Paired Diffusion: Generation of related, synthetic PET-CT-Segmentation scans using Linked Denoising Diffusion Probabilistic Models (2403.17734v1)
Abstract: The rapid advancement of AI in biomedical imaging and radiotherapy is hindered by the limited availability of large imaging data repositories. With recent research and improvements in denoising diffusion probabilistic models (DDPM), high quality synthetic medical scans are now possible. Despite this, there is currently no way of generating multiple related images, such as a corresponding ground truth which can be used to train models, so synthetic scans are often manually annotated before use. This research introduces a novel architecture that is able to generate multiple, related PET-CT-tumour mask pairs using paired networks and conditional encoders. Our approach includes innovative, time step-controlled mechanisms and a `noise-seeding' strategy to improve DDPM sampling consistency. While our model requires a modified perceptual loss function to ensure accurate feature alignment we show generation of clearly aligned synthetic images and improvement in segmentation accuracy with generated images.
- “Impact of target volume segmentation accuracy and variability on treatment planning for 4D-CT-based non-small cell lung cancer radiotherapy,” Acta Oncologica, vol. 54, no. 3, pp. 322–332, Oct. 2014.
- Simon Lewis Duke, Assessing and Teaching Radiotherapy Contouring, Ph.D. thesis, The University of Nottingham, Medical Education Centre, School of Medicine, March 2021.
- “Evaluating target volume delineation in the era of precision radiotherapy: FRCR, revalidation and beyond,” Clinical Oncology, vol. 29, no. 7, pp. 436–438, July 2017.
- “Advances in auto-segmentation,” Seminars in Radiation Oncology, vol. 29, no. 3, pp. 185–197, July 2019.
- “Octree boundary transfiner: Efficient transformers for tumor segmentation refinement,” in Head and Neck Tumor Segmentation and Outcome Prediction 2022, Berlin, Heidelberg, 2023, p. 54–60, Springer-Verlag.
- “Denoising diffusion probabilistic models,” Advances in neural information processing systems, vol. 33, pp. 6840–6851, 2020.
- “Medical diffusion: Denoising diffusion probabilistic models for 3D medical image generation,” 2022.
- “Conditional diffusion models for semantic 3D medical image synthesis,” July 2023.
- Head and Neck Tumor Segmentation and Outcome Prediction, Springer Nature Switzerland, 2023.
- “Brain tumor segmentation using synthetic MR images – a comparison of GANs and diffusion models,” 2023.
- “Denoising diffusion medical models,” 2023.
- “HaN-seg: The head and neck organ-at-risk CT and MR segmentation dataset,” Medical Physics, vol. 50, no. 3, pp. 1917–1927, Jan. 2023.
- “Swin UNETR for tumor and lymph node segmentation using 3D PET/CT imaging: A transfer learning approach,” in Lecture Notes in Computer Science, pp. 114–120. Springer Nature Switzerland, 2023.
- “Multimodal PET/CT tumour segmentation and prediction of progression-free survival using a full-scale UNet with attention,” in 3D Head and Neck Tumor Segmentation in PET/CT Challenge, pp. 189–201. Springer, 2021.
- “Medsegdiff: Medical image segmentation with diffusion probabilistic model,” in Medical Imaging with Deep Learning. PMLR, 2024, pp. 1623–1639.
- Nicholas Guttenberg, “Diffusion with offset noise: Fine-tuning against a modified noise, enables stable diffusion to generate very dark or light images easily,” Jan. 2023, Blog posted by company Cross Labs.
- “DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps,” Advances in Neural Information Processing Systems, vol. 35, pp. 5775–5787, 2022.