Desmoke-LAP: Desmoking in Laparoscopic Surgery Dataset

<p dir="ltr"><b>This is the publicly available dataset from robot-assisted laparoscopic hysterectomy surgery providing a benchmark for designing and validating smoke removal algorithms. </b> </p><h3><b>Overview</b></h3><p dir="ltr">The dataset contains frames and video clips from 10 robot-assisted laparoscopic hysterectomy procedure videos. The original videos were decomposed into frames at 1 fps. From each video, 300 hazy images and 300 clear images were manually selected by observing the electrocauterisation. A short video clip of 50 frames from each procedure was also selected that was utilised for testing. Further details about the dataset and experimentation are reported in [<a href="https://link.springer.com/article/10.1007/s11548-022-02595-2" rel="noreferrer" target="_blank">Yirou et al. IJCARS2022</a>]</p><p dir="ltr">The laparoscopic surgery dataset is associated with our International Journal of Computer Assisted Radiology and Surgery (IJCARS) publication titled “DeSmoke-LAP: Improved Unpaired Image-to-Image Translation for Desmoking in Laparoscopic Surgery”. The training model of the proposed method is available as an open source on Github, please check <a href="https://github.com/yiroup20/DeSmoke-LAP" target="_blank">here</a>. We propose DeSmoke-LAP, a new method for removing smoke from real robotic laparoscopic hysterectomy videos. The proposed method is based on the unpaired image-to-image cycle-consistent generative adversarial network in which two novel loss functions, namely, inter-channel discrepancies and dark channel prior.</p><p dir="ltr">The dataset contains frames and video clips from 10 robot-assisted laparoscopic hysterectomy procedure videos. The original videos were decomposed into frames at 1 fps. From each video, 300 hazy images and 300 clear images were manually selected by observing the electrocauterisation. A short video clip of 50 frames from each procedure was also selected that was utilised for testing. 5-fold cross-validation was performed for all methods under comparison. Quantitative evaluation was done using referenceless metrics and qualitative evaluation was performed through a survey filled out by end-users (surgeons).</p><h3><b>Citing the Dataset</b></h3><p dir="ltr">Cite [<a href="https://link.springer.com/article/10.1007/s11548-022-02595-2" rel="noreferrer" target="_blank">Yirou et al. IJCARS2022</a>] whenever research making use of this dataset is reported in any academic publication or research report.</p>