GAFR-Net: A Graph Attention and Fuzzy-Rule Network for Interpretable Breast Cancer Image Classification

2026-02-10

AI Summary

This work proposes an end-to-end interpretable method for classifying breast cancer histopathological images in settings with limited labeled data and where conventional deep learning models lack transparency. By constructing a graph representation based on sample similarity and employing a multi-head graph attention mechanism to capture complex inter-structural relationships, the approach integrates a differentiable fuzzy rule module that translates topological features—such as node degree and clustering coefficient—into human-readable “IF-THEN” diagnostic rules, thereby emulating heuristic reasoning by medical experts. Unlike post-hoc explanation techniques, this model is inherently interpretable and achieves state-of-the-art performance across multiple datasets (BreakHis, Mini-DDSM, and ICIAR2018) under varying magnification levels and classification tasks, significantly enhancing both classification accuracy and clinical interpretability in weakly supervised scenarios.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Transparent, Interpretable, Explainable ML

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Accurate classification of breast cancer histopathology images is pivotal for early oncological diagnosis and therapeutic intervention.However, conventional deep learning architectures often encounter performance degradation under limited annotations and suffer from a"blackbox"nature, hindering their clinical integration. To mitigate these limitations, we propose GAFRNet, a robust and interpretable Graph Attention and FuzzyRule Network specifically engineered for histopathology image classification with scarce supervision. GAFRNet constructs a similarity-driven graph representation to model intersample relationships and employs a multihead graph attention mechanism to capture complex relational features across heterogeneous tissue structures.Concurrently, a differentiable fuzzy-rule module encodes intrinsic topological descriptorsincluding node degree, clustering coefficient, and label consistencyinto explicit, human-understandable diagnostic logic. This design establishes transparent"IF-THEN"mappings that mimic the heuristic deduction process of medical experts, providing clear reasoning behind each prediction without relying on post-hoc attribution methods. Extensive evaluations on three benchmark datasets (BreakHis, Mini-DDSM, and ICIAR2018) demonstrate that GAFR-Net consistently outperforms various state-of-the-art methods across multiple magnifications and classification tasks. These results validate the superior generalization and practical utility of GAFR-Net as a reliable decision-support tool for weakly supervised medical image analysis.

Problem

• breast cancer
• histopathology image classification
• limited annotations
• black-box models
• clinical interpretability

Innovation

• Graph Attention
• Fuzzy-Rule Network
• Interpretable AI
• Weakly Supervised Learning
• Histopathology Image Classification