Multiple Instance Learning for Heterogeneous Images: Training a CNN for Histopathology

被引:34
|
作者
Couture, Heather D. [1 ]
Marron, J. S. [2 ,3 ]
Perou, Charles M. [2 ,4 ]
Troester, Melissa A. [2 ,5 ]
Niethammer, Marc [1 ,6 ]
机构
[1] Univ N Carolina, Dept Comp Sci, Chapel Hill, NC 27515 USA
[2] Univ N Carolina, Lineberger Comprehens Canc Ctr, Chapel Hill, NC 27515 USA
[3] Univ N Carolina, Dept Stat & Operat Res, Chapel Hill, NC 27515 USA
[4] Univ N Carolina, Dept Genet, Chapel Hill, NC 27515 USA
[5] Univ N Carolina, Dept Epidemiol, Chapel Hill, NC 27515 USA
[6] Univ N Carolina, Biomed Res Imaging Ctr, Chapel Hill, NC 27515 USA
关键词
D O I
10.1007/978-3-030-00934-2_29
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Multiple instance (MI) learning with a convolutional neural network enables end-to-end training in the presence of weak image-level labels. We propose a new method for aggregating predictions from smaller regions of the image into an image-level classification by using the quantile function. The quantile function provides a more complete description of the heterogeneity within each image, improving image-level classification. We also adapt image augmentation to the MI framework by randomly selecting cropped regions on which to apply MI aggregation during each epoch of training. This provides a mechanism to study the importance of MI learning. We validate our method on five different classification tasks for breast tumor histology and provide a visualization method for interpreting local image classifications that could lead to future insights into tumor heterogeneity.
引用
收藏
页码:254 / 262
页数:9
相关论文
共 50 条
  • [41] Multiple-instance ranking: Learning to rank images for image retrieval
    Hu, Yang
    Li, Mingjing
    Yu, Nenghai
    [J]. 2008 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-12, 2008, : 85 - +
  • [42] Tooth-Marked Tongue Recognition Using Multiple Instance Learning and CNN Features
    Li, Xiaoqiang
    Zhang, Yin
    Cui, Qing
    Yi, Xiaoming
    Zhang, Yi
    [J]. IEEE TRANSACTIONS ON CYBERNETICS, 2019, 49 (02) : 380 - 387
  • [43] Introducing instance label correlation in multiple instance learning. Application to cancer detection on histopathological images
    Morales-Alvarez, Pablo
    Schmidt, Arne
    Hernandez-Lobato, Jose Miguel
    Molina, Rafael
    [J]. PATTERN RECOGNITION, 2024, 146
  • [44] Multiple Instance Learning for Training Neural Networks under Label Noise
    Duffner, Stefan
    Garcia, Christophe
    [J]. 2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [45] MILIS: Multiple Instance Learning with Instance Selection
    Fu, Zhouyu
    Robles-Kelly, Antonio
    Zhou, Jun
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2011, 33 (05) : 958 - 977
  • [47] MULTIPLE INSTANCE LEARNING OF DEEP CONVOLUTIONAL NEURAL NETWORKS FOR BREAST HISTOPATHOLOGY WHOLE SLIDE CLASSIFICATION
    Das, Kausik
    Conjeti, Sailesh
    Roy, Abhijit Guha
    Chatterjee, Jyotirmoy
    Sheet, Debdoot
    [J]. 2018 IEEE 15TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2018), 2018, : 578 - 581
  • [48] An Instance Selection Approach to Multiple Instance Learning
    Fu, Zhouyu
    Robles-Kelly, Antonio
    [J]. CVPR: 2009 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-4, 2009, : 911 - +
  • [49] Deep multiple instance learning on heterogeneous graph for drug–disease association prediction
    Gu, Yaowen
    Zheng, Si
    Zhang, Bowen
    Kang, Hongyu
    Jiang, Rui
    Li, Jiao
    [J]. Computers in Biology and Medicine, 2025, 184
  • [50] Detection of Breast Cancer From Whole Slide Histopathological Images Using Deep Multiple Instance CNN
    Das, Kausik
    Conjeti, Sailesh
    Chatterjee, Jyotirmoy
    Sheet, Debdoot
    [J]. IEEE ACCESS, 2020, 8 : 213502 - 213511