CAMIL: channel attention-based multiple instance learning for whole slide image classification
Bioinformatics · 04.02.2025 · 41 (2)
DOI: 10.1093/bioinformatics/btaf024 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 16.01.2025. Verfasst von Jinyang Mao und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics and Statistics, Fuzhou University, Fuzhou 350108, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Multiple-Instance Learning Algorithms. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Hunan Province, Wuhan Textile University Foundation.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Mathematics and Statistics, Fuzhou University, Fuzhou 350108, China.
- School of Computer Science and Technology, Wuhan University of Science and Technology, Hubei 430065, China.
- School of Computer Science and Artificial Intelligence, Wuhan Textile University, Wuhan 430200, China.
- Geneis Beijing Co., Ltd, Beijing 100102, China.
ORCID-Profile: Jinyang Mao, Junlin Xu
Förderung
- Natural Science Foundation of Hunan Province
- Wuhan Textile University Foundation
Zitieren
APA
Mao, J., Xu, J., Tang, X., Liu, Y., Zhao, H., Tian, G., & Yang, J. (2025). CAMIL: channel attention-based multiple instance learning for whole slide image classification. Bioinformatics, 41(2). https://doi.org/10.1093/bioinformatics/btaf024
Vancouver
Mao J, Xu J, Tang X, Liu Y, Zhao H, Tian G, et al. CAMIL: channel attention-based multiple instance learning for whole slide image classification. Bioinformatics. 2025;41(2). doi:10.1093/bioinformatics/btaf024
BibTeX
@article{Mao2025,
author = {Mao, Jinyang and Xu, Junlin and Tang, Xianfang and Liu, Yongjin and Zhao, Heaven and Tian, Geng and Yang, Jialiang},
title = {CAMIL: channel attention-based multiple instance learning for whole slide image classification},
journal = {Bioinformatics},
year = {2025},
volume = {41},
number = {2},
doi = {10.1093/bioinformatics/btaf024}
}
EUVIMED