Diagnose Like a Pathologist: Transformer-Enabled Hierarchical Attention-Guided Multiple Instance Learning for Whole Slide Image Classification

被引:0
|
作者
Xiong, Conghao [1 ]
Chen, Hao [1 ,2 ]
Sung, Joseph J. Y. [3 ]
King, Irwin [1 ]
机构
[1] Chinese Univ Hong Kong, Dept Comp Sci & Engn, Hong Kong, Peoples R China
[2] Hong Kong Univ Sci & Technol, Dept Chem & Biol Engn, Hong Kong, Peoples R China
[3] Nanyang Technol Univ, Lee Kong Chian Sch Med, Singapore, Singapore
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Multiple Instance Learning (MIL) and transformers are increasingly popular in histopathology Whole Slide Image (WSI) classification. However, unlike human pathologists who selectively observe specific regions of histopathology tissues under different magnifications, most methods do not incorporate multiple resolutions of the WSIs, hierarchically and attentively, thereby leading to a loss of focus on the WSIs and information from other resolutions. To resolve this issue, we propose a Hierarchical Attention-Guided Multiple Instance Learning framework to fully exploit the WSIs. This framework can dynamically and attentively discover the discriminative regions across multiple resolutions of the WSIs. Within this framework, an Integrated Attention Transformer is proposed to further enhance the performance of the transformer and obtain a more holistic WSI (bag) representation. This transformer consists of multiple Integrated Attention Modules, which is the combination of a transformer layer and an aggregation module that produces a bag representation based on every instance representation in that bag. The experimental results show that our method achieved state-of-the-art performances on multiple datasets, including Camelyon16, TCGA-RCC, TCGA-NSCLC, and an in-house IMGC dataset. The code is available at https://github.com/BearCleverProud/HAG-MIL.
引用
收藏
页码:1587 / 1595
页数:9
相关论文
共 50 条
  • [31] Multiple instance learning-based two-stage metric learning network for whole slide image classification
    Li, Xiaoyu
    Yang, Bei
    Chen, Tiandong
    Gao, Zheng
    Li, Huijie
    [J]. VISUAL COMPUTER, 2024, 40 (08): : 5717 - 5732
  • [32] Quantifying Melanoma from Whole Slide Image using Multiple Instance Learning
    Jeong, Hyeon Ki
    Park, Christine
    Ravichandran, Surya
    Chen, Emily
    Frisco, Nicholas
    Subrahmanyan, Rishi
    Henao, Ricardo
    Al-Rohil, Rami
    Kheterpal, Meenal
    [J]. JOURNAL OF THE AMERICAN ACADEMY OF DERMATOLOGY, 2023, 89 (03) : AB80 - AB80
  • [33] Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks
    Yao, Jiawen
    Zhu, Xinliang
    Jonnagaddala, Jitendra
    Hawkins, Nicholas
    Huang, Junzhou
    [J]. MEDICAL IMAGE ANALYSIS, 2020, 65
  • [34] Targeting tumor heterogeneity: multiplex-detection-based multiple instance learning for whole slide image classification
    Wang, Zhikang
    Bi, Yue
    Pan, Tong
    Wang, Xiaoyu
    Bain, Chris
    Bassed, Richard
    Imoto, Seiya
    Yao, Jianhua
    Daly, Roger J.
    Song, Jiangning
    [J]. BIOINFORMATICS, 2023, 39 (03)
  • [35] E2-MIL: An explainable and evidential multiple instance learning framework for whole slide image classification
    Shi, Jiangbo
    Li, Chen
    Gong, Tieliang
    Fu, Huazhu
    [J]. MEDICAL IMAGE ANALYSIS, 2024, 97
  • [36] Pseudo-Bag Mixup Augmentation for Multiple Instance Learning-Based Whole Slide Image Classification
    Liu, Pei
    Ji, Luping
    Zhang, Xinyu
    Ye, Feng
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2024, 43 (05) : 1841 - 1852
  • [37] Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Bag-Level Classifier is a Good Instance-Level Teacher
    Wang, Hongyi
    Luo, Luyang
    Wang, Fang
    Tong, Ruofeng
    Chen, Yen-Wei
    Hu, Hongjie
    Lin, Lanfen
    Chen, Hao
    [J]. IEEE Transactions on Medical Imaging, 2024, 43 (11) : 3964 - 3976
  • [38] H2-MIL: Exploring Hierarchical Representation with Heterogeneous Multiple Instance Learning for Whole Slide Image Analysis
    Hou, Wentai
    Yu, Lequan
    Lin, Chengxuan
    Huang, Helong
    Yu, Rongshan
    Qin, Jing
    Wang, Liansheng
    [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, : 933 - 941
  • [39] MuRCL: Multi-Instance Reinforcement Contrastive Learning for Whole Slide Image Classification
    Zhu, Zhonghang
    Yu, Lequan
    Wu, Wei
    Yu, Rongshan
    Zhang, Defu
    Wang, Liansheng
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2023, 42 (05) : 1337 - 1348
  • [40] Multi-scale representation attention based deep multiple instance learning for gigapixel whole slide image analysis
    Xiang, Hangchen
    Shen, Junyi
    Yan, Qingguo
    Xu, Meilian
    Shi, Xiaoshuang
    Zhu, Xiaofeng
    [J]. MEDICAL IMAGE ANALYSIS, 2023, 89