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

TL;DR

This paper introduces FECT, a novel deep learning model that fuses edge, cell, and tissue features for improved breast cancer image classification, demonstrating superior accuracy and interpretability on the BRACS dataset.

Contribution

The paper presents a new feature fusion model using ResMTUNet and attention mechanisms, enhancing classification performance and interpretability over existing methods.

Findings

Outperforms existing methods in accuracy and F1 score on BRACS dataset

Utilizes a novel feature fusion approach aligned with pathologists' diagnostic process

Demonstrates potential for clinical application due to interpretability

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.