• Corpus ID: 229363724

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

  title={CholecSeg8k: A Semantic Segmentation Dataset for Laparoscopic Cholecystectomy Based on Cholec80},
  author={W.-Y. Hong and Chang-Lung Kao and Y.-H. Kuo and J.-R. Wang and Wanxing Chang and C.-S. Shih},
Computer-assisted surgery has been developed to enhance surgery correctness and safety. However, the 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) are limited. This article elaborates the efforts of preparing the dataset for semantic segmentation, which is the foundation of many computer-assisted surgery mechanisms. Based on the… 

Figures and Tables from this paper

Analysis of Current Deep Learning Networks for Semantic Segmentation of Anatomical Structures in Laparoscopic Surgery

  • B. SilvaBruno Oliveira J. Vilaça
  • Computer Science, Medicine
    2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
  • 2022
The results show that there is still room for improvement in the segmentation of anatomical structures from laparoscopic videos, with the U-Net++ being the network with the best overall score with a mean Dice value of 0.62.

Gauze Detection and Segmentation in Minimally Invasive Surgery Video Using Convolutional Neural Networks

A segmentation dataset with 4003 hand-labelled frames from laparoscopic video to demonstrate that precise and real-time gauze segmentation can be achieved, training convolutional neural networks on the proposed dataset.

ALGES: Active Learning with Gradient Embeddings for Semantic Segmentation of Laparoscopic Surgical Images

A novel AL algorithm for segmentation, ALGES, is proposed that utilizes gradient embeddings to effectively select laparoscopic images to be labeled by some external oracle while reducing annotation effort.

Data-centric multi-task surgical phase estimation with sparse scene segmentation

A simple multi-task encoder is proposed that effectively fuses both streams, when available, based on their importance and jointly optimise them for performing accurate phase prediction and it is shown that with a small fraction of scene segmentation annotations, a relatively simple model can obtain comparable results than previous state-of-the-art and more complex architectures when evaluated in similar settings.

Temporally Constrained Neural Networks (TCNN): A framework for semi-supervised video semantic segmentation

This work shows that autoencoder networks can be used to efficiently provide both spatial and temporal supervisory signals to train deep learning models and demonstrates that lower-dimensional representations of predicted masks can be leveraged to provide a consistent improvement on both sparsely labeled datasets with no additional computational cost at inference time.



EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos

This paper proposes a novel method for phase recognition that uses a convolutional neural network (CNN) to automatically learn features from cholecystectomy videos and that relies uniquely on visual information.

Content-based processing and analysis of endoscopic images and videos: A survey

This survey aims to introduce this research field to a broader audience in the Multimedia community to stimulate further research, to describe domain-specific characteristics of endoscopic videos that need to be addressed in a pre-processing step, and to systematically bring together the very diverse research results for the first time.

Efficient Linear Algorithm for Magnetic Localization and Orientation in Capsule Endoscopy

  • Chao HuM. MengM. Mandal
  • Computer Science
    2005 IEEE Engineering in Medicine and Biology 27th Annual Conference
  • 2005
A linear algorithm is proposed to provide faster, more reliable computation, compared to the nonlinear algorithms, and shows that satisfactory localization and orientation accuracy can be achieved using a sensor array with enough number of 3-axis sensors.