CH-DDPMs: A Conjugate and Hybrid Diffusion Model for Low-Dose Fat CT Image Segmentation
Denoising Diffusion Probabilistic Models (DDPMs) have attracted much attention as a powerful generative model and have been widely used in the field of computer vision. In the field of medical images, the noise contained in low-dose images often poses a challenge to deep learning methods, so we propose a Conjugate and Hybrid Diffusion Model (CH-DDPMs) for the task of low-dose fat CT image segmentation. CH-DDPMs is a kind of DDPMs integrated with a DnCNN module. It solves the problem of the noise interference in the low-dose fat CT images. CH-DDPMs achieves better results than other models in images with different noise levels, which can help doctors diagnose MetS more effectively.
Authors
- Hongzan Sun (ORCID: https://orcid.org/0000-0002-4724-5828)
- Marcin Grzegorzek (ORCID: https://orcid.org/0000-0003-4877-8287)
- Tianming Du (ORCID: https://orcid.org/0000-0001-7671-6513)
- Zhihao Chen (ORCID: https://orcid.org/0000-0002-6906-813X)
- Chen Li (ORCID: https://orcid.org/0000-0003-1545-8885)
- Tao Jiang (ORCID: https://orcid.org/0000-0001-8296-3027)
- Yihao Sun
- Ning Xu (ORCID: https://orcid.org/0000-0002-2554-4309)
Institutions
- Liaoning Shihua University (CN)
- Chengdu University of Traditional Chinese Medicine (CN)
- China Medical University (CN)
- Northeastern University (CN)
- University of Lübeck (DE)
Publication Details
- Published
- 2024-12-03
- DOI
- https://doi.org/10.1109/bibm62325.2024.10821733
- Citations
- 2
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.81
Funders
- National Natural Science Foundation of China