# Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization

arXiv: https://arxiv.org/abs/2011.13011 · HTML: https://mlsanity.com/paper/2011.13011/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2020.

## Built on by (most cited first, 12 of 12)

- [Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challenges](https://mlsanity.com/paper/2303.14133/) (2023)
- [Medical Foundation Models are Susceptible to Targeted Misinformation Attacks](https://mlsanity.com/paper/2309.17007/) (2023)
- [Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between Accuracy and Robustness of DNNs](https://mlsanity.com/paper/2302.03523/) (2022)
- [Adversarially Robust Feature Learning for Breast Cancer Diagnosis](https://mlsanity.com/paper/2402.08768/) (2024)
- [SoK: Security and Privacy Risks of Healthcare AI](https://mlsanity.com/paper/2409.07415/) (2024)
- [Effective and Robust Multimodal Medical Image Analysis](https://mlsanity.com/paper/2602.15346/) (2026)
- [Image prediction of disease progression by style-based manifold extrapolation](https://mlsanity.com/paper/2111.11439/) (2021)
- [A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness](https://mlsanity.com/paper/2204.00426/) (2022)
- [On Instabilities of Unsupervised Denoising Diffusion Models in Magnetic Resonance Imaging Reconstruction](https://mlsanity.com/paper/2406.16983/) (2024)
- [Reconstruction of Patient-Specific Confounders in AI-based Radiologic Image Interpretation using Generative Pretraining](https://mlsanity.com/paper/2309.17123/) (2023)
- [Securing the Diagnosis of Medical Imaging: An In-depth Analysis of AI-Resistant Attacks](https://mlsanity.com/paper/2408.00348/) (2024)
- [Adversarial LassoNet: Robust Feature Selection via Stability-Driven Sparse Learning](https://mlsanity.com/paper/2607.03839/) (2026)

## Abstract (arXiv)

Unmasking the decision-making process of machine learning models is essential for implementing diagnostic support systems in clinical practice. Here, we demonstrate that adversarially trained models can significantly enhance the usability of pathology detection as compared to their standard counterparts. We let six experienced radiologists rate the interpretability of saliency maps in datasets of X-rays, computed tomography, and magnetic resonance imaging scans. Significant improvements were found for our adversarial models, which could be further improved by the application of dual batch normalization. Contrary to previous research on adversarially trained models, we found that the accuracy of such models was equal to standard models when sufficiently large datasets and dual batch norm training were used. To ensure transferability, we additionally validated our results on an external test set of 22,433 X-rays. These findings elucidate that different paths for adversarial and real images are needed during training to achieve state of the art results with superior clinical interpretability.