Multi-Conditioned Denoising Diffusion Probabilistic Model (mDDPM) for Medical Image Synthesis
This addresses the problem of limited annotated training data for medical imaging applications, offering a controlled generation framework to enhance dataset diversity and accuracy, though it is incremental as it builds upon existing diffusion models with multi-conditioning.
The paper tackles the challenge of generating diverse and accurate annotated medical images for training deep learning models by proposing a multi-conditioned denoising diffusion probabilistic model (mDDPM) for lung CT synthesis. The result is that the generated images can fool experts into perceiving them as real and surpass nearly every state-of-the-art model in anatomical consistency when trained on comparable large datasets.
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.