# MammoGANesis: Controlled Generation of High-Resolution Mammograms for Radiology Education

arXiv: https://arxiv.org/abs/2010.05177 · HTML: https://mlsanity.com/paper/2010.05177/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2020.

## Built on by (most cited first, 3 of 3)

- [High-resolution synthesis of high-density breast mammograms: Application to improved fairness in deep learning based mass detection](https://mlsanity.com/paper/2209.09809/) (2022)
- [Generation of microbial colonies dataset with deep learning style transfer](https://mlsanity.com/paper/2111.03789/) (2021)
- [GAN-based generative modelling for dermatological applications -- comparative study](https://mlsanity.com/paper/2208.11702/) (2022)

## Abstract (arXiv)

During their formative years, radiology trainees are required to interpret hundreds of mammograms per month, with the objective of becoming apt at discerning the subtle patterns differentiating benign from malignant lesions. Unfortunately, medico-legal and technical hurdles make it difficult to access and query medical images for training. In this paper we train a generative adversarial network (GAN) to synthesize 512 x 512 high-resolution mammograms. The resulting model leads to the unsupervised separation of high-level features (e.g. the standard mammography views and the nature of the breast lesions), with stochastic variation in the generated images (e.g. breast adipose tissue, calcification), enabling user-controlled global and local attribute-editing of the synthesized images. We demonstrate the model's ability to generate anatomically and medically relevant mammograms by achieving an average AUC of 0.54 in a double-blind study on four expert mammography radiologists to distinguish between generated and real images, ascribing to the high visual quality of the synthesized and edited mammograms, and to their potential use in advancing and facilitating medical education.