UESTC-nnLab / ProDiv

[CMPB 2024] ProDiv: Prototype-driven consistent pseudo-bag division for whole-slide image classification

ProDiv: Prototype-driven consistent pseudo-bag division for whole-slide image classification

Computer Methods and Programs in Biomedicine, 2024

[Journal Link] | [arXiv] | [Related Resources] | [Citation]

Abstract: (1) Methods: This scheme first designs an attention-based method to generate a bag prototype for each slide. On this basis, it further groups WSI patch instances into a series of instance clusters according to the feature similarities between the prototype and patches. Finally, pseudo-bags are obtained by randomly combining the non-overlapping patch instances of different instance clusters. Moreover, the design scheme of our ProDiv considers practicality, and it could be smoothly assembled with almost all the MIL-based WSI classification methods in recent years. (2) Conclusions: ProDiv could almost always bring obvious performance improvements to compared MIL models on typical metrics, which suggests the effectiveness of our scheme. Experimental visualization also visually interprets the correctness of the proposed ProDiv.

---

We use the pre-trained ResNet50 for extracting patch features. You can download the pre-trained ResNet50 at here.

ProDiv+

An improved version (ProDiv+) can be found at PseMix. Moreover, ProDiv is also contained. For more details, you can move to the PseMix repo.

🔥 Related Resources

Here we list the related works involving pseudo-bags or using pseudo-bags for training deep MIL networks.

Model	Subfield	Paper	Code	Base
BDOCOX (TMI'21)	WSI Survival Analysis	Weakly supervised deep ordinal cox model for survival prediction from wholeslide pathological images	-	K-means-based pseudo-bag division
DTFD-MIL (CVPR'22)	WSI Classification	Dtfd-mil: Double-tier feature distillation multiple instance learning for histopathology whole slide image classification	Github	Random pseudo-bag division
ProDiv (CMPB'24)	WSI Classification	ProDiv: Prototype-driven Consistent Pseudo-bag Division for Whole-slide Image Classification	Github	Prototype-based consistent pseudo-bag division
PseMix (TMI'24)	WSI Classification	Pseudo-Bag Mixup Augmentation for Multiple Instance Learning-Based Whole Slide Image Classification	Github	Pseudo-bag Mixup
ICMIL (TMI'24)	WSI classification	Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Bag-Level Classifier is a Good Instance-Level Teacher	Github	Utilizing pseudo-bags in training
PMIL	WSI classification	Shapley Values-enabled Progressive Pseudo Bag Augmentation for Whole Slide Image Classification	-	Progressive pseudo-bag augmentation

📝 Citation

If you find this work helps your research, please consider citing our paper via

@article{YANG2024108161,
    author = {Yang, Rui and Liu, Pei and Ji, Luping},
    doi = {https://doi.org/10.1016/j.cmpb.2024.108161},
    issn = {0169-2607},
    journal = {Computer Methods and Programs in Biomedicine},
    pages = {108161},
    title = {{ProDiv: Prototype-driven consistent pseudo-bag division for whole-slide image classification}},
    url = {https://www.sciencedirect.com/science/article/pii/S0169260724001573},
    volume = {249},
    year = {2024}
}