基于聚类的多实例学习全视野数字切片分类

doi:10.3969/j.issn.0258-8021.2024.06.002

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (4459 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Pathological images are the gold standard for cancer examination. Fast and accurate classification of pathological images, especially whole slide images (WSI), helps medical doctors provide personalized treatment and prognosis assessment for patients. In recent years, multiple instance learning (MIL) has played an increasingly important role in WSI classification. However, due to the limited number of WSIs and the low proportion of positive areas, the existing MIL method based on attention mechanism may lead to overfitting, thus affecting the classification performance. To solve this problem, we proposed a new clustering-based MIL classification method. Specifically, this method divided each bag into multiple pseudo bags to increase the number of packages and let the network pay attention to more positive instances. Then, to solve the problem that a pseudo-bag is easy to be full of negative instances in the pseudo-bag division process, resulting in noise, this paper proposed a new pseudo-bag division method based on clustering. Finally, to obtain more accurate classification results, we conducted secondary learning on the learned pseudo-bag-level features to get the final bag-level features and achieve the final WSI classification. We conducted experiments on the Camelyon16 and TCGA-Lung datasets, which have 399 and 1 038 WSIs, respectively, with classification accuracies of 90.69% and 86.54%, and F1-scores of 90.20% and 86.52%. The experimental results showed that the proposed method could be appled to WSI classification effectively.

Key words： whole slide image(WSI) multiple instance learning(MIL) classification clustering pseudo bag

Received: 02 April 2024

PACS:

R318

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Zhong Haiqin
	Zhao Cheng
	Lei Baiying
	Wang Tianfu

Cite this article:

Zhong Haiqin,Zhao Cheng,Lei Baiying, et al. Cluster-Based Multiple Instance Learning for Whole Slide Image Classification[J]. Chinese Journal of Biomedical Engineering, 2024, 43(6): 652-661.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2024.06.002 OR http://cjbme.csbme.org/EN/Y2024/V43/I6/652

[1] He Lei, Long LR, Antani S, et al. Histology image analysis for carcinoma detection and grading [J]. Computer Methods and Programs in Biomedicine, 2012, 107(3): 538-556.
[2] Li Xintong, Li Chen, Rahaman M, et al. A comprehensive review of computer-aided whole-slide image analysis: from datasets to feature extraction, segmentation, classification and detection approaches [J]. Artificial Intelligence Review, 2022, 55(6): 4809-4878.
[3] Tizhoosh HR, Diamandis P, Campbell CJV, et al. Searching images for consensus: can AI remove observer variability in pathology? [J]. The American Journal of Pathology, 2021, 191(10): 1702-1708.
[4] Zhu Xiaohui, Li Xiaoming, Ong K, et al. Hybrid AI-assistive diagnostic model permits rapid TBS classification of cervical liquid-based thin-layer cell smears [J]. Nature Communications, 2021, 12(1): 3541.
[5] Zhang Jianan, Wu Yongfei, Hao Fang, et al. Double similarities weighted multi-instance learning kernel and its application [J]. Expert Systems with Applications, 2024, 238: 121900.
[6] Liu Kangning, Zhu Weicheng, Shen Yiqiu, et al. Multiple instance learning via iterative self-paced supervised contrastive learning [C] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023: 3355-3365.
[7] Sharma Y, Shrivastava A, Ehsan L, et al. Cluster-to-conquer: A framework for end-to-end multi-instance learning for whole slide image classification [C] // Medical Imaging with Deep Learning. Montreal: PMLR, 2021: 682-698.
[8] Hashimoto N, Fukushima D, Koga R, et al. Multi-scale domain-adversarial multiple-instance CNN for cancer subtype classification with unannotated histopathological images [C] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Virtual: IEEE, 2020: 3852-3861.
[9] Ilse M, Tomczak JM, Welling M. Attention-based deep multiple instance learning [C] // International Conference on Machine Learning. Stockholm: PMLR, 2018: 2127-2136.
[10] Lu MingYang, Williamson DFK, Chen TY, et al. Data-efficient and weakly supervised computational pathology on whole-slide images [J]. Nature Biomedical Engineering, 2021, 5(6): 555-570.
[11] Li Bin, Li Yin, Eliceiri KW. Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning [C] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Virtual: IEEE, 2021: 14318-14328.
[12] Tiwari R, Shenoy P. Overcoming simplicity bias in deep networks using a feature sieve [C] // International Conference on Machine Learning. Hawaii: PMLR, 2023: 34330-34343.
[13] Huang Zeyi, Wang Haohan, Xing EP, et al. Self-challenging improves cross-domain generalization [C] // Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II 16. Springer International Publishing, 2020: 124-140.
[14] Zhang Yunlong, Li Honglin, Sun Yuxuan, et al. Attention-challenging multiple instance learning for whole slide image classification [EB/OL]. https://arxiv.org/abs/2311.07125, 2023-11-13/2024-04-07.
[15] Shao Zhuchen, Bian Hao, Chen Yang, et al. Transmil: Transformer based correlated multiple instance learning for whole slide image classification [J]. Advances in Neural Information Processing Systems, 2021, 34: 2136-2147.
[16] Zhu Zhonghang, Yu Lequan, Wu Wei, et al. MuRCL: multi-instance reinforcement contrastive learning for whole slide image classification [J]. IEEE Transactions on Medical Imaging, 2022, 42(5): 1337-1348.
[17] Bejani MM, Ghatee M. A systematic review on overfitting control in shallow and deep neural networks [J]. Artificial Intelligence Review, 2021, 54(8): 6391-6438.
[18] Zhang Hongrun, Meng Yanda, Zhao Yitian,et al. DTFD-MIL: double-tier feature distillation multiple instance learning for histopathology whole slide image classification [C] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 18802-18812.
[19] Bejnordi BE, Veta M, Van Diest PJ, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer [J]. JAMA, 2017, 318(22): 2199-2210.
[20] Steinbach M. A comparison of document clustering techniques [R]. Technical Report# 00_034/University of Minnesota, 2000.
[21] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition [C] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[22] Amores J. Multiple instance classification: Review, taxonomy and comparative study[J]. Artificial Intelligence, 2013, 201: 81-105.
[23] Chen Z, Chi Z, Fu H, et al. Multi-instance multi-label image classification: A neural approach[J]. Neurocomputing, 2013, 99: 298-306.
[24] Wang X, Chen H, Gan C, et al. Weakly supervised deep learning for whole slide lung cancer image analysis[J]. IEEE Transactions on Cybernetics, 2019, 50(9): 3950-3962.