Contrastive Learning for Mitochondria Segmentation

被引:9
|
作者
Li, Zhili [1 ,2 ]
Chen, Xuejin [1 ,2 ]
Zhao, Jie [1 ,2 ]
Xiong, Zhiwei [1 ,2 ]
机构
[1] Univ Sci & Technol China, Natl Engn Lab Brain Inspired Intelligence Technol, Hefei, Peoples R China
[2] Hefei Comprehens Natl Sci Ctr, Inst Artificial Intelligence, Hefei, Peoples R China
基金
国家重点研发计划; 中国国家自然科学基金;
关键词
Electron Microscopy; Mitochondria; Image Segmentation; Contrastive Learning;
D O I
10.1109/EMBC46164.2021.9630350
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Mitochondria segmentation in electron microscopy images is essential in neuroscience. However, due to the image degradation during the imaging process, the large variety of mitochondrial structures, as well as the presence of noise, artifacts and other sub-cellular structures, mitochondria segmentation is very challenging. In this paper, we propose a novel and effective contrastive learning framework to learn a better feature representation from hard examples to improve segmentation. Specifically, we adopt a point sampling strategy to pick out representative pixels from hard examples in the training phase. Based on these sampled pixels, we introduce a pixel-wise label-based contrastive loss which consists of a similarity loss term and a consistency loss term. The similarity term can increase the similarity of pixels from the same class and the separability of pixels from different classes in feature space, while the consistency term is able to enhance the sensitivity of the 3D model to changes in image content from frame to frame. We demonstrate the effectiveness of our method on MitoEM dataset as well as FIB-SEM dataset and show better or on par with state-of-the-art results.
引用
收藏
页码:3496 / 3500
页数:5
相关论文
共 50 条
  • [41] Multi-layered maps of neuropil with segmentation-guided contrastive learning
    Sven Dorkenwald
    Peter H. Li
    Michał Januszewski
    Daniel R. Berger
    Jeremy Maitin-Shepard
    Agnes L. Bodor
    Forrest Collman
    Casey M. Schneider-Mizell
    Nuno Maçarico da Costa
    Jeff W. Lichtman
    Viren Jain
    [J]. Nature Methods, 2023, 20 : 2011 - 2020
  • [42] PRCL: Probabilistic Representation Contrastive Learning for Semi-Supervised Semantic Segmentation
    Xie, Haoyu
    Wang, Changqi
    Zhao, Jian
    Liu, Yang
    Dan, Jun
    Fu, Chong
    Sun, Baigui
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2024, 132 (10) : 4343 - 4361
  • [43] Label-Efficient Multi-task Segmentation Using Contrastive Learning
    Iwasawa, Junichiro
    Hirano, Yuichiro
    Sugawara, Yohei
    [J]. BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES (BRAINLES 2020), PT I, 2021, 12658 : 101 - 110
  • [44] Context-FPN and Memory Contrastive Learning for Partially Supervised Instance Segmentation
    Yuan, Zheng
    Cai, Weiling
    Zhao, Chen
    [J]. PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT XII, 2024, 14436 : 172 - 184
  • [45] A Domain Adaptive Semantic Segmentation Method Using Contrastive Learning and Data Augmentation
    Yixiao Xiang
    Lihua Tian
    Chen Li
    [J]. Neural Processing Letters, 56
  • [46] A Semantic Segmentation Algorithm Based on Contrastive Learning Using Aligned Feature Samples
    Jia, Xibei
    Lian, Zhichao
    [J]. 2022 IEEE INTL CONF ON DEPENDABLE, AUTONOMIC AND SECURE COMPUTING, INTL CONF ON PERVASIVE INTELLIGENCE AND COMPUTING, INTL CONF ON CLOUD AND BIG DATA COMPUTING, INTL CONF ON CYBER SCIENCE AND TECHNOLOGY CONGRESS (DASC/PICOM/CBDCOM/CYBERSCITECH), 2022, : 688 - 693
  • [47] CLUE: Contrastive language-guided learning for referring video object segmentation
    Gao, Qiqi
    Zhong, Wanjun
    Li, Jie
    Zhao, Tiejun
    [J]. PATTERN RECOGNITION LETTERS, 2024, 178 : 115 - 121
  • [48] Self-supervised Learning with Local Contrastive Loss for Detection and Semantic Segmentation
    Islam, Ashraful
    Lundell, Ben
    Sawhney, Harpreet
    Sinha, Sudipta N.
    Morales, Peter
    Radke, Richard J.
    [J]. 2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 5613 - 5622
  • [49] Unsupervised Representation for Semantic Segmentation by Implicit Cycle-Attention Contrastive Learning
    Pang, Bo
    Li, Yizhuo
    Zhang, Yifan
    Peng, Gao
    Tang, Jiajun
    Zha, Kaiwen
    Li, Jiefeng
    Lu, Cewu
    [J]. THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 2044 - 2052
  • [50] Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation
    Marsden, Robert A.
    Bartler, Alexander
    Doebler, Mario
    Yang, Bin
    [J]. 2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,