MS-GWNN:multi-scale graph wavelet neural network for breast cancer diagnosis

TL;DR

This paper introduces MS-GWNN, a novel multi-scale graph wavelet neural network designed for histopathological breast cancer image classification, effectively capturing tissue structure at multiple scales to improve diagnostic accuracy.

Contribution

The paper presents a new graph neural network that leverages spectral graph wavelets for multi-scale analysis in breast cancer detection, outperforming existing methods.

Findings

MS-GWNN outperforms baseline models on public datasets.

Multi-scale analysis significantly improves diagnosis accuracy.

Ablation studies confirm the importance of multi-scale features.

Abstract

Breast cancer is one of the most common cancers in women worldwide, and early detection can significantly reduce the mortality rate of breast cancer. It is crucial to take multi-scale information of tissue structure into account in the detection of breast cancer. And thus, it is the key to design an accurate computer-aided detection (CAD) system to capture multi-scale contextual features in a cancerous tissue. In this work, we present a novel graph convolutional neural network for histopathological image classification of breast cancer. The new method, named multi-scale graph wavelet neural network (MS-GWNN), leverages the localization property of spectral graph wavelet to perform multi-scale analysis. By aggregating features at different scales, MS-GWNN can encode the multi-scale contextual interactions in the whole pathological slide. Experimental results on two public datasets demonstrate the superiority of the proposed method. Moreover, through ablation studies, we find that multi-scale analysis has a significant impact on the accuracy of cancer diagnosis.