Conference item
Paired diffusion: generation of related, synthetic PET-CT-segmentation scans using linked denoising diffusion probabilistic models
- Abstract:
- The rapid advancement of Artificial Intelligence (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.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Accepted manuscript, pdf, 1020.3KB, Terms of use)
-
- Publisher copy:
- 10.1109/ISBI56570.2024.10635593
Authors
- Publisher:
- IEEE
- Host title:
- Proceedings of the 21st IEEE International Symposium on Biomedical Imaging (ISBI 2024)
- Pages:
- 1-5
- Publication date:
- 2024-08-22
- Acceptance date:
- 2024-01-26
- Event title:
- 21st IEEE International Symposium on Biomedical Imaging (ISBI 2024)
- Event location:
- Athens, Greece
- Event website:
- https://biomedicalimaging.org/2024/
- Event start date:
- 2024-05-27
- Event end date:
- 2024-05-30
- DOI:
- EISSN:
-
1945-8452
- ISSN:
-
1945-7928
- EISBN:
- 9798350313338
- ISBN:
- 9798350313345
- Language:
-
English
- Keywords:
- Pubs id:
-
2030609
- UUID:
-
uuid_e27b4f8a-83a2-4d1c-967d-f34006179cdc
- Local pid:
-
pubs:2030609
- Deposit date:
-
2025-12-14
Terms of use
- Copyright holder:
- IEEE
- Copyright date:
- 2024
- Rights statement:
- © 2024 IEEE
- Notes:
- The author accepted manuscript (AAM) of this paper has been made available under the University of Oxford's Open Access Publications Policy, and a CC BY public copyright licence has been applied.
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record