Deep learning-based label-free imaging of lymphatics and aqueous veins in the eye using optical coherence tomography
Abstract We demonstrate an adaptation of deep learning for label-free imaging of the micro-scale lymphatic vessels and aqueous veins in the eye using optical coherence tomography (OCT). The proposed deep learning-based OCT lymphangiography (DL-OCTL) method was trained, validated and tested, using OC...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-03-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-56273-1 |
| _version_ | 1797259300839620608 |
|---|---|
| author | Peijun Gong Xiaolan Tang Junying Chen Haijun You Yuxing Wang Paula K. Yu Dao-Yi Yu Barry Cense |
| author_facet | Peijun Gong Xiaolan Tang Junying Chen Haijun You Yuxing Wang Paula K. Yu Dao-Yi Yu Barry Cense |
| author_sort | Peijun Gong |
| collection | DOAJ |
| description | Abstract We demonstrate an adaptation of deep learning for label-free imaging of the micro-scale lymphatic vessels and aqueous veins in the eye using optical coherence tomography (OCT). The proposed deep learning-based OCT lymphangiography (DL-OCTL) method was trained, validated and tested, using OCT scans (23 volumetric scans comprising 19,736 B-scans) from 11 fresh ex vivo porcine eyes with the corresponding vessel labels generated by a conventional OCT lymphangiography (OCTL) method based on thresholding with attenuation compensation. Compared to conventional OCTL, the DL-OCTL method demonstrates comparable results for imaging lymphatics and aqueous veins in the eye, with an Intersection over Union value of 0.79 ± 0.071 (mean ± standard deviation). In addition, DL-OCTL mitigates the imaging artifacts in conventional OCTL where the OCT signal modelling was corrupted by the tissue heterogeneity, provides ~ 10 times faster processing based on a rough comparison and does not require OCT-related knowledge for correct implementation as in conventional OCTL. With these favorable features, DL-OCTL promises to improve the practicality of OCTL for label-free imaging of lymphatics and aqueous veins for preclinical and clinical imaging applications. |
| first_indexed | 2024-04-24T23:07:15Z |
| format | Article |
| id | doaj.art-a81b71a505ab4b46896f8ec03e68325c |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-24T23:07:15Z |
| publishDate | 2024-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-a81b71a505ab4b46896f8ec03e68325c2024-03-17T12:26:33ZengNature PortfolioScientific Reports2045-23222024-03-0114111210.1038/s41598-024-56273-1Deep learning-based label-free imaging of lymphatics and aqueous veins in the eye using optical coherence tomographyPeijun Gong0Xiaolan Tang1Junying Chen2Haijun You3Yuxing Wang4Paula K. Yu5Dao-Yi Yu6Barry Cense7Key Laboratory for Biomedical Engineering of Ministry of Education, Zhejiang UniversitySchool of Software Engineering, South China University of TechnologySchool of Software Engineering, South China University of TechnologySchool of Software Engineering, South China University of TechnologyKey Laboratory for Biomedical Engineering of Ministry of Education, Zhejiang UniversityCentre for Ophthalmology and Visual Science, The University of Western AustraliaCentre for Ophthalmology and Visual Science, The University of Western AustraliaDepartment of Electrical, Electronic and Computer Engineering, School of Engineering, The University of Western AustraliaAbstract We demonstrate an adaptation of deep learning for label-free imaging of the micro-scale lymphatic vessels and aqueous veins in the eye using optical coherence tomography (OCT). The proposed deep learning-based OCT lymphangiography (DL-OCTL) method was trained, validated and tested, using OCT scans (23 volumetric scans comprising 19,736 B-scans) from 11 fresh ex vivo porcine eyes with the corresponding vessel labels generated by a conventional OCT lymphangiography (OCTL) method based on thresholding with attenuation compensation. Compared to conventional OCTL, the DL-OCTL method demonstrates comparable results for imaging lymphatics and aqueous veins in the eye, with an Intersection over Union value of 0.79 ± 0.071 (mean ± standard deviation). In addition, DL-OCTL mitigates the imaging artifacts in conventional OCTL where the OCT signal modelling was corrupted by the tissue heterogeneity, provides ~ 10 times faster processing based on a rough comparison and does not require OCT-related knowledge for correct implementation as in conventional OCTL. With these favorable features, DL-OCTL promises to improve the practicality of OCTL for label-free imaging of lymphatics and aqueous veins for preclinical and clinical imaging applications.https://doi.org/10.1038/s41598-024-56273-1 |
| spellingShingle | Peijun Gong Xiaolan Tang Junying Chen Haijun You Yuxing Wang Paula K. Yu Dao-Yi Yu Barry Cense Deep learning-based label-free imaging of lymphatics and aqueous veins in the eye using optical coherence tomography Scientific Reports |
| title | Deep learning-based label-free imaging of lymphatics and aqueous veins in the eye using optical coherence tomography |
| title_full | Deep learning-based label-free imaging of lymphatics and aqueous veins in the eye using optical coherence tomography |
| title_fullStr | Deep learning-based label-free imaging of lymphatics and aqueous veins in the eye using optical coherence tomography |
| title_full_unstemmed | Deep learning-based label-free imaging of lymphatics and aqueous veins in the eye using optical coherence tomography |
| title_short | Deep learning-based label-free imaging of lymphatics and aqueous veins in the eye using optical coherence tomography |
| title_sort | deep learning based label free imaging of lymphatics and aqueous veins in the eye using optical coherence tomography |
| url | https://doi.org/10.1038/s41598-024-56273-1 |
| work_keys_str_mv | AT peijungong deeplearningbasedlabelfreeimagingoflymphaticsandaqueousveinsintheeyeusingopticalcoherencetomography AT xiaolantang deeplearningbasedlabelfreeimagingoflymphaticsandaqueousveinsintheeyeusingopticalcoherencetomography AT junyingchen deeplearningbasedlabelfreeimagingoflymphaticsandaqueousveinsintheeyeusingopticalcoherencetomography AT haijunyou deeplearningbasedlabelfreeimagingoflymphaticsandaqueousveinsintheeyeusingopticalcoherencetomography AT yuxingwang deeplearningbasedlabelfreeimagingoflymphaticsandaqueousveinsintheeyeusingopticalcoherencetomography AT paulakyu deeplearningbasedlabelfreeimagingoflymphaticsandaqueousveinsintheeyeusingopticalcoherencetomography AT daoyiyu deeplearningbasedlabelfreeimagingoflymphaticsandaqueousveinsintheeyeusingopticalcoherencetomography AT barrycense deeplearningbasedlabelfreeimagingoflymphaticsandaqueousveinsintheeyeusingopticalcoherencetomography |