MAMBO: High-Resolution Generative Approach for Mammography Images

TL;DR

MAMBO is a novel high-resolution diffusion-based model that generates realistic mammograms, aiding AI training and diagnosis, by capturing fine details at 3840x3840 resolution through local and global context integration.

Contribution

This paper introduces MAMBO, the first high-resolution mammogram generator using diffusion models with local-global context integration for improved realism and utility.

Findings

Generates realistic mammograms up to 3840x3840 pixels

Enhances training of classification models with synthetic data

Supports anomaly segmentation with high fidelity

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 3840x3840 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. The source code used in this study is publicly available at: https://github.com/iai-rs/mambo.