Robust Training with Data Augmentation for Medical Imaging Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Martínez-Martínez, Josué, Brown, Olivia, Karami, Mostafa, Nabavi, Sheida
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915353249972224
author Martínez-Martínez, Josué
Brown, Olivia
Karami, Mostafa
Nabavi, Sheida
author_facet Martínez-Martínez, Josué
Brown, Olivia
Karami, Mostafa
Nabavi, Sheida
contents Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect diagnostic reliability and undermine trust among healthcare professionals. In this study, we propose a robust training algorithm with data augmentation (RTDA) to mitigate these vulnerabilities in medical image classification. We benchmark classifier robustness against adversarial perturbations and natural variations of RTDA and six competing baseline techniques, including adversarial training and data augmentation approaches in isolation and combination, using experimental data sets with three different imaging technologies (mammograms, X-rays, and ultrasound). We demonstrate that RTDA achieves superior robustness against adversarial attacks and improved generalization performance in the presence of distribution shift in each image classification task while maintaining high clean accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17133
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Training with Data Augmentation for Medical Imaging Classification
Martínez-Martínez, Josué
Brown, Olivia
Karami, Mostafa
Nabavi, Sheida
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect diagnostic reliability and undermine trust among healthcare professionals. In this study, we propose a robust training algorithm with data augmentation (RTDA) to mitigate these vulnerabilities in medical image classification. We benchmark classifier robustness against adversarial perturbations and natural variations of RTDA and six competing baseline techniques, including adversarial training and data augmentation approaches in isolation and combination, using experimental data sets with three different imaging technologies (mammograms, X-rays, and ultrasound). We demonstrate that RTDA achieves superior robustness against adversarial attacks and improved generalization performance in the presence of distribution shift in each image classification task while maintaining high clean accuracy.
title Robust Training with Data Augmentation for Medical Imaging Classification
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2506.17133