A Prior-mask-guided Few-shot Learning for Skin Lesion Segmentation

被引:0
|
作者
Junsheng Xiao
Huahu Xu
Wei Zhao
Chen Cheng
HongHao Gao
机构
[1] Shanghai University,School of Computer Engineering and Science
[2] Information Office of Shanghai,undefined
[3] Henan Provincial Hospital of Traditional Chinese Medicine,undefined
来源
Computing | 2023年 / 105卷
关键词
Skin cancer; Few-shot segmentation; Co-occurrence region; Reversing the support and query role;
D O I
暂无
中图分类号
学科分类号
摘要
The incidence of skin cancer, which has high mortality, is growing rapidly worldwide. Early detection of skin lesions is crucial for timely diagnosis and treatment to improve the patient survival rate. Computer vision technology based on deep convolutional neural network requires a large amount of labelled data. The cost of data acquisition and annotation is relatively high, especially for skin cancer segmentation tasks. Therefore, we propose a few-shot segmentation network for skin lesion segmentation, which requires only a few pixel-level annotations. First, the co-occurrence region between the support image and query image is obtained, which is used as a prior mask to exclude irrelevant background regions. Second, the results are concatenated and sent to the inference module to predict segmentation of the query image. Third, the proposed network is retrained by reversing the support and query role, which benefits from the symmetrical structure. Extensive experiments performed on ISIC-2017, ISIC-2019, and PH2 demonstrate that our method forms a promising framework for few-shot segmentation of skin lesion.
引用
收藏
页码:717 / 739
页数:22
相关论文
共 50 条
  • [1] A Prior-mask-guided Few-shot Learning for Skin Lesion Segmentation
    Xiao, Junsheng
    Xu, Huahu
    Zhao, Wei
    Cheng, Chen
    Gao, HongHao
    COMPUTING, 2023, 105 (03) : 717 - 739
  • [2] Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond
    Chen, Shuai
    Meng, Fanman
    Zhang, Runtong
    Qiu, Heqian
    Li, Hongliang
    Wu, Qingbo
    Xu, Linfeng
    IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 26 : 7197 - 7209
  • [3] RPMG-FSS: Robust Prior Mask Guided Few-Shot Semantic Segmentation
    Zhang, Lingling
    Zhang, Xinyu
    Wang, Qianying
    Wu, Wenjun
    Chang, Xiaojun
    Liu, Jun
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2023, 33 (11) : 6609 - 6621
  • [4] Mask-Guided Correlation Learning for Few-Shot Segmentation in Remote Sensing Imagery
    Li, Shuo
    Liu, Fang
    Jiao, Licheng
    Liu, Xu
    Chen, Puhua
    Li, Lingling
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62 : 1 - 1
  • [5] Prior Guided Feature Enrichment Network for Few-Shot Segmentation
    Tian, Zhuotao
    Zhao, Hengshuang
    Shu, Michelle
    Yang, Zhicheng
    Li, Ruiyu
    Jia, Jiaya
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (02) : 1050 - 1065
  • [6] Few-shot learning for skin lesion image classification
    Xue-Jun Liu
    Kai-li Li
    Hai-ying Luan
    Wen-hui Wang
    Zhao-yu Chen
    Multimedia Tools and Applications, 2022, 81 : 4979 - 4990
  • [7] Few-shot learning for skin lesion image classification
    Liu, Xue-Jun
    Li, Kai-li
    Luan, Hai-ying
    Wang, Wen-hui
    Chen, Zhao-yu
    MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (04) : 4979 - 4990
  • [8] Mask-Guided Vision Transformer for Few-Shot Learning
    Chen, Yuzhong
    Xiao, Zhenxiang
    Pan, Yi
    Zhao, Lin
    Dai, Haixing
    Wu, Zihao
    Li, Changhe
    Zhang, Tuo
    Li, Changying
    Zhu, Dajiang
    Liu, Tianming
    Jiang, Xi
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024,
  • [9] Hierarchical bidirectional aggregation with prior guided transformer for few-shot segmentation
    Qiuyu Kong
    Jie Jiang
    Junyan Yang
    Qi Wang
    International Journal of Multimedia Information Retrieval, 2023, 12
  • [10] Hierarchical bidirectional aggregation with prior guided transformer for few-shot segmentation
    Kong, Qiuyu
    Jiang, Jie
    Yang, Junyan
    Wang, Qi
    INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL, 2023, 12 (02)