Pancreatic Image Augmentation Based on Local Region Texture Synthesis for Tumor Segmentation

被引:2
作者
Wei, Zihan [1 ]
Chen, Yizhou [1 ]
Guan, Qiu [1 ]
Hu, Haigen [1 ]
Zhou, Qianwei [1 ]
Li, Zhicheng [2 ]
Xu, Xinli [1 ]
Frangi, Alejandro [3 ]
Chen, Feng [4 ]
机构
[1] Zhejiang Univ Technol, Coll Comp Sci & Technol, Hangzhou, Peoples R China
[2] Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen, Peoples R China
[3] Univ Leeds, Sch Comp, Leeds, England
[4] Zhejiang Univ, Affiliated Hosp 1, Sch Med, Hangzhou, Peoples R China
来源
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2022, PT II | 2022年 / 13530卷
基金
中国国家自然科学基金;
关键词
Pancreatic tumor; Image segmentation; Image texture generation; Data augmentation; Adversarial learning;
D O I
10.1007/978-3-031-15931-2_35
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
High-accuracy segmentation of lesions in pancreatic images is essential for computer-aided precision diagnosis and treatment. The segmentation accuracy of deep learning-based segmentation models depends on the number of annotated pancreatic tumor images. Due to the high cost of labeling, the size of the training set for segmentation models is usually small. This paper proposes an image augmentation model based on local region texture generation. For pancreas images (background) and tumor images (foreground) with ablated regions, the model can generate image textures for the remaining blank areas after combining the two images to obtain new samples. To improve the texture continuity between the tumor region and surrounding tissues in the generated image, this paper constructs a three-level loss function to constrain the training of the augmented model. Simulation experiments on the pancreatic tumor image set provided by the partner hospital show that the Dice coefficient of the segmentation model trained on the dataset augmented by the proposed model improves by 2.4% compared with the current optimal method when the number of real images is sparse, which proves its effectiveness and feasibility.
引用
收藏
页码:419 / 431
页数:13
相关论文
共 16 条
  • [1] COViT-GAN: Vision Transformer for COVID-19 Detection in CT Scan Images with Self-Attention GAN for Data Augmentation
    Ambita, Ara Abigail E.
    Boquio, Eujene Nikka, V
    Naval, Prospero C., Jr.
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2021, PT II, 2021, 12892 : 587 - 598
  • [2] GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review
    Bissoto, Alceu
    Valle, Eduardo
    Avila, Sandra
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021, 2021, : 1847 - 1856
  • [3] Cooperative Training and Latent Space Data Augmentation for Robust Medical Image Segmentation
    Chen, Chen
    Hammernik, Kerstin
    Ouyang, Cheng
    Qin, Chen
    Bai, Wenjia
    Rueckert, Daniel
    [J]. MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT III, 2021, 12903 : 149 - 159
  • [4] Generative Adversarial Networks in Medical Image augmentation: A review
    Chen, Yizhou
    Yang, Xu-Hua
    Wei, Zihan
    Heidari, Ali Asghar
    Zheng, Nenggan
    Li, Zhicheng
    Chen, Huiling
    Hu, Haigen
    Zhou, Qianwei
    Guan, Qiu
    [J]. COMPUTERS IN BIOLOGY AND MEDICINE, 2022, 144
  • [5] Cancer statistics for the year 2020: An overview
    Ferlay, Jacques
    Colombet, Murielle
    Soerjomataram, Isabelle
    Parkin, Donald M.
    Pineros, Marion
    Znaor, Ariana
    Bray, Freddie
    [J]. INTERNATIONAL JOURNAL OF CANCER, 2021, 149 (04) : 778 - 789
  • [6] Generating Synthetic Labeled Data From Existing Anatomical Models: An Example With Echocardiography Segmentation
    Gilbert, Andrew
    Marciniak, Maciej
    Rodero, Cristobal
    Lamata, Pablo
    Samset, Eigil
    Mcleod, Kristin
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2021, 40 (10) : 2783 - 2794
  • [7] Goodfellow IJ, 2014, ADV NEUR IN, V27, P2672
  • [8] Medical image augmentation for lesion detection using a texture-constrained multichannel progressive GAN
    Guan, Qiu
    Chen, Yizhou
    Wei, Zihan
    Heidari, Ali Asghar
    Hu, Haigen
    Yang, Xu-Hua
    Zheng, Jianwei
    Zhou, Qianwei
    Chen, Huiling
    Chen, Feng
    [J]. COMPUTERS IN BIOLOGY AND MEDICINE, 2022, 145
  • [9] Breast Mass Detection in Mammograms via Blending Adversarial Learning
    Lin, Chunze
    Tang, Ruixiang
    Lin, Darryl D.
    Liu, Langechuan
    Lu, Jiwen
    Chen, Yunqiang
    Gao, Dashan
    Zhou, Jie
    [J]. SIMULATION AND SYNTHESIS IN MEDICAL IMAGING, SASHIMI 2019, 2019, 11827 : 52 - 61
  • [10] Local Normalization Based BN Layer Pruning
    Liu, Yuan
    Jia, Xi
    Shen, Linlin
    Ming, Zhong
    Duan, Jinming
    [J]. ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: DEEP LEARNING, PT II, 2019, 11728 : 334 - 346