The application of generative models for the synthetic expansion of medical image datasets has been explored in recent research, offering new opportunities to combat data scarcity and improve computer-aided diagnosis (CAD) systems. In this study, we explore the use of a generative framework based on neural cellular automata (NCA) for the synthesis of mammographic images. While UNet and similar models focus on global coherence, NCAs inherently prioritize local dependencies through repeated, neighborhood-based updates. This feature facilitates capturing local details such as microcalcifications, subtle spiculations, and fine tissue textures, crucial for accurate diagnosis with mammographic images. To our knowledge, this is the first implementation of this type of framework for generating synthetic mammograms. The framework was adapted to process images from the VinDr-Mammo dataset, supporting both full mammograms and extracted findings in a highly configurable workflow. We integrated a custom breast density classifier to evaluate the impact of the addition of synthetic images on downstream classification performance. Qualitative and quantitative evaluations demonstrate that the adapted model is capable of generating perceptually realistic mammograms, with Kernel Inception Distance scores between 0.015 and 0.032. The addition of synthetic data to the density classifier’s training dataset improved macro F1-scores by up to \(12\%\) in underrepresented density classes across multiple dataset configurations, although the effects on binary classification metrics remained mixed. These findings suggest that neural cellular diffusion models hold promise for mammographic image synthesis and further work is warranted to validate these results in clinical settings and with additional datasets.