A cluster attention-based multiple instance learning network for enhancing histopathological image interpretation

Histopathological diagnosis involves examining abnormal architectural patterns and cellular-level changes. Whole slide images (WSIs) provide comprehensive digital representations of tissue samples, enabling detailed analysis and interpretation. Annotating the giga-pixel images remains labor-intensiv...

Full description

Saved in:
Bibliographic Details
Published in:Computers in biology and medicine Vol. 193; p. 110353
Main Authors: Ko, Seokhwan, Ando, Yu, Kim, Moonsik, Park, Nora Jee-Young, Han, Hyungsoo, Park, Ji Young, Cho, Junghwan
Format: Journal Article
Language:English
Published: United States Elsevier Ltd 01.07.2025
Subjects:
Cluster Analysis
Clustering
Deep learning
Histopathology
Humans
Image Interpretation, Computer-Assisted - methods
Internal Medicine
Machine Learning
Multiple instance learning
Multiple-Instance Learning Algorithms
Neoplasms - diagnostic imaging
Neoplasms - pathology
Other
Weakly-supervised learning
Deep learning
Histopathology
Weakly-supervised learning
Clustering
Multiple instance learning
ISSN:0010-4825, 1879-0534, 1879-0534
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Histopathological diagnosis involves examining abnormal architectural patterns and cellular-level changes. Whole slide images (WSIs) provide comprehensive digital representations of tissue samples, enabling detailed analysis and interpretation. Annotating the giga-pixel images remains labor-intensive, requiring experts to label abnormal patterns and cellular changes. To address this, Multiple Instance Learning (MIL), a promising weakly supervised approach, enables models to learn from limited annotations while preserving key histopathological features. However, existing MIL-based methods may overlook potential semantic features, limiting their effectiveness. To overcome this limitation, we propose a novel Cluster-Aware Attention-based MIL (CAAMIL) architecture. This approach employs an advanced attention-based module integrated with a clustering method to enhance the interpretability of heterogeneous features. Our approach clusters architectural or cytologic features, making the groups interpretable at the cluster level and reflective of histopathological grades or prognostic indicators. We demonstrated the efficacy of our model in both slide-level and patch-level classification as well as in interpreting tumor and mutation predictions. Experimental results show that our model achieves an AUC score of 0.96 for tumor detection at slide-level and 0.85 at patch-level, outperforming other state-of-the-art MIL-based methods. Our proposed CAAMIL architecture overcomes the limitations of existing MIL methods by effectively clustering features and providing interpretable results. The high accuracy and interpretability of our model make it a promising tool for histopathological diagnosis and tumor detection. •Proposed a novel architecture leveraging cluster attention mechanisms.•Optimized training conditions to enhance performance and reduce computation.•Enhanced interpretability over other methods based on human annotations.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0010-4825
1879-0534
1879-0534
DOI:10.1016/j.compbiomed.2025.110353