual field, impairing surgeons' ability to perform operations accurately and safely. Thus, smoke removal task for laparoscopic images is highly desirable. Despite laparoscopic image desmoking has attracted the attention of researchers in recent years and several algorithms have emerged, the lack of publicly available high-quality benchmark datasets is the main bottleneck to hamper the development progress of this task. To advance this field, we construct a new high-quality dataset for Laparoscopic Surgery image Desmoking, named LSD3K, consisting of 3,000 paired synthetic non-homogeneous smoke images. In this paper, we provide a dataset generation pipeline, which includes modeling smoke shape using Blender, collecting ground-truth images from the Cholec80 dataset, random sampling of smoke masks and etc. Based on the proposed benchmark, we further conducted a comprehensive evaluation of the existing representative desmoking algorithms. The proposed dataset is publicly available at https://drive.google.com/file/d/1v0U5_3S4nJpaUiP898Q0pc-MfEAtnbOq/view?usp=sharing