首页 > 过刊浏览>2025年第14卷第2期 >24-32. DOI:10.12146/j.issn.2095-3135.20241111001
PDF HTML阅读 XML下载 导出引用 引用提醒
多实例学习在医学图像分析中的应用进展
作者:
中图分类号:

R318

基金项目:

北京大学医学部教育教学研究课题项目(2022YB17)；北京市自然科学基金面上项目(4242004)；国家蛋白质科学研究(北京)设施北京大学分中心开放课题项目(KF-202402)；国家自然科学基金项目(32271053)；北京市自然科学基金-海淀原始创新联合基金项目(L222016)


Application Progress of Multi-instance Learning in Medical Image Analysis
Author:
Fund Project:

Peking University Health Science Center Medical Education Research Funding Project (2022YB17), Beijing Natural Science Foundation (4242004), Open Research Fund of the National Center for Protein Sciences at Peking University in Beijing (KF-202402), National Natural Science Foundation of China (32271053), and Beijing Natural Science Foundation - Haidian Original Innovation Joint Fund (L222016)

  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [38]
    • |
  • 相似文献 [20]
    • | | |
  • 文章评论
    摘要:

    多实例学习(multiple-instance learning，MIL)是一种弱监督学习方法，近年来广泛应用于医学图像分析领域。本文综述了 MIL 在全切片图像中的应用进展，详细分析了其在肿瘤检测、亚型分级和生存预测中的作用。MIL 在弱监督学习中具有独特优势，可通过引入新机制进行优化和拓展，以适应更多的应用场景。本文首先综述了部分应用广泛或独具优势的 MIL 模型，并详细介绍了它们的技术特点和具体应用场景；其次，介绍了 MIL 在多模态医学图像分析中的应用进展和技术进步；最后，总结了 MIL 目前的研究进展，并展望了其未来发展。

    Abstract:

    Multiple-instance learning (MIL), as a weakly supervised learning method, has been widely applied in the field of medical image analysis in recent years. The paper reviews the progress of MIL applications in whole slide images, with a detailed analysis of its roles in tumor detection, subtype classification, and survival prediction. MIL holds unique advantages in weakly supervised learning , which can be optimized and extended through the introduction of new mechanisms to adapt to a broader range of application scenarios. The paper first reviews some widely used or uniquely advantageous MIL models, elaborating on their technical features and specific application contexts. Secondly, it introduces the application and technology advancements of MIL in multimodal medical image analysis. Finally, the current research progress of MIL is summarized, and its future development prospects are explored.

