用多条件扩散模型生成逼真肺部CT图像，提升医学影像合成的可控性与真实性
Multi-Conditioned Denoising Diffusion Probabilistic Model (mDDPM) for Medical Image Synthesis
- 基于无分类器采样策略，实现多条件控制的肺部CT图像生成
- 生成图像在专家评估中近乎以假乱真，解剖结构一致性优于现有方法
- 适合需要高质量合成医学影像的研究者，尤其关注数据增强与生成建模
医学影像应用在人体解剖、病理特征和成像领域具有高度专业性。因此，训练深度学习模型所需的标注数据集不仅需高精度，还需足够多样和庞大，以覆盖几乎所有可能的临床实例。我们提出一种受控生成框架，通过输入多重条件来生成带标注的合成图像，从而促进这一目标的实现。采用去噪扩散概率模型（DDPM）在肺部CT领域训练大规模生成模型，并拓展无分类器采样策略，展示该生成框架的可行性。实验表明，该方法生成的肺部CT图像能忠实反映解剖结构，专家难以辨别真伪。在使用可比大型医学数据集训练的前提下，该方法在生成图像的解剖一致性方面几乎超越所有现有先进生成模型。
原文摘要 · Abstract (English)
Medical imaging applications are highly specialized in terms of human anatomy, pathology, and imaging domains. Therefore, annotated training datasets for training deep learning applications in medical imaging not only need to be highly accurate but also diverse and large enough to encompass almost all plausible examples with respect to those specifications. We argue that achieving this goal can be facilitated through a controlled generation framework for synthetic images with annotations, requiring multiple conditional specifications as input to provide control. We employ a Denoising Diffusion Probabilistic Model (DDPM) to train a large-scale generative model in the lung CT domain and expand upon a classifier-free sampling strategy to showcase one such generation framework. We show that our approach can produce annotated lung CT images that can faithfully represent anatomy, convincingly fooling experts into perceiving them as real. Our experiments demonstrate that controlled generative frameworks of this nature can surpass nearly every state-of-the-art image generative model in achieving anatomical consistency in generated medical images when trained on comparable large medical datasets.
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。