# Automated Mammogram Analysis with a Deep Learning Pipeline

## TL;DR

This paper presents an automated deep learning pipeline for mammogram analysis that detects and classifies lesions using cGAN and DenseNet, improving efficiency and robustness across datasets.

## Contribution

The study introduces a novel pipeline combining cGAN for detection and DenseNet for classification, reducing computational redundancy and enhancing generalization.

## Key findings

- Effective detection and classification on multiple datasets
- Robustness demonstrated on unseen clinical data
- Improved efficiency over patch-based methods

## Abstract

Current deep learning based detection models tackle detection and segmentation tasks by casting them to pixel or patch-wise classification. To automate the initial mass lesion detection and segmentation on the whole mammographic images and avoid the computational redundancy of patch-based and sliding window approaches, the conditional generative adversarial network (cGAN) was used in this study. Subsequently, feeding the detected regions to the trained densely connected network (DenseNet), the binary classification of benign versus malignant was predicted. We used a combination of publicly available mammographic data repositories to train the pipeline, while evaluating the model's robustness toward our clinically collected repository, which was unseen to the pipeline.