    参考文献
    [1]????????????? Thomas G. Dietterich RHL, Tomás Lozano-Pérez. Solving the multiple instance problem with axis-parallel rectangles [J]. Artificial Intelligence, 1997, 89(1–2): 31-71.
    [2]????????????? Ronald APO. A Boosting Approach to Multiple Instance Learning [J]. Lecture Notes in Computer Science, 2004, 3201:63-74.
    [3]????????????? Yao J, Zhu X, Jonnagaddala J, et al. Whole slide images based cancer survival prediction using attention gu ided deep multiple instance learning networks [J]. Medical image analysis, 2020, 65(10):101789.
    [4]????????????? Huang X, Li Z, Zhang M, et al. Fusing hand-crafted and deep-learning features in a convolutional neural network model to identify prostate cancer in pathology images [J]. Front Oncol, 2022, 12(9):994950.
    [5]????????????? Li X, Yang B, Chen T, et al. Multiple instance learning-based two-stage metric learning network for whole slide image classification [J]. The Visual Computer, 2023, 40(8): 5717-5732.
    [6]????????????? Park S, Kim H, Kim M, et al. Normality Guided Multiple Instance Learning for Weakly Supervised Video Anomaly Detection [C] // 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023: 2664-2673.
    [7]????????????? Ilse M, Tomczak JM and Welling M. Attention-based Deep Multiple Instance Learning [C] // 2018 PMLR/Proceedings of the 35th International Conference on Machine Learning, 2018:2127-2136.
    [8]????????????? Zhang S, Ke W and Yang L. Discovery-and-Selection: Towards Optimal Multiple Instance Learning fo r Weakly Supervised Object Detection [J]. arxiv:2110.09060[cs.CV], 2021.
    [9]????????????? Nguyen T and Raich R. Incomplete Label Multiple Instance Multiple Label Learning [J]. IEEE transactions on pattern analysis and machine intelligence, 2022, 44(3): 1320-1337.
    [10]????????????? Zhang X, Liu C, Zhu H, et al. A Universal Multiple Instance Learning Framework for Whole Slide Image Analysis [J]. Computers in Biology and Medicine, 2024, 178(8): 108714.
    [11]????????????? Chen J, Zeng H, Zhang C, et al. Lung cancer diagnosis using deep attention-based multiple instance lea rning and radiomics [J]. Medical physics, 2022, 49(5): 3134-3143.
    [12]????????????? Xiang H, Shen J, Yan Q, et al. Multi-scale representation attention based deep multiple instance lear ning for gigapixel whole slide image analysis [J]. Medical image analysis, 2023, 89(10):102890.
    [13]????????????? Li B, Li Y and Eliceiri KW. Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning [C] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021:14318-14328.
    [14]????????????? Sharma S, Siddiqui MK, Akhtar MS, et al. Domain-aware self-supervised pre-training for label-efficient meme analysis [C] // 2022 Association for Computational Linguistics/Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing, 2022: 792–805.
    [15]????????????? Azizi S, Culp L, Freyberg J, et al. Robust and data-efficient generalization of self-supervised machine le arning for diagnostic imaging [J]. Nature Biomedical Engineering, 2023, 7(6): 756-779.
    [16]????????????? Shi J, Li C, Gong T, et al. E2-MIL: An explainable and evidential multiple instance learning frame work for whole slide image classification [J]. Medical Image Analysis, 2024, 97(10):103294.
    [17]????????????? Tang W, Huang S, Zhang X, et al. Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification [C] // 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023: 4055-4064.
    [18]????????????? Cui Y, Liu Z, Chen Y, et al. Retrieval-augmented multiple instance learning [C] // Proceedings of the 37th International Conference on Neural Information Processing System, 2023: 24859-24878.
    [19]????????????? Qu L, Ma Y, Luo X, et al. Rethinking Multiple Instance Learning for Whole Slide Image Classifica tion: A Good Instance Classifier is All You Need [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(10): 9732-9744.
    [20]????????????? Yang L, Mehta D, Liu S, et al. Tpmil: Trainable prototype enhanced multiple instance learning for who le slide image classification [C] // 2023 PMLR/Proceedings of Medical Imaging with Deep Learning, 2023: 1655-1665.
