FECT: Classification of Breast Cancer Pathological Images Based on Fusion Features

2025-01-17

AI Summary

Fine-grained classification of breast cancer histopathological images suffers from low accuracy for challenging subtypes—particularly ductal carcinoma in situ (DCIS)—due to insufficient exploitation of morphological diagnostic cues. Method: We propose a pathology-interpretable, end-to-end model that fuses edge-, cell-, and tissue-level features. It employs a ResMTUNet-based multi-scale encoder to extract heterogeneous features and introduces a pathology-guided attention-weighted aggregation mechanism to jointly model these three complementary morphological cues. Results: On the BRACS dataset, our model surpasses state-of-the-art methods in both overall accuracy and F1-score, with particularly pronounced improvements for confusable subtypes. To our knowledge, this is the first work to unify edge structure, cellular morphology, and tissue architecture within a single discriminative and clinically interpretable framework, demonstrating strong potential for practical clinical decision support.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• 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

Breast cancer is one of the most common cancers among women globally, with early diagnosis and precise classification being crucial. With the advancement of deep learning and computer vision, the automatic classification of breast tissue pathological images has emerged as a research focus. Existing methods typically rely on singular cell or tissue features and lack design considerations for morphological characteristics of challenging-to-classify categories, resulting in suboptimal classification performance. To address these problems, we proposes a novel breast cancer tissue classification model that Fused features of Edges, Cells, and Tissues (FECT), employing the ResMTUNet and an attention-based aggregator to extract and aggregate these features. Extensive testing on the BRACS dataset demonstrates that our model surpasses current advanced methods in terms of classification accuracy and F1 scores. Moreover, due to its feature fusion that aligns with the diagnostic approach of pathologists, our model exhibits interpretability and holds promise for significant roles in future clinical applications.

Problem

• Breast Cancer
• Pathological Image Recognition
• Accuracy Improvement

Innovation

• FECT
• ResMTUNet
• Breast Cancer Pathology Image Analysis