English

ScribbleVC: Scribble-supervised Medical Image Segmentation with Vision-Class Embedding

Computer Vision and Pattern Recognition 2023-08-01 v1 Multimedia

Abstract

Medical image segmentation plays a critical role in clinical decision-making, treatment planning, and disease monitoring. However, accurate segmentation of medical images is challenging due to several factors, such as the lack of high-quality annotation, imaging noise, and anatomical differences across patients. In addition, there is still a considerable gap in performance between the existing label-efficient methods and fully-supervised methods. To address the above challenges, we propose ScribbleVC, a novel framework for scribble-supervised medical image segmentation that leverages vision and class embeddings via the multimodal information enhancement mechanism. In addition, ScribbleVC uniformly utilizes the CNN features and Transformer features to achieve better visual feature extraction. The proposed method combines a scribble-based approach with a segmentation network and a class-embedding module to produce accurate segmentation masks. We evaluate ScribbleVC on three benchmark datasets and compare it with state-of-the-art methods. The experimental results demonstrate that our method outperforms existing approaches in terms of accuracy, robustness, and efficiency. The datasets and code are released on GitHub.

Keywords

Cite

@article{arxiv.2307.16226,
  title  = {ScribbleVC: Scribble-supervised Medical Image Segmentation with Vision-Class Embedding},
  author = {Zihan Li and Yuan Zheng and Xiangde Luo and Dandan Shan and Qingqi Hong},
  journal= {arXiv preprint arXiv:2307.16226},
  year   = {2023}
}

Comments

Accepted by ACM MM 2023, project page: https://github.com/HUANGLIZI/ScribbleVC

R2 v1 2026-06-28T11:43:47.748Z