To main content

Annotation Web - An open-source web-based annotation tool for ultrasound images

Abstract

The use of deep learning and other machine learning techniques requires large amounts of annotated image data. There exist several tools to annotate images, however to our knowledge there are no tools made specifically for medical ultrasound (US) images. As US is a temporal imaging modality it is essential for such a tool to handle image sequences/videos. To make annotation of US images as easy and efficient as possible, we made a web-based tool called Annotation Web (AW) enabling image classification, segmentation, bounding box and landmark annotation of ultrasound videos. We have now open-sourced this tool, making it available to everyone for free, and we invite the community to use it 1 1 https://github.com/smistad/annotationweb/.
Read the publication

Category

Academic article

Language

English

Author(s)

Affiliation

  • SINTEF Digital / Health Research
  • Norwegian University of Science and Technology

Year

2021

Published in

Proceedings - IEEE Ultrasonics Symposium

ISSN

1948-5719

View this publication at Norwegian Research Information Repository