# Deep-learning based adaptive fusion of CC and MLO views for improved mammographic cancer diagnosis

## TL;DR

This paper introduces a deep learning model that improves breast cancer diagnosis by better combining two mammogram views.

## Contribution

A dual-branch deep learning framework with adaptive fusion for mammogram classification is proposed.

## Key findings

- The framework achieved 92.116% accuracy on the VinDr-Mammo dataset.
- It achieved 95.556% accuracy on the INBreast dataset.
- Grad-CAM visualizations demonstrated model explainability by highlighting lesion regions.

## Abstract

Breast cancer remains the most prevalent malignancy among women worldwide. The timely detection of this cancer type is critical for improving survival outcomes. Despite advancements, mammogram classification using deep learning strategies still faces challenges. These include inter-view feature inconsistency, loss of diagnostic details, and limited interpretability. In order to address these issues, MammoFusion-Net, a dual-branch deep learning framework, is proposed for mammogram-based breast cancer classification. Using residual convolutional streams, the framework processes craniocaudal (CC) and mediolateral oblique (MLO) views independently. This supports preservation of view-specific anatomical information. In the proposed framework, a Gates Cross-View Fusion mechanism adaptively integrates features across views. As a result of experimental analysis, the proposed framework achieved 92.116 % (VinDr-Mammo dataset) and 95.556 % (INBreast dataset) of improved classification performance.•Employs a dual-branch architecture to independently process CC and MLO views using residual convolutional streams.•Integrates Gated Cross-View Fusion and attention mechanisms adaptively and refines multi-view features for stronger discrimination.•Demonstrates the explainability of the model through Grad-CAM visualizations that highlight lesion-relevant regions.

Employs a dual-branch architecture to independently process CC and MLO views using residual convolutional streams.

Integrates Gated Cross-View Fusion and attention mechanisms adaptively and refines multi-view features for stronger discrimination.

Demonstrates the explainability of the model through Grad-CAM visualizations that highlight lesion-relevant regions.

Image, graphical abstract