Unsupervised OCT image despeckling with ground-truth- and repeated-scanning-free features
Optical coherence tomography (OCT) can resolve biological three-dimensional tissue structures, but it is inevitably plagued by speckle noise that degrades image quality and obscures biological structure. Recently unsupervised deep learning methods are becoming more popular in OCT despeckling but the...
| Main Authors: | , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/179827 |
| _version_ | 1826121051018362880 |
|---|---|
| author | Wu, Renxiong Huang, Shaoyan Zhong, Junming Zheng, Fei Li, Meixuan Ge, Xin Zhong, Jie Liu, Linbo Ni, Guangming Liu, Yong |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Wu, Renxiong Huang, Shaoyan Zhong, Junming Zheng, Fei Li, Meixuan Ge, Xin Zhong, Jie Liu, Linbo Ni, Guangming Liu, Yong |
| author_sort | Wu, Renxiong |
| collection | NTU |
| description | Optical coherence tomography (OCT) can resolve biological three-dimensional tissue structures, but it is inevitably plagued by speckle noise that degrades image quality and obscures biological structure. Recently unsupervised deep learning methods are becoming more popular in OCT despeckling but they still have to use unpaired noisy-clean images or paired noisy-noisy images. To address the above problem, we propose what we believe to be a novel unsupervised deep learning method for OCT despeckling, termed Double-free Net, which eliminates the need for ground truth data and repeated scanning by sub-sampling noisy images and synthesizing noisier images. In comparison to existing unsupervised methods, Double-free Net obtains superior denoising performance when trained on datasets comprising retinal and human tissue images without clean images. The efficacy of Double-free Net in denoising holds significant promise for diagnostic applications in retinal pathologies and enhances the accuracy of retinal layer segmentation. Results demonstrate that Double-free Net outperforms state-of-the-art methods and exhibits strong convenience and adaptability across different OCT images. |
| first_indexed | 2024-10-01T05:26:25Z |
| format | Journal Article |
| id | ntu-10356/179827 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:26:25Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1798272024-08-30T15:40:20Z Unsupervised OCT image despeckling with ground-truth- and repeated-scanning-free features Wu, Renxiong Huang, Shaoyan Zhong, Junming Zheng, Fei Li, Meixuan Ge, Xin Zhong, Jie Liu, Linbo Ni, Guangming Liu, Yong School of Electrical and Electronic Engineering Engineering Image despeckling Speckle noise Optical coherence tomography (OCT) can resolve biological three-dimensional tissue structures, but it is inevitably plagued by speckle noise that degrades image quality and obscures biological structure. Recently unsupervised deep learning methods are becoming more popular in OCT despeckling but they still have to use unpaired noisy-clean images or paired noisy-noisy images. To address the above problem, we propose what we believe to be a novel unsupervised deep learning method for OCT despeckling, termed Double-free Net, which eliminates the need for ground truth data and repeated scanning by sub-sampling noisy images and synthesizing noisier images. In comparison to existing unsupervised methods, Double-free Net obtains superior denoising performance when trained on datasets comprising retinal and human tissue images without clean images. The efficacy of Double-free Net in denoising holds significant promise for diagnostic applications in retinal pathologies and enhances the accuracy of retinal layer segmentation. Results demonstrate that Double-free Net outperforms state-of-the-art methods and exhibits strong convenience and adaptability across different OCT images. Ministry of Education (MOE) Ministry of Health (MOH) National Medical Research Council (NMRC) Published version National Natural Science Foundation of China (61905036); China Postdoctoral Science Foundation (2019M663465, 2021T140090); Medico-Engineering Cooperation Funds from University of Electronic Science and Technology of China (ZYGX2021YGCX019); Fundamental Research Funds for the Central Universities (ZYGX2021J012); Ministry of Education Singapore under its Academic Research Fund Tier 2 (MOE-T2EP30120-0001); Ministry of Education Singapore under its Academic Research Fund Tier 1 (RG35/22); Singapore Ministry of Health’s National Medical Research Council under its Open Fund Individual Research Grant (MOH-OFIRG19may-0009); Key Research and Development Project of Health Commission of Sichuan Province (ZH2024-201). 2024-08-27T00:36:48Z 2024-08-27T00:36:48Z 2024 Journal Article Wu, R., Huang, S., Zhong, J., Zheng, F., Li, M., Ge, X., Zhong, J., Liu, L., Ni, G. & Liu, Y. (2024). Unsupervised OCT image despeckling with ground-truth- and repeated-scanning-free features. Optics Express, 32(7), 11934-11951. https://dx.doi.org/10.1364/OE.510696 1094-4087 https://hdl.handle.net/10356/179827 10.1364/OE.510696 38571030 2-s2.0-85188987785 7 32 11934 11951 en MOE-T2EP30120-0001 RG35/22 MOH-OFIRG19may-0009 Optics Express © 2024 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement. application/pdf |
| spellingShingle | Engineering Image despeckling Speckle noise Wu, Renxiong Huang, Shaoyan Zhong, Junming Zheng, Fei Li, Meixuan Ge, Xin Zhong, Jie Liu, Linbo Ni, Guangming Liu, Yong Unsupervised OCT image despeckling with ground-truth- and repeated-scanning-free features |
| title | Unsupervised OCT image despeckling with ground-truth- and repeated-scanning-free features |
| title_full | Unsupervised OCT image despeckling with ground-truth- and repeated-scanning-free features |
| title_fullStr | Unsupervised OCT image despeckling with ground-truth- and repeated-scanning-free features |
| title_full_unstemmed | Unsupervised OCT image despeckling with ground-truth- and repeated-scanning-free features |
| title_short | Unsupervised OCT image despeckling with ground-truth- and repeated-scanning-free features |
| title_sort | unsupervised oct image despeckling with ground truth and repeated scanning free features |
| topic | Engineering Image despeckling Speckle noise |
| url | https://hdl.handle.net/10356/179827 |
| work_keys_str_mv | AT wurenxiong unsupervisedoctimagedespecklingwithgroundtruthandrepeatedscanningfreefeatures AT huangshaoyan unsupervisedoctimagedespecklingwithgroundtruthandrepeatedscanningfreefeatures AT zhongjunming unsupervisedoctimagedespecklingwithgroundtruthandrepeatedscanningfreefeatures AT zhengfei unsupervisedoctimagedespecklingwithgroundtruthandrepeatedscanningfreefeatures AT limeixuan unsupervisedoctimagedespecklingwithgroundtruthandrepeatedscanningfreefeatures AT gexin unsupervisedoctimagedespecklingwithgroundtruthandrepeatedscanningfreefeatures AT zhongjie unsupervisedoctimagedespecklingwithgroundtruthandrepeatedscanningfreefeatures AT liulinbo unsupervisedoctimagedespecklingwithgroundtruthandrepeatedscanningfreefeatures AT niguangming unsupervisedoctimagedespecklingwithgroundtruthandrepeatedscanningfreefeatures AT liuyong unsupervisedoctimagedespecklingwithgroundtruthandrepeatedscanningfreefeatures |