    [21]????????????? Wang J, Mao Y, Guan N, et al. Advances in Multiple Instance Learning for Whole Slide Image Analysis: Techniques, Challenges, and Future Directions [J]. arxiv:2408.09476[cs.CV,cs.LG], 2024.
    [22]????????????? Guan Y, Zhang J, Tian K, et al. Node-aligned Graph Convolutional Network for Whole-slide Image Representation and Classification [C] // 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022: 18791-18801.
    [23]????????????? Bontempo G, Porrello A, Bolelli F, et al. DAS-MIL: Distilling Across Scales for MIL classification of histological WSIs [C] //26th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2023: 248-258.
    [24]????????????? Mao J, Liu J, Lin H, et al. Multi-modal Multi-kernel Graph Learning for Autism Prediction and Biomarker Discovery [J]. arxiv:2303.03388[cs.LG,cs.AI], 2023.
    [25]????????????? Peng S, Cai Y, Yao Z, et al. Weakly-supervised video anomaly detection via temporal resolution feature learning [J]. Applied Intelligence, 2023, 53(24): 30607-30625.
    [26]????????????? Li Z, Huang X, Zhang Z, et al. Synthesis of magnetic resonance images from computed tomography data using convolutional neural network with contextual loss function [J]. Quant Imaging Med Surg, 2022, 12(6): 3151-3169.
    [27]????????????? Xu Y. Deep Learning in Multimodal Medical Image Analysis [M]. Springer International Publishing; 2019.
    [28]????????????? Yan Y, Wang H, Huang Y, et al. Cross-Modal Vertical Federated Learning for MRI Reconstruction [J]. IEEE J Biomed Health Inform, 2024, 28(11):6383-6394
    [29]????????????? Cai W, Gao H, Chu C, et al. Engineering phototheranostic nanoscale metal–organic frameworks for mu ltimodal imaging-guided cancer therapy [J]. ACS applied materials interfaces, 2017, 9(3): 2040-2051.
    [30]????????????? Han H, Lian C, Zeng Z, et al. Multimodal multi-instance learning for long-term ECG classification [J]. Knowledge-Based Systems, 2023, 270(6):110555.
    [31]????????????? Huang Z, Yu X, Wessler BS, et al. Semi-Supervised Multimodal Multi-Instance Learning for Aortic Stenosis Diagnosis [J]. arXiv preprint arXiv:2403.06024, 2024.
    [32]????????????? Bi Q, Sun X, Yu S, et al. MIL-ViT: A multiple instance vision transformer for fundus image class ification [J]. Journal of Visual Communication and Image Representation, 2023, 97(12):103956.
    [33]????????????? Han X, Wang Y-T, Feng J-L, et al. A survey of transformer-based multimodal pre-trained modals [J]. Neurocomputing, 2023, 515(1): 89-106.
    [34]????????????? Zhu Z, Yu L, Wu W, et al. MuRCL: Multi-instance reinforcement contrastive learning for whole sli de image classification [J]. IEEE Transactions on Medical Imaging, 2022, 42(5): 1337-1348.
    [35]????????????? Jiang C, Xu H, Dong M, et al. Hallucination augmented contrastive learning for multimodal large language model [C] // 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024: 27026-27036.
    [36]????????????? Wang Y, Luo Y, Li B, et al. Multi-modality Fusion Based Lung Cancer Survival Analysis with Self-supervised Whole Slide Image Representation Learning [C] // 2023 Pattern Recognition and Computer Vision: 6th Chinese Conference (PRCV), 2023: 333-345.
    [37]????????????? Koutsoubis N, Waqas A, Yilmaz Y, et al. Future-Proofing Medical Imaging with Privacy-Preserving Federated Learning and Uncertainty Quantification: A Review [J]. arxiv:2409.16340[eess.IV,cs.AI,cs.CV], 2024.
    [38]????????????? Xie L, Lin M, Liu S, et al. pFLFE: Cross-silo Personalized Federated Learning viaFeature Enhancem ent onMedical Image Segmentation [M]. Springer Nature Switzerland; 2024.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

引文格式
谢卓恒,伊鸣,黄新瑞.多实例学习在医学图像分析中的应用进展 [J].集成技术,2025,14(2):24-32

Citing format
XIE Zhuoheng, YI Ming, HUANG Xinrui. Application Progress of Multi-instance Learning in Medical Image Analysis[J]. Journal of Integration Technology,2025,14(2):24-32

复制
分享
文章指标
  • 点击次数:65
  • 下载次数: 28
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2024-11-11
  • 最后修改日期:2024-12-28
  • 录用日期:2025-01-07
  • 在线发布日期: 2025-03-14
文章二维码

《集成技术》官网

《集成技术》公众号

  • 集成技术 ® 2025 版权所有
  • 地址：深圳市南山区西丽深圳大学城学苑大道1068号 ,邮政编码：518055
  • 电话：0755-86392070 传真：0755-86392073 Email：jcjs@siat.ac.cn
  • 技术支持：北京勤云科技发展有限公司