CAMIL: Channel Attention-based Multiple Instance Learning for Whole Slide Image Classification

Overview

Journal Bioinformatics

Publisher Oxford University Press

Date 2025 Jan 17

PMID 39820310

Authors

Jinyang Mao

Junlin Xu

Xianfang Tang

Yongjin Liu

Heaven Zhao

Geng Tian

Jialiang Yang

Affiliations

Soon will be listed here.

Abstract

Motivation: The classification task based on whole-slide images (WSIs) is a classic problem in computational pathology. Multiple instance learning (MIL) provides a robust framework for analyzing whole slide images with slide-level labels at gigapixel resolution. However, existing MIL models typically focus on modeling the relationships between instances while neglecting the variability across the channel dimensions of instances, which prevents the model from fully capturing critical information in the channel dimension.

Results: To address this issue, we propose a plug-and-play module called Multi-scale Channel Attention Block (MCAB), which models the interdependencies between channels by leveraging local features with different receptive fields. By alternately stacking four layers of Transformer and MCAB, we designed a channel attention-based MIL model (CAMIL) capable of simultaneously modeling both inter-instance relationships and intra-channel dependencies. To verify the performance of the proposed CAMIL in classification tasks, several comprehensive experiments were conducted across three datasets: Camelyon16, TCGA-NSCLC, and TCGA-RCC. Empirical results demonstrate that, whether the feature extractor is pretrained on natural images or on WSIs, our CAMIL surpasses current state-of-the-art MIL models across multiple evaluation metrics.

Availability And Implementation: All implementation code is available at https://github.com/maojy0914/CAMIL.

References

Xiong Y, Zeng Z, Chakraborty R, Tan M, Fung G, Li Y . Nyströmformer: A Nystöm-based Algorithm for Approximating Self-Attention. Proc AAAI Conf Artif Intell. 2021; 35(16):14138-14148. PMC: 8570649. View

Zhu W, Sun L, Huang J, Han L, Zhang D . Dual Attention Multi-Instance Deep Learning for Alzheimer's Disease Diagnosis With Structural MRI. IEEE Trans Med Imaging. 2021; 40(9):2354-2366. DOI: 10.1109/TMI.2021.3077079. View

Li B, Li Y, Eliceiri K . Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning. Conf Comput Vis Pattern Recognit Workshops. 2022; 2021:14318-14328. PMC: 8765709. DOI: 10.1109/CVPR46437.2021.01409. View

Bejnordi B, Veta M, van Diest P, van Ginneken B, Karssemeijer N, Litjens G . Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer. JAMA. 2017; 318(22):2199-2210. PMC: 5820737. DOI: 10.1001/jama.2017.14585. View

Wang X, Yang S, Zhang J, Wang M, Zhang J, Yang W . Transformer-based unsupervised contrastive learning for histopathological image classification. Med Image Anal. 2022; 81:102559. DOI: 10.1016/j.media.2022.102559. View

Huang H, Chen Z, Zou Y, Lu M, Chen C, Song Y . Channel prior convolutional attention for medical image segmentation. Comput Biol Med. 2024; 178:108784. DOI: 10.1016/j.compbiomed.2024.108784. View

Lu M, Chen T, Williamson D, Zhao M, Shady M, Lipkova J . AI-based pathology predicts origins for cancers of unknown primary. Nature. 2021; 594(7861):106-110. DOI: 10.1038/s41586-021-03512-4. View

Huang K, Lin B, Liu J, Liu Y, Li J, Tian G . Predicting colorectal cancer tumor mutational burden from histopathological images and clinical information using multi-modal deep learning. Bioinformatics. 2022; 38(22):5108-5115. DOI: 10.1093/bioinformatics/btac641. View

Srinidhi C, Ciga O, Martel A . Deep neural network models for computational histopathology: A survey. Med Image Anal. 2020; 67:101813. PMC: 7725956. DOI: 10.1016/j.media.2020.101813. View

10.

He L, Long L, Antani S, Thoma G . Histology image analysis for carcinoma detection and grading. Comput Methods Programs Biomed. 2012; 107(3):538-56. PMC: 3587978. DOI: 10.1016/j.cmpb.2011.12.007. View

11.

Wang X, Chen H, Gan C, Lin H, Dou Q, Tsougenis E . Weakly Supervised Deep Learning for Whole Slide Lung Cancer Image Analysis. IEEE Trans Cybern. 2019; 50(9):3950-3962. DOI: 10.1109/TCYB.2019.2935141. View

12.

Wagner S, Reisenbuchler D, West N, Niehues J, Zhu J, Foersch S . Transformer-based biomarker prediction from colorectal cancer histology: A large-scale multicentric study. Cancer Cell. 2023; 41(9):1650-1661.e4. PMC: 10507381. DOI: 10.1016/j.ccell.2023.08.002. View

13.

Dov D, Kovalsky S, Assaad S, Cohen J, Elliott Range D, Pendse A . Weakly supervised instance learning for thyroid malignancy prediction from whole slide cytopathology images. Med Image Anal. 2020; 67:101814. PMC: 7726041. DOI: 10.1016/j.media.2020.101814. View

14.

Fu Y, Liu J, Shi J . TSCA-Net: Transformer based spatial-channel attention segmentation network for medical images. Comput Biol Med. 2024; 170:107938. DOI: 10.1016/j.compbiomed.2024.107938. View

15.

Coudray N, Ocampo P, Sakellaropoulos T, Narula N, Snuderl M, Fenyo D . Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning. Nat Med. 2018; 24(10):1559-1567. PMC: 9847512. DOI: 10.1038/s41591-018-0177-5. View

16.

Lu M, Williamson D, Chen T, Chen R, Barbieri M, Mahmood F . Data-efficient and weakly supervised computational pathology on whole-slide images. Nat Biomed Eng. 2021; 5(6):555-570. PMC: 8711640. DOI: 10.1038/s41551-020-00682-w. View

17.

Pan W, An Y, Guan Y, Wang J . MCA-net: A multi-task channel attention network for Myocardial infarction detection and location using 12-lead ECGs. Comput Biol Med. 2023; 150:106199. DOI: 10.1016/j.compbiomed.2022.106199. View

18.

Graham S, Vu Q, Raza S, Azam A, Tsang Y, Kwak J . Hover-Net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images. Med Image Anal. 2019; 58:101563. DOI: 10.1016/j.media.2019.101563. View

19.

Yao Y, Lv Y, Tong L, Liang Y, Xi S, Ji B . ICSDA: a multi-modal deep learning model to predict breast cancer recurrence and metastasis risk by integrating pathological, clinical and gene expression data. Brief Bioinform. 2022; 23(6). DOI: 10.1093/bib/bbac448. View

20.

Greenwald N, Miller G, Moen E, Kong A, Kagel A, Dougherty T . Whole-cell segmentation of tissue images with human-level performance using large-scale data annotation and deep learning. Nat Biotechnol. 2021; 40(4):555-565. PMC: 9010346. DOI: 10.1038/s41587-021-01094-0. View