ProMIL: A weakly supervised multiple instance learning for whole slide image classification based on class proxy

被引:0
|
作者
Li, Xiaoyu [1 ]
Yang, Bei [1 ]
Chen, Tiandong [2 ,3 ]
Gao, Zheng [1 ]
Huang, Mengjie [1 ]
机构
[1] Zhengzhou Univ, Sch Comp & Artificial Intelligence, Zhengzhou 450001, Henan, Peoples R China
[2] Zhengzhou Univ, Affiliated Canc Hosp, Dept Pathol, Zhengzhou 450008, Henan, Peoples R China
[3] Henan Canc Hosp, Zhengzhou 450008, Henan, Peoples R China
关键词
Class proxy; Whole slide image; Metric learning; Multiple instance learning; Attention mechanism; TRANSFORMER;
D O I
10.1016/j.eswa.2023.121800
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The histopathological analysis of a suspected region is critical for cancer diagnosis, treatment, and manage-ment. Histopathological diagnosis consists in analyzing the characteristics of the lesions using tissue sections stained with hematoxylin and eosin. Classification of digital tumor pathology images, called whole slide images (WSIs), is a great challenge since WSIs usually have huge resolutions while lacking localized annotations. Multiple instance learning (MIL) is a commonly used method applied to pathological image analysis. However, most MIL methods often focus only on the global representation of WSIs, ignoring whether the category labels play other roles in the model training besides being a supervision signal. In addition, feature confusion is also a problem that should be avoided for the analysis of WSIs with weakly supervised methods. To address these problems, we propose a novel algorithm of classifying WSI for cancer diagnosis. The proposed model, ProMIL, uses only slide-level labels rather than localized annotations for analysis. There are three innovations in this work. Firstly, we present the concept of class proxy which is the representation of the intrinsic feature of each category, and plays a key role in guiding the training of the model. Secondly, we design a novel WSI representation learning module that utilizes a multi-scale feature extraction strategy to represent each patch in a WSI and then aggregates these representations using an attention mechanism to encode the WSI. Thirdly, we design a metric-learning-based weakly supervised multiclass-classifier by measuring the similarity between each WSI embedding and class proxies. The proposed ProMIL can effectively alleviate the side effect of feature confusion, and carry intuitive interpretability and scalability. To evaluate the performance of ProMIL, we conduct a series of experiments on several datasets of WSIs with different types of cancer from open data sources. It can be observed from the experimental results that ProMIL outperforms most of the compared methods and achieves better performance on a various type of cancer image data for classification, thus suggesting the proposed method is suitable for classifying different categories of cancer rather than a specific kind of cancer. Therefore, it is expected to act as a general framework to be extended to more cancer diagnoses.
引用
收藏
页数:12
相关论文
共 50 条
  • [1] Iterative multiple instance learning for weakly annotated whole slide image classification
    Zhou, Yuanpin
    Che, Shuanlong
    Lu, Fang
    Liu, Si
    Yan, Ziye
    Wei, Jun
    Li, Yinghua
    Ding, Xiangdong
    Lu, Yao
    [J]. PHYSICS IN MEDICINE AND BIOLOGY, 2023, 68 (15):
  • [2] Self-supervised comparative learning based improved multiple instance learning for whole slide image classification
    Yao, Luhan
    Wang, Hongyu
    Hao, Yingguang
    [J]. PROCEEDINGS OF 2023 4TH INTERNATIONAL SYMPOSIUM ON ARTIFICIAL INTELLIGENCE FOR MEDICINE SCIENCE, ISAIMS 2023, 2023, : 1353 - 1357
  • [3] MULTIPLE INSTANCE LEARNING WITH CRITICAL INSTANCE FOR WHOLE SLIDE IMAGE CLASSIFICATION
    Zhou, Yuanpin
    Lu, Yao
    [J]. 2023 IEEE 20TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, ISBI, 2023,
  • [4] Weakly supervised pathological whole slide image classification based on contrastive learning
    Xie, Yining
    Long, Jun
    Hou, Jianxin
    Chen, Deyun
    Guan, Guohui
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (21) : 60809 - 60831
  • [5] Rethinking Overfitting of Multiple Instance Learning for Whole Slide Image Classification
    Song, Hongjian
    Tang, Jie
    Xiao, Hongzhao
    Hu, Juncheng
    [J]. 2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME, 2023, : 546 - 551
  • [6] Multiple Instance Learning with random sampling for Whole Slide Image Classification
    Keshvarikhojasteh, H.
    Pluim, J. P. W.
    Veta, M.
    [J]. DIGITAL AND COMPUTATIONAL PATHOLOGY, MEDICAL IMAGING 2024, 2024, 12933
  • [7] CaMIL: Causal Multiple Instance Learning for Whole Slide Image Classification
    Chen, Kaitao
    Sun, Shiliang
    Zhao, Jing
    [J]. THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 2, 2024, : 1120 - 1128
  • [8] DEEP HIERARCHICAL MULTIPLE INSTANCE LEARNING FOR WHOLE SLIDE IMAGE CLASSIFICATION
    Zhou, Yuanpin
    Lu, Yao
    [J]. 2022 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (IEEE ISBI 2022), 2022,
  • [9] TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification
    Shao, Zhuchen
    Bian, Hao
    Chen, Yang
    Wang, Yifeng
    Zhang, Jian
    Ji, Xiangyang
    Zhang, Yongbing
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021,
  • [10] Masked hypergraph learning for weakly supervised histopathology whole slide image classification
    Shi, Jun
    Shu, Tong
    Wu, Kun
    Jiang, Zhiguo
    Zheng, Liping
    Wang, Wei
    Wu, Haibo
    Zheng, Yushan
    [J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2024, 253