Deep Learning Hyperparameter Optimization for Breast Mass Detection in Mammograms

TL;DR

This paper introduces GA-E2E, a genetic algorithm-based method for optimizing hyperparameters in deep learning models to improve breast cancer detection accuracy in mammograms.

Contribution

It presents a novel hyperparameter tuning approach using genetic algorithms specifically for deep learning models in breast cancer detection.

Findings

Hyperparameter choices significantly impact AUC performance.

GA-E2E improves model accuracy over baseline tuning methods.

Optimized parameters lead to better detection performance.

Abstract

Accurate breast cancer diagnosis through mammography has the potential to save millions of lives around the world. Deep learning (DL) methods have shown to be very effective for mass detection in mammograms. Additional improvements of current DL models will further improve the effectiveness of these methods. A critical issue in this context is how to pick the right hyperparameters for DL models. In this paper, we present GA-E2E, a new approach for tuning the hyperparameters of DL models for brest cancer detection using Genetic Algorithms (GAs). Our findings reveal that differences in parameter values can considerably alter the area under the curve (AUC), which is used to determine a classifier's performance.