Physics-Based Practical Speckle Noise Modeling for Optical Coherence Tomography Image Denoising
Optical coherence tomography (OCT) has been extensively utilized in the field of biomedical imaging due to its non-invasive nature and its ability to provide high-resolution, in-depth imaging of biological tissues. However, the use of low-coherence light can lead to unintended interference phenomena...
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | English |
| Veröffentlicht: |
MDPI AG
2024-06-01
|
| Schriftenreihe: | Photonics |
| Schlagworte: | |
| Online Zugang: | https://www.mdpi.com/2304-6732/11/6/569 |
| _version_ | 1827208760147312640 |
|---|---|
| author | Lei Yang Di Wu Wenteng Gao Ronald X. Xu Mingzhai Sun |
| author_facet | Lei Yang Di Wu Wenteng Gao Ronald X. Xu Mingzhai Sun |
| author_sort | Lei Yang |
| collection | DOAJ |
| description | Optical coherence tomography (OCT) has been extensively utilized in the field of biomedical imaging due to its non-invasive nature and its ability to provide high-resolution, in-depth imaging of biological tissues. However, the use of low-coherence light can lead to unintended interference phenomena within the sample, which inevitably introduces speckle noise into the imaging results. This type of noise often obscures key features in the image, thereby reducing the accuracy of medical diagnoses. Existing denoising algorithms, while removing noise, tend to also damage the structural details of the image, affecting the quality of diagnosis. To overcome this challenge, we have proposed a speckle noise (PSN) framework. The core of this framework is an innovative dual-module noise generator that can decompose the noise in OCT images into speckle noise and equipment noise, addressing each type independently. By integrating the physical properties of noise into the design of the noise generator and training it with unpaired data, we are able to synthesize realistic noise images that match clear images. These synthesized paired images are then used to train a denoiser to effectively denoise real OCT images. Our method has demonstrated its superiority in both private and public datasets, particularly in maintaining the integrity of the image structure. This study emphasizes the importance of considering the physical information of noise in denoising tasks, providing a new perspective and solution for enhancing OCT image denoising technology. |
| first_indexed | 2025-03-21T13:01:05Z |
| format | Article |
| id | doaj.art-b51c1fc993224d06bca365d5de9881d8 |
| institution | Directory Open Access Journal |
| issn | 2304-6732 |
| language | English |
| last_indexed | 2025-03-21T13:01:05Z |
| publishDate | 2024-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Photonics |
| spelling | doaj.art-b51c1fc993224d06bca365d5de9881d82024-06-26T15:05:13ZengMDPI AGPhotonics2304-67322024-06-0111656910.3390/photonics11060569Physics-Based Practical Speckle Noise Modeling for Optical Coherence Tomography Image DenoisingLei Yang0Di Wu1Wenteng Gao2Ronald X. Xu3Mingzhai Sun4Department of Precision Machinery and Instruments, University of Science and Technology of China, Hefei 230026, ChinaSuzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou 215123, ChinaDepartment of Precision Machinery and Instruments, University of Science and Technology of China, Hefei 230026, ChinaSuzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou 215123, ChinaSuzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou 215123, ChinaOptical coherence tomography (OCT) has been extensively utilized in the field of biomedical imaging due to its non-invasive nature and its ability to provide high-resolution, in-depth imaging of biological tissues. However, the use of low-coherence light can lead to unintended interference phenomena within the sample, which inevitably introduces speckle noise into the imaging results. This type of noise often obscures key features in the image, thereby reducing the accuracy of medical diagnoses. Existing denoising algorithms, while removing noise, tend to also damage the structural details of the image, affecting the quality of diagnosis. To overcome this challenge, we have proposed a speckle noise (PSN) framework. The core of this framework is an innovative dual-module noise generator that can decompose the noise in OCT images into speckle noise and equipment noise, addressing each type independently. By integrating the physical properties of noise into the design of the noise generator and training it with unpaired data, we are able to synthesize realistic noise images that match clear images. These synthesized paired images are then used to train a denoiser to effectively denoise real OCT images. Our method has demonstrated its superiority in both private and public datasets, particularly in maintaining the integrity of the image structure. This study emphasizes the importance of considering the physical information of noise in denoising tasks, providing a new perspective and solution for enhancing OCT image denoising technology.https://www.mdpi.com/2304-6732/11/6/569optical coherence tomography (OCT)noise synthesisphysical priorimage denoisingdeep learning |
| spellingShingle | Lei Yang Di Wu Wenteng Gao Ronald X. Xu Mingzhai Sun Physics-Based Practical Speckle Noise Modeling for Optical Coherence Tomography Image Denoising Photonics optical coherence tomography (OCT) noise synthesis physical prior image denoising deep learning |
| title | Physics-Based Practical Speckle Noise Modeling for Optical Coherence Tomography Image Denoising |
| title_full | Physics-Based Practical Speckle Noise Modeling for Optical Coherence Tomography Image Denoising |
| title_fullStr | Physics-Based Practical Speckle Noise Modeling for Optical Coherence Tomography Image Denoising |
| title_full_unstemmed | Physics-Based Practical Speckle Noise Modeling for Optical Coherence Tomography Image Denoising |
| title_short | Physics-Based Practical Speckle Noise Modeling for Optical Coherence Tomography Image Denoising |
| title_sort | physics based practical speckle noise modeling for optical coherence tomography image denoising |
| topic | optical coherence tomography (OCT) noise synthesis physical prior image denoising deep learning |
| url | https://www.mdpi.com/2304-6732/11/6/569 |
| work_keys_str_mv | AT leiyang physicsbasedpracticalspecklenoisemodelingforopticalcoherencetomographyimagedenoising AT diwu physicsbasedpracticalspecklenoisemodelingforopticalcoherencetomographyimagedenoising AT wentenggao physicsbasedpracticalspecklenoisemodelingforopticalcoherencetomographyimagedenoising AT ronaldxxu physicsbasedpracticalspecklenoisemodelingforopticalcoherencetomographyimagedenoising AT mingzhaisun physicsbasedpracticalspecklenoisemodelingforopticalcoherencetomographyimagedenoising |