Using a Genetic Algorithm to Update Convolutional Neural Networks for Abnormality Classification in Mammography

Steven Wessels, Dustin van der Haar

2023

Abstract

The processing of medical imaging studies is a costly and error-prone task. The use of deep learning algorithms for the automated classification of abnormalities can aid radiologists in interpreting medical images. This paper presents a genetic algorithm that is used to fine-tune the internal parameters of convolutional neural networks trained for abnormality classification in mammographic imaging. We used our genetic algorithm to search for the neural network weights representing the global minimum solution for ResNet50 and Xception architectures. The Xception architecture outperformed the ResNet baseline for both tasks, with the Xception baseline model achieving an AUC score of 72%. The genetic algorithm demonstrated a slight proclivity for improving the general metric evaluations of the network that it fine-tuned, but in some cases, it was still prone to miss good regions in the search space.

Paper Citation

in Harvard Style

Wessels S. and van der Haar D. (2023). Using a Genetic Algorithm to Update Convolutional Neural Networks for Abnormality Classification in Mammography. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 790-797. DOI: 10.5220/0011648500003411

in Bibtex Style

@conference{icpram23,
author={Steven Wessels and Dustin van der Haar},
title={Using a Genetic Algorithm to Update Convolutional Neural Networks for Abnormality Classification in Mammography},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={790-797},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011648500003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Using a Genetic Algorithm to Update Convolutional Neural Networks for Abnormality Classification in Mammography
SN - 978-989-758-626-2
AU - Wessels S.
AU - van der Haar D.
PY - 2023
SP - 790
EP - 797
DO - 10.5220/0011648500003411