CholecSeg8k: A Semantic Segmentation Dataset for Laparoscopic Cholecystectomy Based on Cholec80

TL;DR

CholecSeg8K tackles the scarcity of labeled endoscopic data for semantic segmentation crucial to endoscopic SLAM and computer-assisted surgery. It builds on the Cholec80 dataset to produce 8,080 pixel-annotated frames across 17 clips, covering 13 classes, with three mask formats and a ~3 GB footprint. The dataset is organized for easy access via a two-level directory structure and includes class distribution details and potential imbalances, while noting practical labeling considerations. Released under CC BY-NC-SA 4.0 on Kaggle, CholecSeg8K provides a practical resource to train and benchmark segmentation models for endoscopic procedures and downstream navigation tasks.

Abstract

Computer-assisted surgery has been developed to enhance surgery correctness and safety. However, researchers and engineers suffer from limited annotated data to develop and train better algorithms. Consequently, the development of fundamental algorithms such as Simultaneous Localization and Mapping (SLAM) is limited. This article elaborates on the efforts of preparing the dataset for semantic segmentation, which is the foundation of many computer-assisted surgery mechanisms. Based on the Cholec80 dataset [3], we extracted 8,080 laparoscopic cholecystectomy image frames from 17 video clips in Cholec80 and annotated the images. The dataset is named CholecSeg8K and its total size is 3GB. Each of these images is annotated at pixel-level for thirteen classes, which are commonly founded in laparoscopic cholecystectomy surgery. CholecSeg8k is released under the license CC BY- NC-SA 4.0.

Figures (8)

• Figure 1: Example of Semantic Segmentation Label of Endoscope Image
• Figure 2: Example of Directory Tree
• Figure 3: Proportion of annotated pixels (y-axis) per class (x-axis)
• Figure 4: Example of annotation masks and raw images
• Figure 5: Example of Semantic Segmentation Annotation of Gallbladder Endoscope Image