Med-cDiff: Conditional Medical Image Generation with Diffusion Models
Conditional image generation plays a vital role in medical image analysis as it is effective in tasks such as super-resolution, denoising, and inpainting, among others. Diffusion models have been shown to perform at a state-of-the-art level in natural image generation, but they have not been thoroug...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/10/11/1258 |
| _version_ | 1797460130737946624 |
|---|---|
| author | Alex Ling Yu Hung Kai Zhao Haoxin Zheng Ran Yan Steven S. Raman Demetri Terzopoulos Kyunghyun Sung |
| author_facet | Alex Ling Yu Hung Kai Zhao Haoxin Zheng Ran Yan Steven S. Raman Demetri Terzopoulos Kyunghyun Sung |
| author_sort | Alex Ling Yu Hung |
| collection | DOAJ |
| description | Conditional image generation plays a vital role in medical image analysis as it is effective in tasks such as super-resolution, denoising, and inpainting, among others. Diffusion models have been shown to perform at a state-of-the-art level in natural image generation, but they have not been thoroughly studied in medical image generation with specific conditions. Moreover, current medical image generation models have their own problems, limiting their usage in various medical image generation tasks. In this paper, we introduce the use of conditional Denoising Diffusion Probabilistic Models (cDDPMs) for medical image generation, which achieve state-of-the-art performance on several medical image generation tasks. |
| first_indexed | 2024-03-09T17:01:41Z |
| format | Article |
| id | doaj.art-7f8ee9e64a8d47508131f79f06e32683 |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-09T17:01:41Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-7f8ee9e64a8d47508131f79f06e326832023-11-24T14:29:41ZengMDPI AGBioengineering2306-53542023-10-011011125810.3390/bioengineering10111258Med-cDiff: Conditional Medical Image Generation with Diffusion ModelsAlex Ling Yu Hung0Kai Zhao1Haoxin Zheng2Ran Yan3Steven S. Raman4Demetri Terzopoulos5Kyunghyun Sung6Computer Science Department, University of California, Los Angeles, CA 90095, USADepartment of Radiology, University of California, Los Angeles, CA 90095, USAComputer Science Department, University of California, Los Angeles, CA 90095, USADepartment of Radiology, University of California, Los Angeles, CA 90095, USADepartment of Radiology, University of California, Los Angeles, CA 90095, USAComputer Science Department, University of California, Los Angeles, CA 90095, USADepartment of Radiology, University of California, Los Angeles, CA 90095, USAConditional image generation plays a vital role in medical image analysis as it is effective in tasks such as super-resolution, denoising, and inpainting, among others. Diffusion models have been shown to perform at a state-of-the-art level in natural image generation, but they have not been thoroughly studied in medical image generation with specific conditions. Moreover, current medical image generation models have their own problems, limiting their usage in various medical image generation tasks. In this paper, we introduce the use of conditional Denoising Diffusion Probabilistic Models (cDDPMs) for medical image generation, which achieve state-of-the-art performance on several medical image generation tasks.https://www.mdpi.com/2306-5354/10/11/1258image generationdiffusion modelsgenerative modelssuper-resolutiondenoisinginpainting |
| spellingShingle | Alex Ling Yu Hung Kai Zhao Haoxin Zheng Ran Yan Steven S. Raman Demetri Terzopoulos Kyunghyun Sung Med-cDiff: Conditional Medical Image Generation with Diffusion Models Bioengineering image generation diffusion models generative models super-resolution denoising inpainting |
| title | Med-cDiff: Conditional Medical Image Generation with Diffusion Models |
| title_full | Med-cDiff: Conditional Medical Image Generation with Diffusion Models |
| title_fullStr | Med-cDiff: Conditional Medical Image Generation with Diffusion Models |
| title_full_unstemmed | Med-cDiff: Conditional Medical Image Generation with Diffusion Models |
| title_short | Med-cDiff: Conditional Medical Image Generation with Diffusion Models |
| title_sort | med cdiff conditional medical image generation with diffusion models |
| topic | image generation diffusion models generative models super-resolution denoising inpainting |
| url | https://www.mdpi.com/2306-5354/10/11/1258 |
| work_keys_str_mv | AT alexlingyuhung medcdiffconditionalmedicalimagegenerationwithdiffusionmodels AT kaizhao medcdiffconditionalmedicalimagegenerationwithdiffusionmodels AT haoxinzheng medcdiffconditionalmedicalimagegenerationwithdiffusionmodels AT ranyan medcdiffconditionalmedicalimagegenerationwithdiffusionmodels AT stevensraman medcdiffconditionalmedicalimagegenerationwithdiffusionmodels AT demetriterzopoulos medcdiffconditionalmedicalimagegenerationwithdiffusionmodels AT kyunghyunsung medcdiffconditionalmedicalimagegenerationwithdiffusionmodels |