Simultaneous Dual-View Mammogram Synthesis Using Denoising Diffusion Probabilistic Models
This work addresses a dataset limitation in breast cancer screening for AI algorithm development, though it is incremental as it adapts existing diffusion models to a specific medical imaging task.
The paper tackled the problem of incomplete paired mammogram views in datasets by proposing a three-channel denoising diffusion probabilistic model to simultaneously generate craniocaudal and mediolateral oblique views, with results showing that difference-based encoding helps preserve global breast structure across views.
Breast cancer screening relies heavily on mammography, where the craniocaudal (CC) and mediolateral oblique (MLO) views provide complementary information for diagnosis. However, many datasets lack complete paired views, limiting the development of algorithms that depend on cross-view consistency. To address this gap, we propose a three-channel denoising diffusion probabilistic model capable of simultaneously generating CC and MLO views of a single breast. In this configuration, the two mammographic views are stored in separate channels, while a third channel encodes their absolute difference to guide the model toward learning coherent anatomical relationships between projections. A pretrained DDPM from Hugging Face was fine-tuned on a private screening dataset and used to synthesize dual-view pairs. Evaluation included geometric consistency via automated breast mask segmentation and distributional comparison with real images, along with qualitative inspection of cross-view alignment. The results show that the difference-based encoding helps preserve the global breast structure across views, producing synthetic CC-MLO pairs that resemble real acquisitions. This work demonstrates the feasibility of simultaneous dual-view mammogram synthesis using a difference-guided DDPM, highlighting its potential for dataset augmentation and future cross-view-aware AI applications in breast imaging.