Skip to content

NanoNet: Real-Time Polyp Segmentation in Capsule Endoscopy & Colonoscopy [Contains an open-access capsule endoscopy dataset (2021 IEEE CBMS)]

Notifications You must be signed in to change notification settings

DebeshJha/Kvasircapsule-SEG

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

35 Commits
 
 
 
 
 
 

Repository files navigation

Kvasircapsule-SEG

KvasirCapsule-SEG is an open-access dataset curated specifically for capsule endoscopy polyp segmentation. Derived from the Kvasir-Capsule dataset, it features 55 medically verified video capsule polyp frames. Each frame has been meticulously annotated, generating corresponding ground truth masks, making it an ideal resource for various applications.

🔍 Use-Cases:

  • Polyp segmentation
  • Semantic Segmentation
  • Medical image segmentation
  • Semantic Meta-Learning
  • Domain Generalization
  • Out-of-Distribution Detection Task

Pillcam

A capsule endoscopy procedure enables direct visualization of the small bowel.

It is used for capturing video capsule frames. The examples of capsule endoscopy polyp frames are below:

KvasirCapsule-SEG dataset

Baseline Results on KvasirCapsule-SEG

Access the Dataset

📂 Download Options:

Research Publication

Delve deeper into our work through the following publications:

Citation

Please cite our paper if you find the work useful:

@proceedings{jha2021nanonet,
  title={NanoNet: Real-Time Polyp Segmentation in Endoscopy},
  author={Jha, Debesh and Tomar, Nikhil Kumar and Ali, Sharib and Riegler, Michael A and Johansen, H{\aa}vard D and Johansen, Dag and Halvorsen, P{\aa}l},
  booktitle={Proceedings of the IEEE Computer Based Multimedia System},
  year={2021},
  publisher={IEEE}
}

License and Usage

It is an open-access dataset available for research and academic purposes. For industrial applications, obtaining prior consent is mandatory.

Contact

Please reach out to debeshjha1@gmail.com for any further questions.