# Style transfer as data augmentation: evaluating unpaired image-to-image translation models in mammography

arXiv: https://arxiv.org/abs/2502.02475 · HTML: https://mlsanity.com/paper/2502.02475/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 4 Feb 2025.

## Builds on (most cited first, 10 of 10)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Rethinking FID: Towards a Better Evaluation Metric for Image Generation](https://mlsanity.com/paper/2401.09603/) (2023)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [Unsupervised Medical Image Translation with Adversarial Diffusion Models](https://mlsanity.com/paper/2207.08208/) (2022)
- [VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography](https://mlsanity.com/paper/2203.11205/) (2022)
- [mr2NST: Multi-Resolution and Multi-Reference Neural Style Transfer for Mammography](https://mlsanity.com/paper/2005.11926/) (2020)
- [Five Pitfalls When Assessing Synthetic Medical Images with Reference Metrics](https://mlsanity.com/paper/2408.06075/) (2024)
- [Trustworthy image-to-image translation: evaluating uncertainty calibration in unpaired training scenarios](https://mlsanity.com/paper/2501.17570/) (2025)

## Built on by (most cited first, 1 of 1)

- [Quantifying the uncertainty of model-based synthetic image quality metrics](https://mlsanity.com/paper/2504.03623/) (2025)

## Abstract (arXiv)

Several studies indicate that deep learning models can learn to detect breast cancer from mammograms (X-ray images of the breasts). However, challenges with overfitting and poor generalisability prevent their routine use in the clinic. Models trained on data from one patient population may not perform well on another due to differences in their data domains, emerging due to variations in scanning technology or patient characteristics. Data augmentation techniques can be used to improve generalisability by expanding the diversity of feature representations in the training data by altering existing examples. Image-to-image translation models are one approach capable of imposing the characteristic feature representations (i.e. style) of images from one dataset onto another. However, evaluating model performance is non-trivial, particularly in the absence of ground truths (a common reality in medical imaging). Here, we describe some key aspects that should be considered when evaluating style transfer algorithms, highlighting the advantages and disadvantages of popular metrics, and important factors to be mindful of when implementing them in practice. We consider two types of generative models: a cycle-consistent generative adversarial network (CycleGAN) and a diffusion-based SynDiff model. We learn unpaired image-to-image translation across three mammography datasets. We highlight that undesirable aspects of model performance may determine the suitability of some metrics, and also provide some analysis indicating the extent to which various metrics assess unique aspects of model performance. We emphasise the need to use several metrics for a comprehensive assessment of model performance.