MAMBO: High-Resolution Generative Approach for Mammography Images

Milica Škipina1,2,3, Nikola Jovišić1,3, Nicola Dall'Asen2,4, Vanja Švenda1, Anil Osman Tur2,6, Slobodan Ilić1, Elisa Ricci2,5, Dubravko Ćulibrk1,3,
1The Institute for Artificial Intelligence Research and Development of Serbia
2University of Trento  3Faculty of Technical Sciences, University of Novi Sad
4University of Pisa  5Fondazione Bruno Kessler  6University of Verona
Paper Code arXiv
MAMBO synthetic 3840x3840 mammogram

Abstract

Mammography is the gold standard for the detection and diagnosis of breast cancer. This procedure can be significantly enhanced with Artificial Intelligence (AI)-based software, which assists radiologists in identifying abnormalities. However, training AI systems requires large and diverse datasets, which are often difficult to obtain due to privacy and ethical constraints. To address this issue, the paper introduces MAMmography ensemBle mOdel (MAMBO), a novel patch-based diffusion approach designed to generate full-resolution mammograms. Diffusion models have shown breakthrough results in realistic image generation, yet few studies have focused on mammograms, and none have successfully generated high-resolution outputs required to capture fine-grained features of small lesions. To achieve this, MAMBO integrates separate diffusion models to capture both local and global (image-level) contexts. The contextual information is then fed into the final model, significantly aiding the noise removal process. This design enables MAMBO to generate highly realistic mammograms of up to 3840×3840 pixels. Importantly, this approach can be used to enhance the training of classification models and extended to anomaly segmentation. Experiments, both numerical and radiologist validation, assess MAMBO's capabilities in image generation, super-resolution, and anomaly segmentation, highlighting its potential to enhance mammography analysis for more accurate diagnoses and earlier lesion detection.

MAMBO synthetic 3840x3840 mammogram

Synthetic 3840x3840 mammogram generated using MAMBO. Details at different resolutions correspond to the global context (whole image), local context, and individual patch.

Method

MAMBO method

In the three-stage approach of MAMBO, the first stage of the model generates a novel global context x0G, which is then used to generate a set of local contexts x0L in the second stage, conditioned on shifted global contexts →x0G. Synthetic global context and synthetic local contexts become the conditioning in the third stage to generate highly detailed patches x0P, which are finally combined to obtain a high-resolution full mammogram.

Examples

BibTeX

@article{vskipina2025mambo,
  title={MAMBO: High-Resolution Generative Approach for Mammography Images},
  author={{\v{S}}kipina, Milica and Jovi{\v{s}}i{\'c}, Nikola and Dall'Asen, Nicola and {\v{S}}venda, Vanja and Tur, Anil Osman and Ili{\'c}, Slobodan and Ricci, Elisa and {\'C}ulibrk, Dubravko},
  journal={arXiv preprint arXiv:2506.08677},
  year={2025}
}