Mask Rearranging Data Augmentation for 3D Mitochondria Segmentation

被引:3
作者
Chen, Qi [1 ]
Li, Mingxing [1 ]
Li, Jiacheng [1 ]
Hu, Bo [1 ]
Xiong, Zhiwei [1 ,2 ]
机构
[1] Univ Sci & Technol China, Hefei, Peoples R China
[2] Hefei Comprehens Natl Sci Ctr, Inst Artificial Intelligence, Hefei, Peoples R China
来源
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT IV | 2022年 / 13434卷
基金
中国国家自然科学基金; 国家重点研发计划;
关键词
Mitochondria segmentation; Data augmentation; 3D convolution; Generative adversarial networks; Electron microscopy;
D O I
10.1007/978-3-031-16440-8_4
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
3D mitochondria segmentation in electron microscopy (EM) images has achieved significant progress. However, existing learning-based methods with high performance typically rely on extensive training data with high-quality manual annotations, which is time-consuming and labor-intensive. To address this challenge, we propose a novel data augmentation method tailored for 3D mitochondria segmentation. First, we train a Mask2EM network for learning the mapping from the ground-truth instance masks to real 3D EM images in an adversarial manner. Based on the Mask2EM network, we can obtain synthetic 3D EM images from arbitrary instance masks to form a sufficient amount of paired training data for segmentation. Second, we design a 3D mask layout generator to generate diverse instance layouts by rearranging volumetric instance masks according to mitochondrial distance distribution. Experiments demonstrate that, as a plug-and-play module, the proposed method boosts existing 3D mitochondria segmentation networks to achieve state-of-the-art performance. Especially, the proposed method brings significant improvements when training data is extremely limited. Code will be available at: https://github.com/qic999/MRDA_MitoSeg.
引用
收藏
页码:36 / 46
页数:11
相关论文
共 50 条
  • [41] Data Augmentation For CNN-Based 3D Action Recognition on Small-Scale Datasets
    Huynh-The, Thien
    Kim, Dong-Seong
    2019 IEEE 17TH INTERNATIONAL CONFERENCE ON INDUSTRIAL INFORMATICS (INDIN), 2019, : 239 - 244
  • [42] Effective data augmentation for brain tumor segmentation
    Akram, Muhammad Tahir
    Asghar, Sohail
    Shahid, Ahmad Raza
    INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY, 2023, 33 (04) : 1247 - 1260
  • [43] Adversarial Data Augmentation on Breast MRI Segmentation
    Teixeira, Joao E.
    Dias, Mariana
    Batista, Eva
    Costa, Joana
    Teixeira, Luis E.
    Oliveira, Helder P.
    APPLIED SCIENCES-BASEL, 2021, 11 (10):
  • [44] Data Augmentation for Improved Brain Tumor Segmentation
    Biswas, Ankur
    Bhattacharya, Paritosh
    Maity, Santi P.
    Banik, Rita
    IETE JOURNAL OF RESEARCH, 2023, 69 (05) : 2772 - 2782
  • [45] Semantic Segmentation with the Mixup Data Augmentation Method
    Arpaci, Saadet Aytac
    Varli, Songul
    2022 30TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, SIU, 2022,
  • [46] Semantic Segmentation and 3D Reconstruction of Concrete Cracks
    Shokri, Parnia
    Shahbazi, Mozhdeh
    Nielsen, John
    REMOTE SENSING, 2022, 14 (22)
  • [47] InstaBoost plus plus : Visual Coherence Principles for Unified 2D/3D Instance Level Data Augmentation
    Sun, Jianhua
    Fang, Hao-Shu
    Li, Yuxuan
    Wang, Runzhong
    Gou, Minghao
    Lu, Cewu
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2023, 131 (10) : 2665 - 2681
  • [48] Topology-Preserving Augmentation for CNN-Based Segmentation of Congenital Heart Defects from 3D Paediatric CMR
    Byrne, Nick
    Clough, James R.
    Valverde, Isra
    Montana, Giovanni
    King, Andrew P.
    SMART ULTRASOUND IMAGING AND PERINATAL, PRETERM AND PAEDIATRIC IMAGE ANALYSIS, SUSI 2019, PIPPI 2019, 2019, 11798 : 181 - 188
  • [49] Face mask recognition using a custom CNN and data augmentation
    Fazeli Ardekani, Pooya
    Tale, Seyede Zahra
    Parseh, Mohammad Javad
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (01) : 255 - 263
  • [50] Face mask recognition using a custom CNN and data augmentation
    Pooya Fazeli Ardekani
    Seyede Zahra Tale
    Mohammad Javad Parseh
    Signal, Image and Video Processing, 2024, 18 : 255 - 263