用扩散模型生成逼真乳腺双视角影像，提升数据多样性。
MammoRGB: Dual-View Mammogram Synthesis Using Denoising Diffusion Probabilistic Models
- 三通道扩散模型融合双视图信息，通过加和或差值编码提升一致性。
- 生成图像在分割重叠度与分布上接近真实数据（IoU/DSC相似，EMD=0.020）。
- 适合医学影像数据增强，尤其缺样本的乳腺筛查研究者。
目的：开发并评估一种三通道去噪扩散概率模型（DDPM），用于合成单个乳腺的双视角乳腺钼靶图像，并分析通道表示对图像保真度和跨视图一致性的影响。方法：基于Hugging Face预训练的三通道DDPM，在包含11020张筛查乳腺钼靶的私有数据集上进行微调，生成配对的头尾向（CC）与内外斜向（MLO）视图。评估了三种第三通道编码方式：相加、绝对差值和零通道。每种模型生成500对合成图像。定量评估采用交并比（IoU）和骰子相似系数（DSC）进行乳腺掩码分割，并使用地球移动距离（EMD）与科莫戈罗夫-斯米尔诺夫检验（KS）对比2500对真实图像分布。定性评估由非专业放射科医生进行视觉图灵测试，以判断跨视图一致性和伪影。结果：合成图像的IoU与DSC分布与真实图像相当，EMD与KS值分别为0.020与0.077。采用相加或绝对差值编码的模型在IoU与DSC上显著优于其他模型（p < 0.001），但整体分布仍相近。生成的CC与MLO视图保持良好跨视图一致性，6至8%的合成图像存在与训练数据一致的伪影。结论：三通道DDPM可生成真实且解剖结构一致的双视角乳腺钼靶图像，具有在数据集扩充中的潜在应用价值。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。