MammoRGB: Dual-View Mammogram Synthesis Using Denoising Diffusion Probabilistic Models

TL;DR

This paper introduces a three-channel denoising diffusion probabilistic model (DDPM) for synthesizing dual-view mammograms, demonstrating realistic image quality and cross-view consistency, with potential for dataset augmentation in medical imaging.

Contribution

The study develops and evaluates a novel three-channel DDPM approach for dual-view mammogram synthesis, exploring channel encoding impacts on image fidelity and consistency.

Findings

Synthetic images have similar segmentation metrics to real images.

Sum and absolute difference encodings outperform others.

Generated images maintain cross view consistency with minimal artifacts.

Abstract

Purpose: This study aims to develop and evaluate a three channel denoising diffusion probabilistic model (DDPM) for synthesizing single breast dual view mammograms and to assess the impact of channel representations on image fidelity and cross view consistency. Materials and Methods: A pretrained three channel DDPM, sourced from Hugging Face, was fine tuned on a private dataset of 11020 screening mammograms to generate paired craniocaudal (CC) and mediolateral oblique (MLO) views. Three third channel encodings of the CC and MLO views were evaluated: sum, absolute difference, and zero channel. Each model produced 500 synthetic image pairs. Quantitative assessment involved breast mask segmentation using Intersection over Union (IoU) and Dice Similarity Coefficient (DSC), with distributional comparisons against 2500 real pairs using Earth Movers Distance (EMD) and Kolmogorov Smirnov (KS) tests. Qualitative evaluation included a visual Turing test by a non expert radiologist to assess cross view consistency and artifacts. Results: Synthetic mammograms showed IoU and DSC distributions comparable to real images, with EMD and KS values (0.020 and 0.077 respectively). Models using sum or absolute difference encodings outperformed others in IoU and DSC (p < 0.001), though distributions remained broadly similar. Generated CC and MLO views maintained cross view consistency, with 6 to 8 percent of synthetic images exhibiting artifacts consistent with those in the training data. Conclusion: Three channel DDPMs can generate realistic and anatomically consistent dual view mammograms with promising applications in dataset augmentation.